4,434 skills found · Page 147 of 148
tygwan / craft-syncfoliocraft에서 생성/배포된 프로젝트 사이트 정보를 메인 포트폴리오(`dev/portfolio`)의 데이터 파일과 동기화합니다. ```
joonwon-space / fix-alertsdocs/alerts/ 의 미처리 알림을 읽고 원인을 파악해 코드를 수정한다.
bben15600-sys / skill-routerYou are a Skill Navigator. You take the user's free-form intent in natural language and route it to the most appropriate installed skill — printing a ranked list with confidence scores and explicit reasoning to chat, never executing the skill itself until the user confirms.
skand-io / codebase-locatorLocates files, directories, and components relevant to a feature or task. Call `codebase-locator` with human language prompt describing what you're looking for. Basically a "Super Grep/Glob/LS tool" — Use it if you find yourself desiring to use one of these tools more than once.
Zhang-Haoran / analyze-issueFetch GitHub issue details and create a comprehensive implementation specification.
EMC2-MapItApp / capacitor-android-reviewRevisa el trabajo actual con el subagente capacitor-android-reviewer (permisos, componentes exportados, cleartext, deep links, firma — android/ y Capacitor, repo WEB)
web-everything / nextShortcut for /backlog — pick & work the next backlog item (routes to the next-backlog-item skill)
juanmartin1892 / worktree-deliverEmpaqueta los cambios del worktree actual como un pull request. Sigue la especificación en `docs/specs/worktree-deliver.md` para el formato de mensajes. Pasos: 1. Verifica que estás en un worktree (no en `main`). Si estás en `main`, avisa y detente. 2. Ejecuta `/check-sensitive` antes de continuar.
mrojas54 / wids-pick-leaderPick next reading_group leader via longest-gap algorithm with random tie-break; operator confirms
brandonvio / pythonic-refactorAdd type hints and refactor Python code to use Pydantic models without breaking interfaces
Soproyectos / gentle-sdd-verifyValidate implementation matches specs, design, and tasks
LesterThomas / extract-golf-roundsExtract golf round data from Golfshot website within a specified date range and append to `golf-data/rounds-data.json`. - `start_date` (optional): Start date in format "MMM DD, YYYY" (e.g., "Jan 01, 2024"). Defaults to beginning of time.
ValonHajredini / architectWhen this command is used, adopt the following agent persona: <!-- Powered by BMAD™ Core -->
crisweber2600 / retrospectivePost-epic review to extract lessons and assess success
gieljnssns / My-Hassio-configMy configuration files for Hassio
PYUDNG / Kemono-DownloaderUserscript for downloading pawchive/kemono files
revodatanl / databricks-mcp-servername: databricks-local version: 0.0.1 schema: v1 mcpServers: - name: databricks-local command: /bin/zsh args:
dabit3 / lightningFull stack framework for building cross-platform mobile AI apps
OutlineDriven / mesonUse when setting up a Meson project, meson setup/compile/test, wrap dependencies, cross-file cross-compiling, meson.build, or migrating from CMake/Autotools to Meson.
OutlineDriven / tasteUse when asking "overkill?", "elegant?", "audit", or "taste-test this", or setting a taste register. Not for tasks that require source or remote-system changes.
OutlineDriven / ninjaUse when diagnosing Ninja build failures, tuning parallelism, interpreting verbose output, or working with build.ninja files as a CMake-generated low-level build executor.
OutlineDriven / commitUse when asked to commit changes, create a typed branch, format history for a changelog, or rewrite messages of HEAD or an unpushed range. Not for pushing or a PR: use commit-push-pr.
OutlineDriven / principlesUse when a request names a working principle (subtract before you add, idempotent operations, never block on the human) or asks which principle applies. Not for running a repair: use strike-the-root.
OutlineDriven / sagaUse when a user runs saga or asks to autonomously build a sizable feature. Not for executing a given plan: use subagent-driven.
OutlineDriven / reviewUse when asked to review a pull request, examine code changes, find bugs, or audit a branch, in standard or depth mode. Not for an iterative review-and-fix loop: use audit-project.
OutlineDriven / to-specUse when settled conversation decisions need synthesis into an agent-ready implementation spec, stopping before publication. Not for turning plans into tickets: use to-tickets.
OutlineDriven / resolveUse when addressing review feedback in analyze or reception mode, or handling GitHub PR feedback in autonomous, interactive, or summary mode for a named PR target. Classifies, applies, replies, or summarizes comments.
OutlineDriven / tddUse when developing a fix or feature test-first, plan a TDD build, or work red-to-green in slices. Not for hardening: use tests-adversarial. Not for deleting weak tests: use tests-purge-unneeded.
OutlineDriven / povUse when asked to judge whether to adopt, switch, reject, or revisit technology, library, pattern, or architecture, or a second opinion. Not for scoping: use brainstorm. Not for forks: use decide.
OutlineDriven / whyUse when asked why something works this way, for design rationale, a postmortem, a data-backed threshold, or a source-tiered evidence report. Not for current runtime behavior: use how.
