Command Claude Code
Phase 3 of reviewing-impl-plans: Behavior Verification Audit.
not rated 10 2d ago A 13 tokens
original MIT
Command Claude Code
Phase 4-5 of reviewing-impl-plans: Completeness Checks, Escalation, and report assembly.
not rated 10
changed 1mo ago A 23 tokens
original MIT
Command Claude Code
Phase 2 of reviewing-impl-plans: Interface Contract Audit.
not rated 10 2d ago A 13 tokens
original MIT
Command Claude Code
Phase 1 of reviewing-impl-plans: Context and Inventory analysis.
not rated 10 2d ago A 14 tokens
original MIT
sharpen-audit
101Command Claude Code
Audit LLM prompts/instructions for ambiguity. Use when reviewing prompts, skill instructions, subagent prompts, or any AI-targeted text. Produces findings report with severity, executor predictions, and remediation.
not rated 10 2d ago A 41 tokens
original MIT
sharpen-improve
102Command Claude Code
Rewrite LLM prompts to eliminate ambiguity. Use when you have a prompt that needs sharpening and authority to modify it. Produces improved prompt with change log. Asks clarifying questions when context insufficient.
not rated 10 2d ago A 40 tokens
original MIT
simplify-analyze
103Command Claude Code
Analyze code for simplification opportunities. Part of simplify- family.
not rated 10 2d ago A 13 tokens
original MIT
Command Claude Code
Apply verified simplifications with user approval. Part of simplify- family.
not rated 10 2d ago A 14 tokens
original MIT
simplify-verify
105Command Claude Code
Verify simplification candidates pass all gates. Part of simplify- family.
not rated 10 2d ago A 14 tokens
original MIT
simplify
106Command Claude Code
Orchestrates code simplification via verified transformations. Delegates to simplify-analyze, simplify-verify, and simplify-transform.
not rated 10 2d ago A 25 tokens
original MIT
test-bar-remove
107Command Claude Code
Remove test bar artifacts injected by /test-bar. Use when user says /test-bar-remove or wants to clean up QA overlay code.
not rated 10 2d ago A 26 tokens
original MIT
test-bar
108Command Claude Code
Generate a floating QA test overlay for the current branch's UI changes. Use when user says /test-bar, needs visual QA scenarios, or wants to test conditional rendering paths.
not rated 10 2d ago A 34 tokens
original MIT
verify
109Command Claude Code
Run verification commands and confirm output before making success claims. Use before committing, creating PRs, or claiming work is complete. Evidence before assertions, ALWAYS.
not rated 10 2d ago A 31 tokens
original MIT
write-plan
110Command Claude Code
Create detailed implementation plan with bite-sized tasks. Use when starting any multi-step development work.
not rated 10 2d ago A 18 tokens
original MIT
write-skill-test
111Command Claude Code
RED-GREEN-REFACTOR implementation for writing-skills: Baseline testing, minimal skill writing, loophole closure, and full creation checklist.
not rated 10 2d ago A 29 tokens
original MIT
Command Claude Code
Create a new command file following the command schema. Use when writing-commands skill dispatches Phase 1, or when user says 'create command', 'new command'.
not rated 10 2d ago A 34 tokens
original MIT
Command Claude Code
Create paired commands (create + remove) with proper artifact contracts. Use when writing-commands skill dispatches Phase 3, or when creating commands that produce artifacts.
not rated 10 2d ago A 33 tokens
original MIT
Command Claude Code
Review and test a command against the quality checklist. Use when writing-commands skill dispatches Phase 2, or when user says 'review command', 'check command quality'.
not rated 10 2d ago A 35 tokens
original MIT
Skill Claude CodeCodex
Use for branch code review whenever the user does not explicitly ask for a lightweight pass — this is the DEFAULT for unspecified-scope review. Triggers: 'code review', 'review this branch', 'review the changes', 'review what's on this branch', 'do a code review of the branch', 'branch code review', 'review the work'…
not rated 10 2d ago A 180 tokens
original MIT
Skill Claude CodeCodex
Use when dispatching a subagent to re-check work against external feedback (PR review comments, audit findings, multi-comment review cycles, 'did I really address X' verifications). Triggers: 'verify all the review comments are addressed', 'check that I really fixed all the audit findings', 'did I miss anything from…
not rated 10 2d ago A SkillSpector: pass 117 tokens
original MIT
agent2agent
117Skill Claude Code
Use when the user wants two or more Claude/agent sessions to talk to each other via the filesystem. Triggers: 'your name for inter-agent chat is X', 'your a2a name is X', 'listen for messages', 'open as X', 'talk to the session named Y', 'send a message to session Y', 'check the inbox', 'reply to that session'…
not rated 10 2d ago A SkillSpector: pass 139 tokens
original MIT
Skill Claude CodeCodex
Use when entering unfamiliar domains, modeling complex business logic, or when terms/concepts are unclear. Triggers: 'what are the domain concepts', 'define the entities', 'model this domain', 'DDD', 'ubiquitous language', 'bounded context'. Also invoked by develop during research phase.
not rated 10 2d ago A 67 tokens
original MIT
Skill Claude CodeCodex
Use when evaluating skill effectiveness or comparing skill versions. Triggers: 'how are skills performing', 'skill metrics', 'which skills fire correctly', 'skill invocation analysis', 'compare skill versions', 'analyze skill usage'. NOT for: authoring or editing a skill (use writing-skills).
not rated 10 2d ago A SkillSpector: pass 68 tokens
original MIT
Skill Claude CodeCodex
Use when preparing context for subagent dispatch or managing token budgets. Triggers: 'prepare context for', 'assemble context', 'token budget', 'context package', 'what context does the subagent need'. Also invoked by develop during planning and execution phases.
not rated 10 2d ago A 56 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: