All authors
Claude Skills by shenxingy
github.com/shenxingy163 skills11 installs464 views
- ShipFull release pipeline — tests → coverage → review gate → version bump → CHANGELOG → commit → PRVotes: 0GitHub stars: 10
- SltToggle the statusline quota pace indicator (mode/theme)Votes: 0GitHub stars: 10
- StartAutonomous session launcher — morning briefing, unattended overnight runs, cross-project patrol, auto-researchVotes: 0GitHub stars: 10
- StatusSession activity dashboard — lists background agents, /loop iterations, worktrees, orchestrator workers, unpushed commits, and recent PR activity. Use when the user asks "what's going on right now" mid-session.Votes: 0GitHub stars: 10
- SyncEnd-of-session documentation sync — updates TODO.md and PROGRESS.md only (run /commit after to commit everything)Votes: 0GitHub stars: 10
- VerifyVerify project behavior anchors — compilation, tests, and interaction checks after autonomous runs. NOT the Claude Code built-in /verify (which runs the app to observe a single change working) — this one walks the CLAUDE.md "Features (Behavior Anchors)" list.Votes: 0GitHub stars: 10
- WorktreeCreate or inspect runtime-adaptive isolated Git workspaces with explicit ownership and delivery routingVotes: 0GitHub stars: 10
- Codex OrchestrateOrchestrate a fleet of parallel `codex exec` workers with you as supervisor — one per isolated git worktree, dispatched headless, each verified INDEPENDENTLY, then PR/merge. The manual \"codex-ultracode\" fan-out pattern with the hard gotchas baked in (stdin blocking, background tracking, don't-trust-self-reports, writer isolation). Triggers: orchestrate codex, codex workers/fleet, spawn codex, delegate to codex in parallel, manual ultracode, 开 codex 小弟, 派 codex worker — NOT for a single cros...Votes: 0GitHub stars: 10
- Codex UsageShow Codex rate-limit usage and pace, or configure the native Codex status lineVotes: 0GitHub stars: 10
- Create PrPublish or update one repository-adaptive, exact-SHA pull request without duplicating or broadening authorityVotes: 0GitHub stars: 10
- DeliveryAdaptive, resumable Git delivery across repositories and agent runtimes — probe policy, checkpoint coherent work, publish, review, integrate, and verify cleanupVotes: 0GitHub stars: 10
- Domain ModelMaintain a living domain glossary (CONTEXT.md) and gated architecture decision records (docs/adr/) — pin down ambiguous terminology the moment it causes friction; record a decision only when irreversible, surprising, or a genuine trade-off. NOT a design-doc replacement or the corrections/rules.md learning loop — terminology precision and decision provenance only.Votes: 0GitHub stars: 10
- GreenRun the repository's real CI gates locally and drive them to green — read the failing step, fix the cause, re-run only that job, repeat. Use before pushing, after a red hosted run, or whenever "make CI pass" is the ask. Never weakens a gate to make it pass.Votes: 0GitHub stars: 10
- LandscapeProduce a whole-system landscape report as a published artifact — every part and surface, per-part architecture, who owns what and where the code lives, the ultimate goal and measured gap, abandoned attempts, and one expanded next step. For "understand the whole system", cross-repo status, or a report for a reader who is simultaneously a PhD, a PM and an engineer.Votes: 0GitHub stars: 10
- LocalizeFull-site/app internationalization — audit translatable surfaces, extract hardcoded strings, wire i18n (next-intl etc.), translate to N locales with brand/ICU/RTL fidelity, then an independent ISO-17100 revision pass (second native reviewer per locale, back-translation + MQM scoring) and key-parity, leak, build, and viewport/RTL verification. NOT for blog article content (use blog-localize) — this is for codebase/marketing-site UI.Votes: 0GitHub stars: 10
- Muller Brockmann Grid SystemsBuild editorial/magazine/report webpages on a GENUINE Müller-Brockmann modular grid (International Typographic Style), not a decorative one — columns + modules + baseline, grotesque type, flush-left ragged-right, restrained black/white/red — with the engineering that makes the grid load-bearing: CSS-variable source of truth, in-box grid-toggle overlay, subgrid bands, 8px baseline lock, optical alignment, a scaffold generator, and a Puppeteer harness proving 0px adherence. Triggers: magazine s...Votes: 0GitHub stars: 10
