bigeasyfreeman
46 verified skills1 total stars
build-feature
Orchestration skill: chains the full ADLC Build Loop. PRD → Brief → Council → Scaffold → Codegen → LDD → TDD → Council → PR. Use when implementing a new feature end-to-end.
development1
skills/tdd-enforcement
# Skill: Verification Discipline > Enforces task-class-aware verification during execution. The source of truth is `verification_spec`, not a universal TDD ritual. --- ## Why This Exists ADLC needs one discipline for all tasks, but not one verifier shape for all tasks. The right verifier depends on what changed: - `feature` tasks need behavior-defining tests - `bugfix` tasks need a reproducible failure first - `build_validation` tasks need the exact failing build or test command - `lint_clea
development
skills/ux-flow-builder
# Skill: UX Flow Builder > Generates user flow diagrams (Mermaid) from PRD personas and screen specifications. Surfaces dead ends, missing screens, and disconnected flows before design or engineering starts. Helps PMs think in screens, not features. --- ## Trigger - Automatically during PRD Phase 4 (Personas & Flows) to visualize the user journey - On-demand when the PM says "show me the flow" or "map the user journey" - During PRD evaluation to verify screen connectivity --- ## Input ```
development
verifier-semantic-judge
Decide whether an intersecting verifier actually exercises the semantic change.
testing
spec-to-tests
Authors failing tests and reproducers from Build Brief acceptance criteria plus verification_spec before coding starts.
development
skills/helm-argocd-deployment
# Skill: Helm & ArgoCD Deployment > Validates Helm charts and generates ArgoCD Application manifests when the ADLC pipeline produces infrastructure or service code. Ensures every deployable artifact has correct chart structure, environment-specific values, and a GitOps-ready Application manifest before code review. --- ## Why This Exists Without deployment validation in the pipeline, common failures slip through to production: - **Helm charts fail `helm template`** because of missing values,
development
skills/agentic-security
# OWASP Agentic Security Skill > Threat analysis for autonomous agent systems against the OWASP Agentic Security Initiative (ASI) Top 10. Covers behavior hijacking, tool misuse, inter-agent trust, cascading failures, and rogue agent containment. ## Trigger Invoke when: a task involves agent orchestration, multi-agent communication, tool/function calling, autonomous decision-making, persistent agent memory, or any feature where an agent acts without immediate human supervision. ## Input Contr
tools
skills/api-security
# OWASP API Security Skill > Threat analysis for API surfaces against OWASP API Security Top 10 (2023). Covers authorization, authentication, resource consumption, and business logic abuse for any exposed API endpoint. ## Trigger Invoke when: a task creates or modifies API endpoints (MCP tools, HTTP routes, WebSocket handlers, gateway endpoints), API clients, or inter-service communication. ## Input Contract ```json { "task_spec": "TaskSpec from Build Brief", "repo_map": "Cached codebas
tools
skills/appsec-threat-model
# OWASP AppSec Threat Model Skill > Systematic application security analysis against OWASP Top 10 (2021). Produces per-component threat assessments with concrete mitigations tied to the codebase. ## Trigger Invoke when: a Build Brief task touches authentication, authorization, data handling, user input processing, external API consumption, session management, or deployment configuration. Also invoke on any task flagged `security-relevant` by the Eval Council. ## Input Contract ```json { "
development
skills/architecture-pattern
# Skill: Architecture Pattern Scaffolding > Generates port interfaces, implementation guides, directory structures, and other non-placeholder scaffolding from Build Brief architecture pattern decisions. Ensures autonomous coding agents start with the right structure, not a blank file. --- ## Trigger Activated when coding starts (after brief approval and ticket creation). Consumes Section 2 (Architecture Patterns) and Section 8 (Task Breakdown) from the brief. ## Input Contract ```json {
development
brief-clarity-judge
Resolve ambiguous triage outcomes in the middle confidence band.
