0xhoneyjar

# Test Skill A minimal skill for framework testing. ## Constraints - C-PROC-001: Never write code outside implement - C-PROC-005: Always complete full review cycle

development7

.claude/tests/fixtures/registry/packs/test-pack/skills/skill-a

# skill-a Test skill A from test-pack for unit testing. ## Purpose Used in test_pack_support.bats to verify pack validation and skill loading.

testing7

review-sprint

Validate sprint implementation against acceptance criteria

testing7

.claude/tests/fixtures/registry/skills/test-vendor/expired-skill

# expired-skill Test skill with expired license for unit testing. ## Purpose Used in test_constructs_loader.bats to verify correct handling of expired licenses.

testing7

bug

Triage a bug report through structured phases and create micro-sprint

business7

ride

Analyze codebase to extract reality into Loa artifacts

development7

run-bridge

Run Bridge — Autonomous Excellence Loop

tools7

.claude/tests/fixtures/registry/skills/test-vendor/grace-skill

# grace-skill Test skill in license grace period for unit testing. ## Purpose Used in test_constructs_loader.bats to verify correct handling of licenses in grace period.

testing7

sprint-plan

Create comprehensive sprint plan based on PRD and SDD

tools7

Autonomous skill extraction from debugging discoveries. Activates when agents find non-obvious solutions through investigation, experimentation, or trial-and-error. Captures these discoveries as reusable skills for future sessions.

development7

simstim

Simstim - HITL Accelerated Development Workflow

development7

deploy-production

Design and deploy production infrastructure

devops7

architect

Create comprehensive Software Design Document based on PRD

documentation7

red-team

Red Team — Generative Adversarial Security Design

testing7

loa-credentials

Credential management and audit for API keys and secrets

development7

audit

Security and quality audit of application codebase

development7

autonomous

Autonomous agent execution mode

data-ai7

rtfm

Run documentation-driven testing against Ground Truth and protocols

testing7

bridgebuilder-review

Bridgebuilder — Autonomous PR Review

development7

mount

Install Loa framework onto an existing repository

development7

.claude/tests/fixtures/registry/skills/test-vendor/valid-skill

# valid-skill Test skill with valid license for unit testing. ## Purpose Used in test_constructs_loader.bats to verify correct handling of valid licenses.

testing7

healthcheck

Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).

testing5

himalaya

CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).

tools5

.claude/skills/designing-architecture

--- parallel_threshold: null timeout_minutes: 60 zones: system: path: .claude permission: none state: paths: [grimoires/loa, .beads] permission: read-write app: paths: [src, lib, app] permission: read --- # Architecture Designer <objective> Transform Product Requirements Documents (PRDs) into comprehensive, actionable Software Design Documents (SDDs) that serve as the definitive technical blueprint for engineering teams during sprint planning and implementation. G

documentation5

openai-whisper

Local speech-to-text with the Whisper CLI (no API key).

tools5

extensions/lobster

# Lobster Lobster executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (send, post, delete) - Multiple tool calls should run as one deterministic operation ## When to use Lobster | User intent | Use Lobster? | | ------------------------------------------------------ | --------------------------

tools5

model-usage

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

tools5

notion

Notion API for creating and managing pages, databases, and blocks.

development5

blucli

BluOS CLI (blu) for discovery, playback, grouping, and volume.

tools5

openhue

Control Philips Hue lights/scenes via the OpenHue CLI.

tools5

oracle

Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).