- OutboundVerify an artifact about to leave the building — partnership brief, pitch page, press release, customer email, RFP response, or any document sent outside the org. Six checks before send — premise, confidentiality forward-test, evidence class, cold read by recipient personas, AI read, tone metrics — returning what to change with replacement copy.Votes: 0GitHub stars: 10
- Qa ExploreGit-log-scoped exploratory regression hunting — scope a pass from recent commit history, form concrete side-effect hypotheses per commit (not just re-testing stated intent), then drive the live app via curl or Playwright MCP to probe them. Open-ended exploration with no maintained fixture, bounded by time and commit count — NOT the fixed VERIFY.md anchor checks (/verify) or a PR-diff review (/review-pr).Votes: 0GitHub stars: 10
- RadarAutonomous discovery of concepts, methods, and vocabulary we have NOT heard of yet — sweeps broadly, diffs against a known-concepts ledger, and reports only what is genuinely new plus whether it names a gap in this stack. A fixed topic list can only refresh what you already named; radar surfaces what you did not know to look for.Votes: 0GitHub stars: 10
- Seo Content BriefGenerate competitive SEO content briefs with per-section word counts, competitor scoring, keyword density guidance, and page-type templates. Supports both new page briefs and improve-existing-page briefs. Use when user says "content brief", "write a brief", "content outline", "blog brief", "service page brief", "brief for", "writing brief", "content plan", or "outline for".Votes: 0GitHub stars: 10
- Skill NewScaffold a new Clade skill end-to-end — interview for use cases and trigger phrases, generate SKILL.md + prompt.md with spec-validated frontmatter (bilingual triggers, NOT-for disambiguation), wire golden-set routing tests, and run the lint gate before committingVotes: 0GitHub stars: 10
- Trim TestsTest-suite diet — consolidate near-identical tests into table-driven cases, delete trivial/mock-only/brittle tests, and report every piece of coverage intentionally given up. Counterweight to AI test bloat that erodes loop clock speed.Votes: 0GitHub stars: 10
- Vignelli Canon Design SystemMassimo Vignelli's design discipline distilled from The Vignelli Canon — the Intangibles (semantics, discipline, appropriateness, timelessness, equity) and the Tangibles (grid, six typefaces, two-size scale, rulers, primary-color-as-identifier, white space) as an applyable method, plus railway-signage module logic, a deterministic token generator, and production notes. For disciplined, timeless, Swiss-modernist artifacts: identity systems, style guides, editorial/poster layouts, transit signa...Votes: 0GitHub stars: 10
- CommitCreate repository-adaptive checkpoint commits for coherent work, including requests to split changes into commits and push; publication remains separately authorizedVotes: 0GitHub stars: 10
- InvestigateRoot cause analysis skill — diagnose bugs systematically before fixing. Iron Law: no fix without a confirmed hypothesis. Uses scope lock, 3-strike escalation, and structured debug reports.Votes: 0GitHub stars: 10
- Merge PrIntegrate an exact reviewed PR under repository policy, choose truthful history semantics, and verify cleanupVotes: 0GitHub stars: 10
- ProviderInspect or select a Clade execution connection while keeping agent runtime, inference provider, wire protocol, and model distinct. Use for Claude/Codex runtime selection, Anthropic/OpenAI/MiniMax/Kimi/custom gateways, model routing, or connection troubleshooting.Votes: 0GitHub stars: 10
- ResearchResearch external tools/competitors for a topic and write findings to BRAINSTORM.md (project topics) or ~/.claude/research/ (personal topics). Use when user says "/research [topic]".Votes: 0GitHub stars: 10
- Review PrReview an exact PR head in isolation using trusted-base instructions and execution evidenceVotes: 0GitHub stars: 10
- StatusShow a provider-neutral, freshness-aware snapshot of active Agent work, Git delivery, execution identity, and usage limits. Use for “what's going on right now”, what is running, progress updates, active runtime/provider/model, or stuck-work checks.Votes: 0GitHub stars: 10
- Codex UsageShow Codex rate-limit usage and pace, or configure the native Codex status lineVotes: 0GitHub stars: 10
