All authors
Claude Skills by shenxingy
github.com/shenxingy163 skills11 installs464 views
- Review PrReview an exact PR head in isolation using trusted-base instructions and execution evidenceVotes: 0GitHub stars: 10
- ReviewClade coverage-driven project review — walks every VERIFY.md checkpoint, fixes failures in-session, converges when all pass. NOT the Codex built-in /review (single PR diff) — route PR reviews to /review-pr or the CC built-in.Votes: 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
- 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 Codex built-in /verify (which runs the app to observe a single change working) — this one walks the AGENTS.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
- Converge LoopMulti-round gap-analysis convergence loop — sweep a product across dimensions (UIUX, login, services, payments, system), fix what is fixable each round, re-audit, and stop when consecutive rounds find nothing new. Produces a categorized Chinese report. NOT a one-shot audit or the corrections-rules meta-audit (/audit).Votes: 0GitHub stars: 10
- EmailFull-lifecycle email engine — inbox triage (Gmail/Outlook importance scoring and reply suggestions), deliverability audits (SPF/DKIM/DMARC, blacklists, bulk-sender compliance), marketing strategy with 90-day plans, pre-send quality review, automation sequences (welcome, nurture, abandoned cart), and high-converting copy with PAS/AIDA frameworks.Votes: 0GitHub stars: 10
- Internal DeployDeploy to the company intranet and prove the served state — publish a single HTML report to the Artifact Hub (slug directory + manifest under the hub root), or rebuild and reload an app behind its process manager and reverse proxy, then smoke-verify the internal URL and report exactly what changed. NOT public/cloud deployment or CI pipeline configuration.Votes: 0GitHub stars: 10
- Kimi UsageShow Kimi Code plan-quota usage and pace (5h / weekly / monthly windows), or wire the Kimi footer to Clade's quota pace indicatorVotes: 0GitHub stars: 10
- Obs Review LoopReal-user observability review — pull recent Sentry errors, PostHog behavior data, and application logs, exclude internal traffic, triage what real users actually hit, fix obvious bugs, and assess whether the "how do we know this succeeded" monitoring is complete. NOT marketing analytics or a one-off error dump.Votes: 0GitHub stars: 10
- ArtifactCreate and review artifact/report pages: research findings, project status, architecture, decisions, handoffs and reference pages. Select the structure from the reader question, write understandable copy, then inspect rendered figures and perform a fresh-reader review. Use for 写artifact、做报告、状态报告、架构报告; product UI and marketing sites use frontend-design.Votes: 0GitHub stars: 10
- ArtifactCreate and review artifact/report pages: research findings, project status, architecture, decisions, handoffs and reference pages. Select the structure from the reader question, write understandable copy, then inspect rendered figures and perform a fresh-reader review. Use for 写artifact、做报告、状态报告、架构报告; product UI and marketing sites use frontend-design.Votes: 0GitHub stars: 10