Skip to content

mattgierhart/PRD-driven-context-engineering / .claude/skills/SKILL_TEMPLATE

prd-vXX-skill-name

Verified

[1-2 sentence description of what this skill does]. Triggers on [specific phrases/contexts that should activate this skill]. Outputs [what the skill produces].

[Skill Name]

[One sentence summary of the skill's purpose.]

Workflow Overview

  1. Step 1 → Brief description
  2. Step 2 → Brief description
  3. Step 3 → Brief description

Core Output Template

[Define the primary output structure this skill produces]

ElementDefinitionEvidence
Field 1What this capturesHow to validate
Field 2What this capturesHow to validate

See assets/output-template.md for copy-paste template.

Step 1: [First Major Step]

[Detailed instructions for this step]

Checklist

  • Item 1
  • Item 2

Step 2: [Second Major Step]

[Detailed instructions for this step]

Step 3: [Third Major Step]

[Detailed instructions for this step]

Quality Gates

Pass Checklist

  • Gate 1: [Specific, measurable criterion]
  • Gate 2: [Specific, measurable criterion]
  • Gate 3: [Specific, measurable criterion]

Testability Check

  • Can this output be validated?
  • Does it reference IDs from SoT/?

How this is evaluated: This skill's output is scored by scripts/readiness.py (a deterministic, $0, no-LLM proxy). Clearing a gate is permission to advance, not the goal — the goal is evidence. Padding inputs to move the score without moving the evidence is a frozen-replay defect. See PRINCIPLES.md P7.

Anti-Patterns

PatternExampleFix
Bad pattern 1"Example"→ "Better approach"
Bad pattern 2"Example"→ "Better approach"
Evidence fabricationBack-filling confidence/evidence to clear a gate→ Cite a real source or mark the gap; never invent to pass (P4 anti-leakage, P7)

Bundled Resources

  • references/[file].md — [Description of when to use]
  • assets/[template].md — [Description of template purpose]

Handoff

[What happens after this skill completes? What stage/skill comes next?]

reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 469kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 321kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 321kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 321kUpdated Claude CodeCodexVerifiedInstall