- CommitCreate repository-adaptive checkpoint commits for coherent work, including requests to split changes into commits and push; publication remains separately authorizedVotes: 0GitHub stars: 10
- Create PrPublish or update one repository-adaptive, exact-SHA pull request without duplicating or broadening authorityVotes: 0GitHub stars: 10
- CsoSecurity audit skill — systematic OWASP + STRIDE review of a project. Covers attack surface, secrets archaeology, dependency supply chain, OWASP Top 10, threat modeling, and false-positive filtering. Outputs a prioritized findings report.Votes: 0GitHub stars: 10
- DeliveryAdaptive, resumable Git delivery across repositories and agent runtimes — probe policy, checkpoint coherent work, publish, review, integrate, and verify cleanupVotes: 0GitHub stars: 10
- Document ReleasePost-ship documentation sync — updates README, CHANGELOG, AGENTS.md, and TODOS after a release. Ensures docs never drift from code. Run after /commit or /ship before closing a PR.Votes: 0GitHub stars: 10
- Frontend DesignCreate, prototype, redesign, audit, or optimize production-grade interfaces across websites, responsive/mobile web, iOS/iPadOS/macOS, Android, Windows, Electron/Tauri, Flutter/React Native, and other local/native apps — UI/UX, visual polish, named or tunable themes and design variants, components, interaction and motion, design systems, and decks, including requests such as 设计页面、优化网页/界面/UI、设计主题/视觉风格/界面版本. Runs a platform-aware benchmark, design-direction profiles, an optional preview checkpoi...Votes: 0GitHub stars: 10
- GoAccept the recommendation from the most recent A/B/C option set and execute it without re-asking — for \"按你推荐的来\" / \"go with your pick\", when the user glanced at the options and wants the recommended branch executed immediately.Votes: 0GitHub stars: 10
- GreenRun the repository's real CI gates locally and drive them to green — read the failing step, fix the cause, re-run only that job, repeat. Use before pushing, after a red hosted run, or whenever \"make CI pass\" is the ask. Never weakens a gate to make it pass.Votes: 0GitHub stars: 10
- HandoffEnd-of-session context handoff. Saves session state so the next session or a parallel agent can pick up exactly where the left off. Run this when context is getting full (~80%) or before stopping work.Votes: 0GitHub stars: 10
- IncidentIncident response mode — diagnose a production issue, write a postmortem, add follow-up tasks to TODO.md. Use when user says \"/incident [description]\".Votes: 0GitHub stars: 10
- InvestigateRoot cause analysis skill — diagnose bugs systematically before fixing. Iron Law: no fix without a confirmed hypothesis. Uses scope lock, 3-strike escalation, and structured debug reports.Votes: 0GitHub stars: 10
- MapScan project structure and generate ARCHITECTURE.md with a Mermaid module relationship diagram. Use when user says \"/map\".Votes: 0GitHub stars: 10
- Merge PrIntegrate an exact reviewed PR under repository policy, choose truthful history semantics, and verify cleanupVotes: 0GitHub stars: 10
- Next\\\"What should I work on next?\\\" — two modes. Fast mode (default): one-shot recommendation from docs + git state, ≤15 lines, no interview. Deep mode (`/next deep` or when user asks to explore priorities): multi-round interview to surface the best move.Votes: 0GitHub stars: 10
- OrchestrateProject orchestrator mode — ask clarifying questions, decompose goals into tasks, write proposed-tasks.md for workers to execute. Use inside the Orchestrator Web UI.Votes: 0GitHub stars: 10
- PickupStart-of-session context pickup. Reads the latest handoff file and resumes work where the last session left off. Run this at the start of a new session if a handoff file exists.Votes: 0GitHub stars: 10
- ProviderInspect or select a Clade execution connection while keeping agent runtime, inference provider, wire protocol, and model distinct. Use for Claude/Codex runtime selection, Anthropic/OpenAI/MiniMax/Kimi/custom gateways, model routing, or connection troubleshooting.Votes: 0GitHub stars: 10
- ResearchResearch external tools/competitors for a topic and write findings to BRAINSTORM.md (project topics) or ~/.clade/research/ (personal topics). Use when user says \"/research [topic]\".Votes: 0GitHub stars: 10
- RetroEngineering retrospective — generates a data-driven report of development velocity, commit patterns, hotspots, and team insights from git history. Saves results for week-over-week comparison.Votes: 0GitHub stars: 10