Skill Claude CodeCodex
Sets quality expectations for implementation — "imagine this serves 1 million users." Checks for observability, error handling, input validation, graceful degradation.
10 3mo ago A 37 tokens
original MIT
Skill Claude CodeCodex
Enforces the Implement→Review→Test→Fix→Loop cycle until work is clean. Use after any non-trivial implementation to prevent "good enough" exits.
10 3mo ago A 38 tokens
original MIT
Skill Claude CodeCodex
Extracts learnings from completed work, feedback, or failures. Updates a persistent learnings file with capped entries. Use after receiving feedback, fixing bugs, or completing complex tasks.
10 3mo ago A 44 tokens
original MIT
Skill Claude CodeCodex
Validates PRD, user stories, or feature requirements against SMART criteria. Use when reviewing requirements to catch vagueness before it causes expensive rework.
10 3mo ago A 38 tokens
original MIT
Skill Claude CodeCodex
Dispatches SOTA research before proposing any new feature, architecture, or technology choice. Use when facing design decisions, not when implementing existing specs.
10 3mo ago A 36 tokens
original MIT
Skill Claude CodeCodex
Documents rollback procedures before making risky changes. Covers what's changing, verification steps, rollback procedures, and blast radius assessment.
10 3mo ago A 29 tokens
original MIT
Skill Claude CodeCodex
Performs deployment with pre-flight checks, atomic replacement, post-deploy verification, and automatic rollback. Use before any deployment to staging or production.
10 3mo ago A 35 tokens
original MIT
Skill Claude CodeCodex
Generates a behavioral scenario acceptance matrix for comprehensive test coverage planning. Maps user scenarios to acceptance criteria with stable IDs.
10 3mo ago A 30 tokens
original MIT
Skill Claude CodeCodex
Detects and redirects scope creep during implementation. Catches unrequested features, unnecessary refactoring, and over-engineering.
10 3mo ago A 31 tokens
original MIT
Skill Claude CodeCodex
Queries all configured services for health status — uptime, restarts, errors, resources. Use when checking the health of running services.
10 3mo ago A 32 tokens
original MIT
Skill Claude CodeCodex
Performs smart context summarization when the context window is approaching capacity. Identifies what to keep, what to summarize, and creates a compact resume state.
10 3mo ago A 38 tokens
original MIT
Skill Claude CodeCodex
Bidirectional sync between specification documents and code. Detects spec drift from staged changes, updates spec to reflect approved decisions, and ensures every commit represents a reconciled snapshot of spec, tests, and code.
10 3mo ago A 46 tokens
original MIT
Skill Claude CodeCodex
Compares specification documents against implementation code to find divergences. Use when implementation of a spec or design doc is claimed complete.
10 3mo ago A 34 tokens
original MIT
Skill Claude CodeCodex
Enforces structured output format for analyses, reports, and recommendations — Executive Summary, Detailed Analysis, Next Steps, Metrics. Prevents wall-of-text responses.
10 3mo ago A 37 tokens
original MIT
Skill Claude CodeCodex
Bootstraps the agent to check for applicable vibe-engineering skills before every action. Loads at conversation start for skill discovery.
10 3mo ago A 34 tokens
original MIT
vibe-help
40Skill Claude CodeCodex
Routes users to the right vibe-engineering skill for their current task. Use when user asks "what skill should I use?" or seems unsure about which skill to invoke.
10 3mo ago A 38 tokens
original MIT
Skill Claude CodeCodex
Dispatches research agents to find real projects, papers, and documented failures before proposing any feature, architecture, or technology choice. Triggers on creative/design tasks, not on implementation of already-designed specs.
10 3mo ago A 45 tokens
original MIT
Skill Claude CodeCodex
Systematically fixes large backlogs of issues using prioritized waves. Use when facing 10+ issues, bugs, or gaps to address.
10 3mo ago A 34 tokens
original MIT