Explorar skills

CI/CD pipeline hardening for GitHub Actions and GitLab CI — trust-model (pull_request_target vs pull_request), action pinning to SHA, OIDC-based cloud access, permissions minimization, runner isolation, and supply-chain gates (SLSA provenance, signing).

Commit staged git changes w/ descriptive Conventional Commits message. Triggers when user asks to commit, save changes, ∨ mentions GitHub commits. Phrasings: "commit", "save my changes", "commit this".

Parameterized single-question intent-sharpening gate. ⊥ user-invoked — invoked from consumer cmd pre-apply gate (/gh:issue, /sdd:spec).

Standardize post-change verification and “definition of done” evidence for infra work (IaC/Helm/GitHub/Kubernetes).

Use when the user wants to discover and review PRs across the team awaiting their attention. NOT for a single specific PR (use review-pr). Supports three discovery modes: Label (GitHub label scan), Slack (channel-wide scan), Thread (specific Slack thread URL). Trigger: '掃 PR', 'review 大家的 PR', '批次 review', '有哪些 PR 要我看', Slack thread URL + review intent ('review <slack_url>', '幫我看這串'). Key: '我的 PR'

Gera um roast divertido e compartilhável de desenvolvedores, baseado em sua presença online pública (GitHub, npm, etc.). Use esta skill quando o usuário pedir para roast, torrar, zoar um perfil de desenvolvedor, ou mencionar um nome de usuário do GitHub em tom de brincadeira.

Propose-then-critique structural design loop → draft to `designs/<slug>.md`. Distinct from socratic (which sharpens vague intent). Use when user wants to design a structural change, weigh tradeoffs between named alternatives, propose an architecture, or shape a subsystem before implementation. Triggers: "/sdd:design", "design the X", "shape the X subsystem", "tradeoffs between A and B", "how shoul

GitHub repository standards and workflow rules. Use when creating repos, opening PRs, pushing code, setting up CI, creating branches, writing READMEs, or reviewing repo hygiene. Covers commit format (complements git-commit skill), PR message template, sensitive data pre-commit checks, repo naming, README requirements, branch naming, .gitignore baseline, release tagging, and CI/CD baseline. Derived

Esta skill facilita a revisão interativa de pull requests em blocos, exibindo feedback existente e permitindo comentários ponderados sem sobrecarga cognitiva. Use-a para revisar PRs, examinar mudanças ou postar comentários no GitHub, ativando-se também ao mencionar números ou URLs de PR.

Human-facing terse-prose register for non-author reviewers. Triggers: write/edit human-facing terse prose for review; user says "steno", "shorthand", "tighten this", "make this shorter".

Math-glyph → prose. Expand any SPEC.md citation into plain English. Read-only. Inverse of the glyph skill (math-glyph encoder). Triggers when human wants to understand a §V invariant, §T task, §B bug, or §I interface without the encoding. Phrasings: "/sdd:explain", "what does §V.<n> mean", "decompress this", "explain in prose", "I don't read math-glyphs". ⊥ for writes — those go through /sdd:spec.

Load skills from a GitHub repository into the current Cowork session as a unified plugin. Use when the user says "load skills from GitHub", "import skills from repo", "add skills from URL", "install skills from this link", or runs /skills-load with a GitHub URL. Also trigger when the user pastes a GitHub URL and mentions skills, plugins, or Claude capabilities they want to add.