tools5

.claude/skills/planning-sprints

--- parallel_threshold: null timeout_minutes: 60 zones: system: path: .claude permission: none state: paths: [grimoires/loa, .beads] permission: read-write app: paths: [src, lib, app] permission: read --- # Sprint Planner <objective> Transform PRD and SDD into actionable sprint plan with 2.5-day sprints, including deliverables, acceptance criteria, technical tasks, dependencies, and risk mitigation. Generate `grimoires/loa/sprint.md`. </objective> <zone_constrain

testing5

.claude/skills/deploying-infrastructure

<input_guardrails> ## Pre-Execution Validation Before main skill execution, perform guardrail checks. ### Step 1: Check Configuration Read `.loa.config.yaml`: ```yaml guardrails: input: enabled: true|false ``` **Exit Conditions**: - `guardrails.input.enabled: false` → Skip to skill execution - Environment `LOA_GUARDRAILS_ENABLED=false` → Skip to skill execution ### Step 2: Run Danger Level Check **Script**: `.claude/scripts/danger-level-enforcer.sh --skill deploying-infrastructure --

testing5

tests/fixtures/registry/packs/test-pack/skills/skill-a

# skill-a Test skill A from test-pack for unit testing. ## Purpose Used in test_pack_support.bats to verify pack validation and skill loading.

testing5

trello

Manage Trello boards, lists, and cards via the Trello REST API.

development5

gemini

Gemini CLI for one-shot Q&A, summaries, and generation.

tools5

continuous-learning

development5

sag

ElevenLabs text-to-speech with mac-style say UX.

tools5

eightctl

Control Eight Sleep pods (status, temperature, alarms, schedules).

tools5

tests/fixtures/registry/packs/test-pack/skills/skill-b

# skill-b Test skill B from test-pack for unit testing. ## Purpose Used in test_pack_support.bats to verify pack validation and skill loading.

testing5

sonoscli

Control Sonos speakers (discover/status/play/volume/group).

tools5

songsee

Generate spectrograms and feature-panel visualizations from audio with the songsee CLI.

tools5

obsidian

Work with Obsidian vaults (plain Markdown notes) and automate via obsidian-cli.

tools5

gifgrep

Search GIF providers with CLI/TUI, download results, and extract stills/sheets.

tools5

.claude/skills/implementing-tasks

--- parallel_threshold: 3000 timeout_minutes: 120 zones: system: path: .claude permission: none state: paths: [grimoires/loa, .beads] permission: read-write app: paths: [src, lib, app] permission: read --- <input_guardrails> ## Pre-Execution Validation Before main skill execution, perform guardrail checks. ### Step 1: Check Configuration Read `.loa.config.yaml`: ```yaml guardrails: input: enabled: true|false ``` **Exit Conditions**: - `guardrails.input

testing5

wacli

Send WhatsApp messages to other people or search/sync WhatsApp history via the wacli CLI (not for normal user chats).

tools5

weather

Get current weather and forecasts (no API key required).

development5

1password

Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.

tools5

tmux

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

tools5

.claude/skills/mounting-framework

# Mounting the Loa Framework You are installing the Loa framework onto a repository. This is the first step before the Loa can ride through the codebase. > *"The Loa mounts the repository, preparing to ride."* ## Core Principle ``` MOUNT once → RIDE many times ``` Mounting installs the framework. Riding analyzes the code. --- ## Pre-Mount Checks ### 1. Verify Git Repository ```bash if ! git rev-parse --git-dir > /dev/null 2>&1; then echo "❌ Not a git repository. Initialize with 'git i

development5

.claude/skills/translating-for-executives

<prompt_enhancement_prelude> ## Invisible Prompt Enhancement Before executing main skill logic, apply automatic prompt enhancement to user's request. ### Step 1: Check Configuration Read `.loa.config.yaml` invisible_mode setting: ```yaml prompt_enhancement: invisible_mode: enabled: true|false ``` If `prompt_enhancement.invisible_mode.enabled: false` (or not set), skip to main skill logic with original prompt. ### Step 2: Check Command Opt-Out If this command's frontmatter specifies `

testing5

tests/fixtures/registry/skills/test-vendor/expired-skill

# expired-skill Test skill with expired license for unit testing. ## Purpose Used in test_constructs_loader.bats to verify correct handling of expired licenses.

