Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
external-tool-coordination
Coordinate external AI tool integration (OpenAI Codex, Google Gemini) for cross-model adversarial review and delegated implementation.
a5c-ai/babysitter 514
-
pr-shepherding
Monitor PR lifecycle from creation through merge including CI monitoring, review comment handling, thread resolution, and merge readiness verification.
a5c-ai/babysitter 514
-
orchestrated-execution
Execute work units through the rigorous 4-phase Metaswarm cycle (Implement -> Validate -> Adversarial Review -> Commit) with independent quality gate enforcement.
a5c-ai/babysitter 514
-
brainstorming
Clarify vague requirements through exploratory questioning and option generation before committing to research or implementation.
a5c-ai/babysitter 514
-
decision-documentation
Create Architecture Decision Records (ADRs) documenting significant technical choices with context, options, consequences, and sequential numbering.
a5c-ai/babysitter 514
-
test-driven-development
Test-first development practice where test specifications are written before production code, integrated into plan tasks as mandatory first sub-steps.
a5c-ai/babysitter 514
-
systematic-debugging
Structured debugging methodology using hypothesis-driven investigation, log analysis, and bisection to isolate and resolve defects.
a5c-ai/babysitter 514
-
codebase-research
Systematic codebase exploration following the Iron Law - understand the problem before exploring code. Four phases with file-finder and web-researcher agents.
a5c-ai/babysitter 514
-
code-review
Structured code quality assessment with Conventional Comments format, scaled review depth, and soft-gating verdicts preserving user autonomy.
a5c-ai/babysitter 514
-
plan-implementation
Disciplined execution of approved plans with step-by-step verification, phase checkpoints, failure investigation, and mandatory code/security reviews.
a5c-ai/babysitter 514
-
plan-writing
Transform research findings into actionable implementation plans with stakes-based rigor, test-first strategy, and granular task decomposition.
a5c-ai/babysitter 514
-
verification
Verification-before-completion discipline ensuring all success criteria are met, tests pass, and reviews complete before declaring work done.
a5c-ai/babysitter 514
-
security-review
Security vulnerability assessment identifying OWASP risks, injection vectors, authentication issues, and data exposure with severity classification.
a5c-ai/babysitter 514
-
finishing-work
Final completion discipline including summary generation, plan document updates, and confirmation that all success criteria from the original plan are satisfied.
a5c-ai/babysitter 514
-
brainstorming
Use when starting any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
a5c-ai/babysitter 514
-
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code. Enforces RED-GREEN-REFACTOR cycle.
a5c-ai/babysitter 514
-
using-superpowers
Use when starting any conversation. Establishes how to find and use skills, requiring skill invocation before any response.
a5c-ai/babysitter 514
-
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements.
a5c-ai/babysitter 514
-
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code. Creates bite-sized TDD implementation plans with dependency tracking.
a5c-ai/babysitter 514
-
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes. Requires root cause investigation first.
a5c-ai/babysitter 514
-
subagent-driven-development
Use when executing implementation plans with independent tasks in the current session. Dispatches fresh subagent per task.
a5c-ai/babysitter 514
-
executing-plans
Use when you have a written implementation plan to execute in a separate session with review checkpoints between batches.
a5c-ai/babysitter 514
-
verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs. Evidence before assertions.
a5c-ai/babysitter 514
-
code-review-checklist
Generate context-aware code review checklists from PR diffs — tailored to language, codebase patterns, and team standards. Identifies what reviewers should focus on. NOT for automated code fixing, test generation, or security auditing.
curiositech/some_claude_skills 81