tools
skills/ci-cd-pipeline
# Skill: CI/CD Pipeline Generation > Generates or updates GitHub Actions workflows and Argo CD configurations from Build Brief infrastructure tasks. Ensures new features have proper build, test, and deploy pipelines before coding begins. --- ## Trigger Activated after work-item artifacts are created. Consumes Section 8 (Infra tasks) and Section 6 (SLOs) from the brief. ## Input Contract ```json { "build_brief_id": "string", "repo_url": "string", "branch_strategy": "trunk | gitflow |
development
skills/codebase-research
# Skill: Codebase Research & Repo Analysis > Produces a structured repo map, tech debt analysis, and improvement recommendations from deep analysis of a codebase. When given a PRD, cross-references requirements against repo capabilities to identify gaps, reusable components, and prerequisite fixes. This is the first deliverable the engineer reads — not background context, but the starting point for the Build Brief conversation. --- ## Why This Exists Every skill and agent in the ADLC system
development
skills/confluence-decomposition
# Skill: Confluence Decomposition > Decomposes a completed Build Brief into structured Confluence pages following the team's documentation hierarchy. Creates living docs that stay linked to JIRA tickets and runbooks. --- ## Trigger Activated immediately on Build Brief completion. Consumes the full Build Brief markdown. ## Emitter Contract Alignment This skill is a document emitter and must conform to [docs/specs/emitter-contract.md](/Users/eric/adlc/docs/specs/emitter-contract.md). Honor t
development
definition-of-done
Applicability-aware Definition of Done checklist. Core checks apply to every task; overlay checks activate only when the applicability manifest says the surface exists. Binary verification — pass or fail. Triggers at Phase 4 completion and Phase 5 entry.
testing
execute-trade
Orchestration skill for Ratatosk trade execution. Thesis → Council → Risk Check → Execute → Audit → Report. End-to-end trade lifecycle.
testing
skills/figma-integration
# Skill: Figma Integration > Pulls design specs, component inventories, and screen states from Figma into the PRD and Build Brief pipeline. Validates that PRD screen specifications match actual Figma mocks. Extracts design tokens, spacing, and component names so coding agents produce pixel-accurate implementations. --- ## Why This Exists PRDs describe screens in text. Figma has the actual designs. Without this skill: - PRD field-detail tables drift from what design actually built - Engineers
development
fix-bug
Orchestration skill for bug fixes and production issue repair. Investigate -> light brief -> targeted verification -> council -> PR.
testing
fix-loop
Autonomous error detection and repair pipeline. Runs parallel to Build Loop. Capture → Confirm → Investigate → Fix → Prove → Light Council → Deliver or Escalate.
development
skills/gong-customer-evidence
# Skill: Gong Customer Evidence > Searches customer call transcripts in Gong to validate PRD assumptions, surface unmet needs the PM may have missed, and ground feature decisions in actual customer language. Prevents building features nobody asked for and catches gaps in features customers desperately need. --- ## Why This Exists PRDs are hypotheses. Customer calls are evidence. Without this skill: - PMs build from internal assumptions, not customer voice - Features ship without validation t
development
skills/grafana-observability
# Skill: Grafana Observability > Connects to Grafana to pull real traffic baselines, existing dashboards, and alert rules for services in the ADLC pipeline. Validates PRD traffic estimates against production reality. Provisions dashboards and alert rules from Build Brief throughput SLOs. Long-term, feeds live metrics into failure detection, capacity planning, and anomaly alerting across all services. --- ## Why This Exists Without real observability data, the ADLC pipeline operates on estima
development
skills/incident-runbook
# Skill: Incident Runbook Generation > Generates incident runbooks from Build Brief failure modes, SLOs, and incident ownership definitions. Produces actionable runbooks that on-call engineers can follow at 2am without context loading. --- ## Trigger Activated when Phase 1 is ready for deploy. Consumes Section 4 (Risk), Section 5 (Security), Section 6 (SLOs & Incident Ownership), and Section 11 (Failure Mode Roll-Up). ## Input Contract ```json { "build_brief_id": "string", "feature_nam
development
skills/infra-security
# OWASP Kubernetes / Infrastructure Security Skill > Threat analysis for container and infrastructure deployments against OWASP Kubernetes Top 10 (2025). Covers workload hardening, RBAC, secrets management, network segmentation, and cloud lateral movement. ## Trigger Invoke when: a task involves Dockerfiles, docker-compose, Kubernetes manifests, Helm charts, CI/CD pipelines, deployment scripts, systemd/launchd services, infrastructure-as-code, or cloud configuration. ## Input Contract ```js
development
ldd-enforcement
Lint-Driven Development — formatting and syntax gate that runs BEFORE test execution. Violations block TDD entry. Triggers at Phase 4 entry.