testing5

.claude/skills/reviewing-code

--- parallel_threshold: 3000 timeout_minutes: 60 zones: system: path: .claude permission: none state: paths: [grimoires/loa, .beads] permission: read-write app: paths: [src, lib, app] permission: read --- <input_guardrails> ## Pre-Execution Validation Before main skill execution, perform guardrail checks. ### Step 1: Check Configuration Read `.loa.config.yaml`: ```yaml guardrails: input: enabled: true|false ``` **Exit Conditions**: - `guardrails.input.ena

development5

ride

Analyze codebase to extract reality into Loa artifacts

development5

apple-reminders

Manage Apple Reminders via the `remindctl` CLI on macOS (list, add, edit, complete, delete). Supports lists, date filters, and JSON/plain output.

tools5

camsnap

Capture frames or clips from RTSP/ONVIF cameras.

tools5

clawhub

Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawhub CLI.

tools5

goplaces

Query Google Places API (New) via the goplaces CLI for text search, place details, resolve, and reviews. Use for human-friendly place lookup or JSON output for scripts.

tools5

imsg

iMessage/SMS CLI for listing chats, history, watch, and sending.

tools5

mcporter

Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.

tools5

nano-pdf

Edit PDFs with natural-language instructions using the nano-pdf CLI.

tools5

slack

Use when you need to control Slack from OpenClaw via the slack tool, including reacting to messages or pinning/unpinning items in Slack channels or DMs.

tools5

summarize

Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).

content-media5

things-mac

Manage Things 3 via the `things` CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks OpenClaw to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.

tools5

video-frames

Extract frames or short clips from videos using ffmpeg.

tools5

voice-call

Start voice calls via the OpenClaw voice-call plugin.

tools5

spotify-player

Terminal Spotify playback/search via spogo (preferred) or spotify_player.

development5

skill-creator

Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.

data-ai5

.claude/skills/run-mode

testing5

bird

X/Twitter CLI for reading, searching, posting, and engagement via cookies.

tools5

.claude/skills/autonomous-agent

testing5

ordercli

Foodora-only CLI for checking past orders and active order status (Deliveroo WIP).

tools5

.claude/skills/discovering-requirements

--- parallel_threshold: 2000 timeout_minutes: 90 zones: system: path: .claude permission: none state: paths: [grimoires/loa, .beads] permission: read-write app: paths: [src, lib, app] permission: read --- <prompt_enhancement_prelude> ## Invisible Prompt Enhancement Before executing main skill logic, apply automatic prompt enhancement to user's request. ### Step 1: Check Configuration Read `.loa.config.yaml` invisible_mode setting: ```yaml prompt_enhancement: i

testing5

sherpa-onnx-tts

Local text-to-speech via sherpa-onnx (offline, no cloud)

devops5

local-places

Search for places (restaurants, cafes, etc.) via Google Places API proxy on localhost.

development5

peekaboo

Capture and automate macOS UI with the Peekaboo CLI.

tools5

openai-whisper-api

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

development5

.claude/skills/simstim-workflow

# Simstim - HITL Accelerated Development Workflow <objective> Orchestrate the complete Loa development cycle (PRD → SDD → Sprint → Implementation) with integrated Flatline Protocol reviews at each stage. Human drives planning phases interactively while HIGH_CONSENSUS findings auto-integrate. "Experience the AI's work while maintaining your own consciousness." — Gibson, Neuromancer </objective> <input_guardrails> - PII filter: enabled - Injection detection: enabled - Danger level: moderate (o

development5

apple-notes

Manage Apple Notes via the `memo` CLI on macOS (create, view, edit, delete, search, move, and export notes). Use when a user asks OpenClaw to add a note, list notes, search notes, or manage note folders.

tools5

.claude/skills/auditing-security

--- parallel_threshold: 2000 audit_categories: 5 timeout_minutes: 60 zones: system: path: .claude permission: none state: paths: [grimoires/loa, .beads] permission: read-write app: paths: [src, lib, app] permission: read --- <input_guardrails> ## Pre-Execution Validation Before main skill execution, perform guardrail checks. ### Step 1: Check Configuration Read `.loa.config.yaml`: ```yaml guardrails: input: enabled: true|false ``` **Exit Conditions**:

development5

tests/fixtures/registry/skills/test-vendor/valid-skill

# valid-skill Test skill with valid license for unit testing. ## Purpose Used in test_constructs_loader.bats to verify correct handling of valid licenses.

