Loading...
Loading...
Found 110 Skills
Defense-in-depth verification before declaring any task complete. Run tests, check build, validate changed files, verify no regressions. Applies 4-level adversarial artifact verification (EXISTS > SUBSTANTIVE > WIRED > DATA FLOWS) with goal-backward framing. Use before saying "done", "fixed", or "complete" on any code change. Use for "verify", "make sure it works", "check before committing", or "validate changes". Do NOT use for debugging (use systematic-debugging) or code review (use systematic-code-review).
[user/auto] 하나의 pull request의 review feedback 또는 지원 가능한 GitHub Actions 실패를 fresh state로 읽고, 자연스러운 해결 계획을 합의한 뒤 필요 시 `seed.md`를 사용해 수정·검증·제한된 publication까지 처리합니다.
Onboard an AI coding agent to a Syncfusion project. Identifies the framework and product family, installs or selects the official component skills, finds current documentation, handles licensing safely, and verifies a working implementation. Use when starting, integrating, upgrading, migrating, evaluating, or troubleshooting Syncfusion UI components, document SDKs, viewers, or editors on any platform.
Test-driven development workflow with philosophy guide - plan → write tests → implement → validate
Use when you have a spec or requirements for a multi-step task, before writing implementation code. Helps break down complex features into bite-sized, verifiable tasks.
Issue Workflow Stage 3——Fix code precisely based on confirmed root cause and solution, verify the effect, and document it in {slug}-fix-note.md. This is the final stage of the issue workflow—no verification loop means the workflow is incomplete. Two entry points: the standard path is triggered from easysdd-issue-analyze (with existing {slug}-analysis.md), and the quick path is triggered directly from easysdd-issue-report (without {slug}-analysis.md, as the root cause was determined by AI reading code during the report stage). Trigger scenarios: user says 'Start fixing the bug', 'Fix according to analysis', 'Start modifying code'. During repair, only modify the files stated in the solution; do not optimize casually or introduce new abstractions—these actions will make the scope spread to untraceable levels.
Use when about to submit work, before committing or pushing, to run verification commands and confirm the work actually passes before claiming completion
Use when reviewing a PR with contrarian inversion to stress-test changes via @coderabbitai, making specific factual claims about dependency behavior that Conejo can later verify by reading library source code. Triggers on proud-zanahoria, contrarian review, inverse review, devil's advocate PR, zanahoria.
Implement approved technical plans phase-by-phase, including code changes, verification, and progress updates directly in the plan file. Use this whenever the user asks to execute a plan, implement from a plan document, continue plan-based work, resume from checked/unchecked tasks, or "do phase 1/2/3" from an implementation plan in `rpi/plans/`, even if they do not explicitly name this skill.
Use this skill for mathematical code verification. Use when reviewing math-heavy code, verifying algorithm correctness, checking numerical stability, aligning with mathematical standards. Do not use when general algorithm review - use architecture-review. DO NOT use when: performance optimization - use parseltongue:python-performance.
Run the Ouroboros specification-first development loop: reduce ambiguity with a Socratic interview, freeze an immutable seed/spec, execute against that contract, verify before claiming success, and keep looping until completion is actually verified. Use when the user wants spec-first clarification, immutable requirements, drift-aware implementation, or a persistent completion loop that should keep going until tests / checks / acceptance criteria pass. Triggers on: ooo, ouroboros, interview, seed, run workflow, evaluate, evolve, ooo ralph, specification first, socratic interview, ambiguity reduction, persistent completion.
Build a screen with StyleSeed's composed design method — choose or compile an output grammar, apply a brand recipe plus domain/page/profile/lock constraints, then run the code and pixel gates before presenting.