development
skills/llm-security
# OWASP LLM Security Skill > Threat analysis for LLM-integrated systems against OWASP Top 10 for LLM Applications (v2.0, 2025). Covers prompt injection, output handling, agency boundaries, and supply chain risks specific to LLM-powered features. ## Trigger Invoke when: a task involves LLM calls (`llm_call_fn`), prompt construction, model output parsing, RAG/embedding pipelines, agent orchestration, or any feature where an LLM produces content that drives downstream behavior. ## Input Contrac
testing
mutant-materiality-judge
Classify surviving mutants as trivial or material after deterministic mutation measurement.
tools
skills/notion-decomposition
# Skill: Notion Decomposition > Decomposes a completed Build Brief into structured Notion pages and optional task database entries. Creates living docs that stay linked to work-item emitters, runbooks, and decision logs. --- ## Trigger Activated immediately on Build Brief completion. Consumes the full Build Brief markdown. ## Emitter Contract Alignment This skill is a document emitter and must conform to [docs/specs/emitter-contract.md](/Users/eric/adlc/docs/specs/emitter-contract.md). Hon
development
observability-contract
Logging mandate with applicability-aware activation: structured error, audit, and general logging are required only when the task introduces a runtime path, service boundary, or user-facing operation. Triggers at Phase 1 (specification) and Phase 5 (verification).
testing
skills/qa-test-data
# Skill: QA Test Data Generation > Generates deterministic verification artifacts from task definitions. It produces behavioral tests when the task warrants tests, and produces command-verifier metadata when the task is maintenance. --- ## Trigger Activated after the Build Brief and task classification are available. Consumes `task_classification`, `verification_spec`, and task-level acceptance criteria. --- ## Input Contract ```json { "build_brief_id": "string", "task_classification"
development
reuse-analysis
Discovers existing functions/patterns/utilities that must be reused (not reimplemented) and identifies antipatterns to avoid. Triggers at Phase 1 (discovery) and Phase 5 (verification).
research
section-policy-judge
Override deterministic section suppression when manifest evidence shows the section should stay active.
tools
security-review
Security analysis with applicability-aware activation: STRIDE threat modeling only when the task introduces attack surface, trust-boundary, auth, data, or external-integration change; OWASP Top 10 vulnerability scanning per-diff post-execution (Phase 5).
development
ship-content
Orchestration skill for Magnus content delivery. Brief → Council → Draft → Slop Gate → Council(light) → Publish. End-to-end content creation and publishing.
testing
skills/slack-orchestration
# Skill: Slack Workflow Orchestration > Manages the end-to-end workflow from PRD to Build Brief to approval to coding kickoff. Posts summaries, routes Type 1 escalations, collects approvals, and tracks decision resolution. This is the glue that connects all ADLC agents and skills. --- ## Trigger Multiple trigger points throughout the ADLC lifecycle: | Trigger | Event | Action | |---------|-------|--------| | PRD Handoff | Product Agent completes PRD | Notify engineer, start Build Brief | |
development
slop-judge
Judge whether prose that cleared regex still contains generic filler, passive evasion, or tautology.