testing5

cloudflare-browser

Control headless Chrome via Cloudflare Browser Rendering CDP WebSocket. Use for screenshots, page navigation, scraping, and video capture when browser automation is needed in a Cloudflare Workers environment. Requires CDP_SECRET env var and cdpUrl configured in browser.profiles.

tools5

bear-notes

Create, search, and manage Bear notes via grizzly CLI.

tools5

blogwatcher

Monitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI.

tools5

nano-banana-pro

Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).

content-media5

bluebubbles

Build or update the BlueBubbles external channel plugin for OpenClaw (extension package, REST send/probe, webhook inbound).

tools5

.claude/skills/enhancing-prompts

# Enhancing Prompts <objective> Analyze prompt quality, classify task type, and enhance with optimized templates while preserving original intent. Provides transparent feedback showing what was enhanced and why. </objective> <inputs> - `prompt`: The user's original prompt to analyze and enhance - `--analyze-only`: (optional) Show analysis without enhancement - `--task-type <type>`: (optional) Force a specific task type </inputs> <workflow> ## Phase 1: Analysis Analyze the prompt for compone

testing5

skills/canvas

# Canvas Skill Display HTML content on connected OpenClaw nodes (Mac app, iOS, Android). ## Overview The canvas tool lets you present web content on any connected node's canvas view. Great for: - Displaying games, visualizations, dashboards - Showing generated HTML content - Interactive demos ## How It Works ### Architecture ``` ┌─────────────────┐ ┌──────────────────┐ ┌─────────────┐ │ Canvas Host │────▶│ Node Bridge │────▶│ Node App │ │ (HTTP Server) │ │ (TCP

tools5

coding-agent

Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.

tools5

openai-image-gen

Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.

development5

.claude/skills/browsing-constructs

# Browsing Constructs Skill ## Purpose Provide a multi-select UI for browsing and installing packs from the Loa Constructs Registry. Enables composable skill installation per-repo. ## Invocation - `/constructs` - Smart default: manage installed packs OR browse to install - `/constructs browse` - Browse available packs with selection UI - `/constructs install <pack>` - Install specific pack directly - `/constructs list` - List installed packs - `/constructs search <query>` - Search packs by n

testing5

skills/discord

--- name: discord description: Use when you need to control Discord from OpenClaw via the discord tool: send messages, react, post or upload stickers, upload emojis, run polls, manage threads/pins/search, create/edit/delete channels and categories, fetch permissions or member/role/channel info, or handle moderation actions in Discord DMs or channels. metadata: {"openclaw":{"emoji":"🎮","requires":{"config":["channels.discord"]}}} --- # Discord Actions ## Overview Use `discord` to manage messa

tools5

tests/fixtures/registry/skills/test-vendor/grace-skill

# grace-skill Test skill in license grace period for unit testing. ## Purpose Used in test_constructs_loader.bats to verify correct handling of licenses in grace period.

testing5

session-logs

Search and analyze your own session logs (older/parent conversations) using jq.

tools5

prose

OpenProse VM skill pack. Activate on any `prose` command, .prose files, or OpenProse mentions; orchestrates multi-agent workflows.

data-ai5

.claude/skills/flatline-knowledge

# Flatline Knowledge Skill ## Purpose Provides optional NotebookLM integration for the Flatline Protocol, enabling external knowledge retrieval from curated AI-powered notebooks. ## Overview This skill automates browser interaction with Google NotebookLM to query organizational knowledge bases. It serves as a Tier 2 knowledge source, supplementing the local grimoire search (Tier 1). ## Architecture ``` Flatline Protocol │ ▼ ┌─────────────────┐ │ Knowledge Hub │ ├───────────

development5

github

Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.

tools5

gog

Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.

