adeitasuna
31 verified skills
.claude/skills/run-bridge
--- parallel_threshold: 2000 timeout_minutes: 480 zones: system: path: .claude permission: read state: paths: [grimoires/loa, .beads, .run] permission: read-write app: paths: [src, lib, app] permission: read-write --- # Run Bridge — Autonomous Excellence Loop ## Overview The Run Bridge skill orchestrates an iterative improvement loop: 1. Execute sprint plan via `/run sprint-plan` 2. Invoke Bridgebuilder review on the resulting changes 3. Parse findings into stru
development
.claude/skills/rtfm-testing
--- parallel_threshold: 3000 timeout_minutes: 15 zones: system: path: .claude permission: none state: paths: [grimoires/loa] permission: read-write app: paths: [src, lib, app] permission: none --- # RTFM Testing Skill <objective> Spawn a zero-context agent to test documentation usability. The tester operates under strict "no inference" rules and reports every gap it encounters. Parse the structured gap report, determine a verdict, and write results to the RTFM rep
testing
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
.claude/skills/eval-running
# Eval Running Skill Run evaluation suites against the Loa framework to detect regressions and benchmark skill quality. ## Usage ```bash # Run framework correctness suite /eval --suite framework # Run regression suite /eval --suite regression # Run a single task /eval --task constraint-proc-001-enforced # Run all tasks for a skill /eval --skill implementing-tasks # Update baselines /eval --suite framework --update-baseline --reason "Post-refactor re-baseline" ``` ## How It Works 1. Pars
development
.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**: - `
development
.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 `
testing
continuous-learning
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.
development
.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
testing
.claude/skills/browsing-constructs
# Browsing Constructs Skill ## Purpose Unified construct discovery surface for the Constructs Network. This skill is a **thin API client** — all search intelligence, ranking, and composability analysis lives in the Constructs Network API. ## API Configuration - **Base URL**: `LOA_CONSTRUCTS_API_URL` env var, default `https://api.constructs.network/v1` - **Auth**: `LOA_CONSTRUCTS_API_KEY` env var or `~/.loa/credentials.json` (for premium packs) ## Invocation ### `/constructs` (no args) — Br
tools
.claude/skills/bug-triaging
--- parallel_threshold: 3000 timeout_minutes: 60 zones: system: path: .claude permission: none state: paths: [grimoires/loa, .beads, .run] 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.inp
testing
.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
testing
.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 │ ├───────────
development
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.
testing
.claude/skills/red-teaming
# Red Team — Generative Adversarial Security Design ## Purpose Use the Flatline Protocol's red team mode to generate creative attack scenarios against design documents. Produces structured attack scenarios with consensus classification and architectural counter-designs. ## Invocation ```bash /red-team grimoires/loa/sdd.md /red-team grimoires/loa/sdd.md --focus "agent-identity,token-gated-access" /red-team grimoires/loa/sdd.md --mode quick /red-team grimoires/loa/sdd.md --depth 2 --mode deep
testing
ride
Analyze codebase to extract reality into Loa artifacts
development
.claude/skills/run-mode
<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 run-mode --mode {mode}` **
testing
.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 (or
development
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
development
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
.claude/skills/butterfreezone-gen
--- parallel_threshold: 3000 timeout_minutes: 5 zones: system: path: .claude permission: read state: paths: [grimoires/loa] permission: read app: paths: [src, lib, app] permission: none --- # BUTTERFREEZONE Generation Skill <objective> Generate and validate BUTTERFREEZONE.md — the agent-grounded README that provides token-efficient, provenance-tagged, checksum-verified project context for AI agents. Every claim cites its source. No butter, no hype. </objective> <
testing
.claude/skills/bridgebuilder-review
--- zones: system: path: .claude permission: read state: paths: [grimoires/bridgebuilder] permission: read app: permission: none --- # Bridgebuilder — Autonomous PR Review ## Prerequisites - `gh` CLI installed and authenticated (`gh auth status`) - `ANTHROPIC_API_KEY` environment variable set - Node.js >= 20.0.0 ## Usage ```bash /bridgebuilder # Review all open PRs on auto-detected repo /bridgebuilder --dry-run # Preview revi
tools
.claude/skills/autonomous-agent
<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 autonomous-agent --mode {mo
testing
.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
development
.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.en
testing
.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 --
testing
.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 right-sized sprints, including deliverables, acceptance criteria, technical tasks, dependencies, and risk mitigation. Generate `grimoires/loa/sprint.md`. </objective> <zone_const
testing
.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
documentation
.claude/skills/managing-credentials
--- parallel_threshold: 1000 timeout_minutes: 10 zones: system: path: .claude permission: none state: paths: [grimoires/loa] permission: read app: paths: [src, lib, app] permission: none --- # /loa-credentials — Credential Management ## Overview Manage API credentials for Loa's multi-model provider system. Three storage tiers: 1. **Environment variables** — highest priority, standard approach 2. **Encrypted store** — `~/.loa/credentials/store.json.enc` (Fernet/A
development
.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
development
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