data-ai
skills/stop-slop
Dual-mode slop detection for code and content. ADLC v2 spec.
development
skills/systematic-debugging
# Skill: Systematic Debugging > 4-phase root cause investigation protocol for agent-driven debugging. Prevents "quick patch" guessing by enforcing evidence gathering, hypothesis formation, isolated testing, and defense-in-depth fixes. Designed for use by self-healing-agent on gate failures and by any agent encountering unexpected errors during execution. --- ## Why This Exists Agents are biased toward action. When a test fails or a gate rejects, the default behavior is: guess what's wrong, a
development
test-strength
Audits generated test strength on changed files using deterministic coverage and mutation measurement, then judges only surviving-mutant materiality.
testing
skills/eval-council
# Skill: Eval Council > Multi-perspective evaluation agent that validates Build Brief quality, skill outputs, and critical decisions before they proceed downstream. Inspired by the Council/RedTeam/FirstPrinciples thinking tools from Daniel Miessler's PAI system. Evaluation is opt-OUT for active surfaces, not a universal mandate for every overlay. You must justify skipping an active persona or section. --- ## Why This Exists Agents are confident. Confidently wrong is still wrong. The Build B
tools
skills/github-issue-creation
# Skill: GitHub Issue Creation > Creates structured GitHub tracking issues and task issues from Build Brief task breakdowns. Produces issue bodies that preserve verifier contracts, dependencies, and execution context for coding agents. --- ## Trigger Activated after the engineer approves the Build Brief. Consumes the schema-validated Build Brief, especially task breakdown, phased plan, and each task's applicability and verifier contract. ## Emitter Contract Alignment This skill is a work-i
development
skills/codegen-context
# Skill: Codegen Context Assembly > Assembles a single per-task coding prompt from the brief, research, scaffolding, and verifier metadata. The prompt should match the task class, not force universal test ceremony. --- ## Why This Exists The coding agent needs one prompt, not a pile of documents. But that prompt should be driven by `task_classification` and `verification_spec`, because different tasks need different verifiers: - feature tasks need behavioral tests - bugfix tasks need a repro
development
skills/jira-ticket-creation
# Skill: JIRA Ticket Creation > Creates structured JIRA tickets from Build Brief task breakdowns. Produces tickets with acceptance criteria, constraints, architecture pattern references, and linked failure modes that autonomous coding agents can execute against. --- ## Trigger Activated after the engineer approves the Build Brief. Consumes the schema-validated Build Brief, especially task breakdown, phased plan, and each task's applicability/verifier contract. ## Emitter Contract Alignment
development
skills/prd-generation
# Skill: PRD Quality Evaluator > Validates a PRD against the standard template before it's handed to engineering. Catches missing fields, vague specs, orphan screens, undefined interactions, missing reuse/debt framing, and TBDs without owners. Runs automatically before PRD finalization — the last gate before the ADLC pipeline consumes it. --- ## Trigger Runs automatically when the PRD Agent completes Phase 7 (Review & Finalize). Also runnable on-demand against any PRD document. --- ## Inpu
testing
skills/linear-ticket-creation
# Skill: Linear Ticket Creation > Creates structured Linear issues from Build Brief task breakdowns. Produces cycle-aware tickets that preserve verifier contracts, dependencies, and execution context for coding agents. --- ## Trigger Activated after the engineer approves the Build Brief. Consumes the schema-validated Build Brief, especially task breakdown, phased plan, and each task's applicability and verifier contract. ## Emitter Contract Alignment This skill is a work-item emitter and m
development
feedback-loop
Self-improving skill system. Captures diffs between agent output and human edits, distills patterns into rules, writes them back to skill files. Makes Build and Fix loops better over time.
development
specificity-judge
Score whether each task is specific enough for autonomous, one-shot, production-ready execution.
testing