tools5

skills/food-order

--- name: food-order description: Reorder Foodora orders + track ETA/status with ordercli. Never confirm without explicit user approval. Triggers: order food, reorder, track ETA. homepage: https://ordercli.sh metadata: {"openclaw":{"emoji":"🥡","requires":{"bins":["ordercli"]},"install":[{"id":"go","kind":"go","module":"github.com/steipete/ordercli/cmd/ordercli@latest","bins":["ordercli"],"label":"Install ordercli (go)"}]}} --- # Food order (Foodora via ordercli) Goal: reorder a previous Foodo

tools5

tests/fixtures/registry/skills/test-vendor/expired-skill

# expired-skill Test skill with expired license for unit testing. ## Purpose Used in test_constructs_loader.bats to verify correct handling of expired licenses.

testing3

tests/fixtures/registry/skills/test-vendor/grace-skill

# grace-skill Test skill in license grace period for unit testing. ## Purpose Used in test_constructs_loader.bats to verify correct handling of licenses in grace period.

testing3

tests/fixtures/registry/packs/test-pack/skills/skill-a

# skill-a Test skill A from test-pack for unit testing. ## Purpose Used in test_pack_support.bats to verify pack validation and skill loading.

testing3

tests/fixtures/registry/skills/test-vendor/valid-skill

# valid-skill Test skill with valid license for unit testing. ## Purpose Used in test_constructs_loader.bats to verify correct handling of valid licenses.

testing3

tests/fixtures/registry/packs/test-pack/skills/skill-b

# skill-b Test skill B from test-pack for unit testing. ## Purpose Used in test_pack_support.bats to verify pack validation and skill loading.

testing3

implement

Execute sprint tasks with production-quality code and tests

development2

mount

Install Loa framework onto an existing repository

development2

eval

Run evaluation suites against the Loa framework

development2

red-team

Red Team — Generative Adversarial Security Design

testing2

ride

Analyze codebase to extract reality into Loa artifacts

development2

rtfm

Run documentation-driven testing against Ground Truth and protocols

testing2

translate

Translate technical documentation into executive-ready communications

documentation2

plan-and-analyze

Launch PRD discovery with codebase grounding and context ingestion

development2

review-sprint

Validate sprint implementation against acceptance criteria

testing2

enhance

Enhance a prompt for better outputs with analysis and optimization

data-ai2

plan-and-analyze

Launch PRD discovery with codebase grounding and context ingestion

development2

continuous-learning

development2

constructs

Browse and install construct packs from the Loa Constructs Registry

tools2

loa-credentials

Credential management and audit for API keys and secrets

development2

run-bridge

Run Bridge — Autonomous Excellence Loop

tools2

tests/fixtures/registry/skills/test-vendor/expired-skill

# expired-skill Test skill with expired license for unit testing. ## Purpose Used in test_constructs_loader.bats to verify correct handling of expired licenses.

testing2

tests/fixtures/registry/skills/test-vendor/valid-skill

# valid-skill Test skill with valid license for unit testing. ## Purpose Used in test_constructs_loader.bats to verify correct handling of valid licenses.

testing2

evals/fixtures/loa-skill-dir/.claude/skills/test-skill

# Test Skill A minimal skill for framework testing. ## Constraints - C-PROC-001: Never write code outside implement - C-PROC-005: Always complete full review cycle

development2

architect

Create comprehensive Software Design Document based on PRD

documentation2

evals/fixtures/loa-skill-dir/.claude/skills/test-skill

# Test Skill A minimal skill for framework testing. ## Constraints - C-PROC-001: Never write code outside implement - C-PROC-005: Always complete full review cycle

development2

simstim

Simstim - HITL Accelerated Development Workflow

development2

tests/fixtures/registry/packs/test-pack/skills/skill-b

# skill-b Test skill B from test-pack for unit testing. ## Purpose Used in test_pack_support.bats to verify pack validation and skill loading.

testing2

tests/fixtures/registry/packs/test-pack/skills/skill-b

# skill-b Test skill B from test-pack for unit testing. ## Purpose Used in test_pack_support.bats to verify pack validation and skill loading.

testing2

run

Autonomous sprint execution mode

tools2

run-bridge

Run Bridge — Autonomous Excellence Loop

tools2

review-sprint

Validate sprint implementation against acceptance criteria

testing2

tests/fixtures/registry/skills/test-vendor/grace-skill

# grace-skill Test skill in license grace period for unit testing. ## Purpose Used in test_constructs_loader.bats to verify correct handling of licenses in grace period.

testing2

tests/fixtures/registry/packs/test-pack/skills/skill-a

# skill-a Test skill A from test-pack for unit testing. ## Purpose Used in test_pack_support.bats to verify pack validation and skill loading.

testing2

sprint-plan

Create comprehensive sprint plan based on PRD and SDD

tools2

ride

Analyze codebase to extract reality into Loa artifacts

development2

implement

Execute sprint tasks with production-quality code and tests

development2

tests/fixtures/registry/skills/test-vendor/grace-skill

# grace-skill Test skill in license grace period for unit testing. ## Purpose Used in test_constructs_loader.bats to verify correct handling of licenses in grace period.

testing2

flatline-knowledge

Query Flatline protocol knowledge base via NotebookLM integration

databases2

tests/fixtures/registry/skills/test-vendor/expired-skill

# expired-skill Test skill with expired license for unit testing. ## Purpose Used in test_constructs_loader.bats to verify correct handling of expired licenses.

testing2

eval

Run evaluation suites against the Loa framework

development2

architect

Create comprehensive Software Design Document based on PRD

documentation2

tests/fixtures/registry/skills/test-vendor/valid-skill

# valid-skill Test skill with valid license for unit testing. ## Purpose Used in test_constructs_loader.bats to verify correct handling of valid licenses.

testing2

bridgebuilder-review

Bridgebuilder — Autonomous PR Review

development2

bridgebuilder-review

Bridgebuilder — Autonomous PR Review

development2

continuous-learning

development2

deploy-production

Design and deploy production infrastructure

devops2

autonomous

Autonomous agent execution mode

data-ai2

audit

Security and quality audit of application codebase

development2

audit

Security and quality audit of application codebase

development2

butterfreezone

BUTTERFREEZONE Generation Skill

tools2

run

Autonomous sprint execution mode

tools2

ground-truth

Generate factual, code-grounded GTM documents with BridgeBuilder voice and deterministic verification

development2

enhance

Enhance a prompt for better outputs with analysis and optimization

data-ai2

tests/fixtures/registry/packs/test-pack/skills/skill-a

# skill-a Test skill A from test-pack for unit testing. ## Purpose Used in test_pack_support.bats to verify pack validation and skill loading.

testing2

translate

Translate technical documentation into executive-ready communications

documentation2

sprint-plan

Create comprehensive sprint plan based on PRD and SDD

tools2

flatline-knowledge

Query Flatline protocol knowledge base via NotebookLM integration

databases2

butterfreezone

BUTTERFREEZONE Generation Skill

tools2

rtfm

Run documentation-driven testing against Ground Truth and protocols

testing2

simstim

Simstim - HITL Accelerated Development Workflow

development2

bug

Triage a bug report through structured phases and create micro-sprint

business2

constructs

Browse and install construct packs from the Loa Constructs Registry

tools2

loa-credentials

Credential management and audit for API keys and secrets

development2

deploy-production

Design and deploy production infrastructure

devops2

red-team

Red Team — Generative Adversarial Security Design

testing2

mount

Install Loa framework onto an existing repository

development2

autonomous

Autonomous agent execution mode

data-ai2

bug

Triage a bug report through structured phases and create micro-sprint

business2

.claude/skills/auditing-security

--- parallel_threshold: 2000 audit_categories: 5 timeout_minutes: 60 zones: system: path: .claude permission: none state: paths: [loa-grimoire, .beads] permission: read-write app: paths: [src, lib, app] permission: read --- # Paranoid Cypherpunk Auditor <objective> Perform comprehensive security and quality audit of code, architecture, infrastructure, or sprint implementations. Generate prioritized findings with actionable remediation at the appropriate output pat

development

.claude/skills/discovering-requirements

--- parallel_threshold: 2000 timeout_minutes: 90 zones: system: path: .claude permission: none state: paths: [loa-grimoire, .beads] permission: read-write app: paths: [src, lib, app] permission: read --- # Discovering Requirements <objective> Synthesize existing project documentation and conduct targeted discovery interviews to produce a comprehensive PRD at `loa-grimoire/prd.md`. </objective> <persona> **Role**: Senior Product Manager | 15 years | Enterprise & S

documentation

.claude/skills/reviewing-code

--- parallel_threshold: 3000 timeout_minutes: 60 zones: system: path: .claude permission: none state: paths: [loa-grimoire, .beads] permission: read-write app: paths: [src, lib, app] permission: read --- # Senior Tech Lead Reviewer <objective> Review sprint implementation for completeness, quality, security, and architecture alignment. Either approve (write "All good" + update sprint.md with checkmarks) OR provide detailed feedback at `loa-grimoire/a2a/sprint-N/en

development

.claude/skills/planning-sprints

--- parallel_threshold: null timeout_minutes: 60 zones: system: path: .claude permission: none state: paths: [loa-grimoire, .beads] permission: read-write app: paths: [src, lib, app] permission: read --- # Sprint Planner <objective> Transform PRD and SDD into actionable sprint plan with 2.5-day sprints, including deliverables, acceptance criteria, technical tasks, dependencies, and risk mitigation. Generate `loa-grimoire/sprint.md`. </objective> <zone_constraints

testing

.claude/skills/designing-architecture

--- parallel_threshold: null timeout_minutes: 60 zones: system: path: .claude permission: none state: paths: [loa-grimoire, .beads] permission: read-write app: paths: [src, lib, app] permission: read --- # Architecture Designer <objective> Transform Product Requirements Documents (PRDs) into comprehensive, actionable Software Design Documents (SDDs) that serve as the definitive technical blueprint for engineering teams during sprint planning and implementation. Ge

documentation

speaking

Golden path /speak — generate RLM-isolated follow-ups with chronicle temporal context injection.

development

.claude/skills/riding-codebase

# Riding Through the Codebase You are analyzing an existing codebase to generate evidence-grounded Loa artifacts following the v0.6.0 Enterprise-Grade Managed Scaffolding model. > *"The Loa rides through the code, channeling truth into the grimoire."* ## Core Principles ``` CODE IS TRUTH → Loa channels CODE → Grimoire reflects REALITY ``` 1. **Never trust documentation** - Verify everything against code 2. **Flag, don't fix** - Dead code/issues flagged for human decision 3. **Evidence requi

development

tests/fixtures/registry/packs/test-pack/skills/skill-a

# skill-a Test skill A from test-pack for unit testing. ## Purpose Used in test_pack_support.bats to verify pack validation and skill loading.

testing

detecting-staleness

Scan all artifacts for confidence metadata and report staleness using pure derived scoring.

data-ai

.claude/skills/implementing-tasks

--- parallel_threshold: 3000 timeout_minutes: 120 zones: system: path: .claude permission: none state: paths: [loa-grimoire, .beads] permission: read-write app: paths: [src, lib, app] permission: read --- # Sprint Task Implementer <objective> Implement sprint tasks from `loa-grimoire/sprint.md` with production-grade code and comprehensive tests. Generate detailed implementation report at `loa-grimoire/a2a/sprint-N/reviewer.md`. Address feedback iteratively until s

development

analyzing-gaps

Compare user expectations (UTCs) with code reality to identify gaps. Use when you need to understand discrepancies between what users expect and what code actually does.

development

batch-filing-gaps

Batch scan canvases for GAP sections, deduplicate, route to correct repos, draft issue bodies, and file confirmed issues.

tools

daily-synthesis

Automated end-to-end feedback pipeline that pulls new Supabase entries, enriches, classifies, routes to canvases, and generates a synthesis report.

devops

batch-observing

Parallel multi-user processing using Claude Code native teams. Leader spawns workers per user, each runs /ingest-dm, leader aggregates for cross-canvas patterns.

development

feedback-observing

Read agent interaction logs across packs and detect operational patterns. Emits state-transition FeedbackEvents for degradation/recovery.

data-ai

growing

Golden path /grow — confirm proposed matches, classify evidence, update confidence, run decay, surface growth changes. Full L4 backpropagation orchestrator.

development

ingesting-dms

Single-user conversation import that creates an enriched canvas scaffold from a DM export.

tools

level-3-diagnostic

Diagnostic-first user research for support conversations and feedback analysis. Reaches Level 3 (user goal) before investigating or fixing. Applies The Mom Test methodology to extract product insights from bug reports and feature requests.

development

refreshing-artifacts

Re-validate an artifact and update its confidence inputs. Routes to appropriate re-validation skill based on artifact type.

testing

listening

Golden path /listen — ingest all new signals: chronicle releases, Supabase feedback, DM exports, growth matches.

development

observing-users

Capture user feedback as hypothesis-first research using Level 3 diagnostic. Forms theories (not conclusions) from quotes.

research

shaping-journeys

List user canvases and shape common patterns into journey definitions. Use when consolidating user research into testable user flows.

development

generating-followups

RLM-isolated follow-up generation: orchestrator + per-user subagent architecture where cross-user contamination is architecturally impossible.

data-ai

thinking

Cognition orchestrator — analyze canvases, distill fears via /distill subagent, run gap analysis, optional cross-user synthesis.

data-ai

importing-research

Bulk convert legacy user research profiles to UTC (User Truth Canvas) format. Use when migrating existing research from grimoires/pub/research/users/ to laboratory.

development

distilling

Analyze a user canvas and distill structured fears, steering targets, and synthesis features into a cognition sidecar file.

tools

detecting-drift

Show what changed since last validation for a specific artifact. Computes confidence without writing to frontmatter.

testing

.claude/skills/translating-for-executives

# DevRel Translator Skill (Enterprise-Grade v2.0) <skill_context> You are an elite Developer Relations professional with 15 years of experience. You operate as a **Senior Financial Auditor for codebases**—verifying code ledgers against documentation reports to surface Ghost Assets (documented but missing features) and Undisclosed Liabilities (undocumented systems). Your task: Translate the "Ground Truth" discovered by /ride into strategic narratives for non-technical stakeholders, enabling bus

development

shaping

Golden path /shape — consolidate journey patterns across canvases and file gap issues.

development

.claude/skills/mounting-framework

development

concierge-testing

Validate gap hypotheses by manually simulating features for individual users and measuring commitment, not satisfaction.

testing

tests/fixtures/registry/skills/test-vendor/valid-skill

# valid-skill Test skill with valid license for unit testing. ## Purpose Used in test_constructs_loader.bats to verify correct handling of valid licenses.

testing

tests/fixtures/registry/skills/test-vendor/expired-skill

# expired-skill Test skill with expired license for unit testing. ## Purpose Used in test_constructs_loader.bats to verify correct handling of expired licenses.

testing

tests/fixtures/registry/packs/test-pack/skills/skill-b

# skill-b Test skill B from test-pack for unit testing. ## Purpose Used in test_pack_support.bats to verify pack validation and skill loading.

testing

.claude/skills/deploying-infrastructure

# DevOps Crypto Architect Skill You are a battle-tested DevOps Architect with 15 years of experience building and scaling infrastructure for crypto and blockchain systems at commercial and corporate scale. You bring a cypherpunk security-first mindset, having worked through multiple crypto cycles, network attacks, and high-stakes production incidents. <objective> Design and deploy production-grade infrastructure for crypto/blockchain projects with security-first approach. Generate IaC code, CI

development