代码评审
自动化代码审查与分析
plotpickle-architecture-review
BryanHarrisScripts
Scout PlotPickle architecture before non-trivial changes and independently review an exact diff/head against architecture, engineering standards, and the originating spec.
cloud-storage-web
TencentCloudBase
Complete guide for CloudBase cloud storage using Web SDK (@cloudbase/js-sdk) - upload, download, temporary URLs, file management, and best practices.
docs
costiash
Router for the /docs command. Look up Claude documentation, ask plain-English questions, generate interactive courses and HTML changelog reports, check freshness, and sync the local cache. Dispatches to the claude-docs, claude-docs-validate, claude-docs-course, and claude-docs-changelog skills.
deft-directive-pre-pr
deftai
Iterative pre-PR quality improvement loop. Use before pushing a branch for PR creation -- after completing implementation but before task check. Cycles through Read-Write-Lint-Diff until a full pass produces zero changes.
rafter-code-review
Raftersecurity
"REQUIRED before declaring a task done when the diff touches user input, SQL, shell, auth, credentials, file paths, serialization, crypto, network endpoints, data deletion, or dependency surface. Judge by that surface, not the task label — research/experimental/local-only code with none of it can skip this. Walks OWASP/ASVS/MITRE questions the compiler and the test suite won't catch. Pair with rafter run on the same diff. When the diff has that surface, marking it complete without both has been under-delivered — do not claim done."
rafter
Raftersecurity
"Entry point for rafter. Invoke when a sub-skill is unclear, or when the task needs rafter run (remote SAST+SCA), rafter secrets (local secrets-only), rafter audit, policy checks, or command-risk evaluation. Scope by security surface, not task label: engage when the diff touches auth, credentials/secrets/tokens, untrusted input, SQL, shell/exec, file paths, deserialization, crypto, network endpoints, data deletion, or dependencies; for research/experimental/local-only code with none of that, a quick surface check is enough. When such surface IS present and no rafter skill or CLI call has been made, invoke this before handing the task off — an un-evaluated \"done\" on genuine security surface is not done."
rafter
Raftersecurity
"Entry point for rafter. Invoke when a sub-skill is unclear, or when the task needs rafter run (remote SAST+SCA), rafter secrets (local secrets-only), rafter audit, policy checks, or command-risk evaluation. Scope by security surface, not task label: engage when the diff touches auth, credentials/secrets/tokens, untrusted input, SQL, shell/exec, file paths, deserialization, crypto, network endpoints, data deletion, or dependencies; for research/experimental/local-only code with none of that, a quick surface check is enough. When such surface IS present and no rafter skill or CLI call has been made, invoke this before handing the task off — an un-evaluated \"done\" on genuine security surface is not done."
swiftui-view-refactor
Dimillian
Refactor and review SwiftUI view files with strong defaults for small dedicated subviews, MV-over-MVVM data flow, stable view trees, explicit dependency injection, and correct Observation usage. Use when cleaning up a SwiftUI view, splitting long bodies, removing inline actions or side effects, reducing computed some View helpers, or standardizing @Observable and view model initialization patterns.
swiftui-performance-audit
Dimillian
Audit and improve SwiftUI runtime performance from code review and architecture. Use for requests to diagnose slow rendering, janky scrolling, high CPU/memory usage, excessive view updates, or layout thrash in SwiftUI apps, and to provide guidance for user-run Instruments profiling when code review alone is insufficient.
logs
vercel
View Vercel deployment logs. Use when the user says "show logs", "check logs", "vercel logs", or "what went wrong with the deployment".
image-audit
xiaowu89
对图片进行鉴黄、政治、暴恐内容审核。先将图片压缩到 500px/JPEG 后直传 NX API 审核，以表格汇总结果。适用于用户提到图片审核、内容检查、鉴黄、政治识别、暴恐识别、违规扫描、图片安全、JPG/PNG/WebP 审核的场景。
java-audit-skill
AuroraProudmoore
AI驱动的Java/前端代码安全审计技能，实现系统化、高覆盖率的漏洞挖掘。使用场景： (1) 审计Java/Kotlin项目寻找安全漏洞（0day挖掘、代码审计、安全评估） (2) 审计前端项目（JavaScript/TypeScript/React/Vue）寻找安全漏洞 (3) 企业级代码库的安全审计（支持大型项目） (4) 需要高质量、低幻觉率的安全审计报告 (5) CI/CD集成的前期漏洞发现 触发关键词：Java审计、代码审计、安全审计、漏洞挖掘、0day、安全评估、前端审计、React审计、Vue审计、Java security audit、code review for security
stock_analyzer
SiinXu
"分析股票和市场。当用户想要分析单个或多个股票，或进行市场复盘时调用。"
handle-review-feedback
SiinXu
Process external review feedback on your own open PR by converging the full business contract instead of stacking point patches.
sd-meeting-follow-through
platypeeps
Use when the user wants a source-traceable post-meeting package that reconciles intended and actual outcomes, decisions, commitments, unresolved items, and consent-gated follow-through.
amg-wip-payroll-vs-rth-analysis
joecastelino
Analyze an AMG per-store semi-monthly WIP workbook (tech payroll vs RTH / labor relieved to WIP) and produce Joe's service-manager meeting prep — trend table, per-tech gap ranking, talking points, recoverable-$ target. First run 2026-07-08 on "2026- SCWV Wip.xlsx" (Stevens Creek VW); Joe approved the format verbatim.
sd-retro
platypeeps
Use when the user wants an evidence-led, non-blaming retrospective of a project, research effort, meeting, launch, or operational period with lessons and proposed follow-ups.
sd-postmortem
platypeeps
Use when the user wants a formal, evidence-linked, blameless analysis of an incident or failed outcome with defensible causes, safeguard findings, and verifiable corrective actions.
subagent-optimizer
IonDen
Optimizes Claude Code subagents (.claude/agents/.md) and Codex custom agents (.codex/agents/.toml); agent skills (SKILL.md folders) are handled by skill-optimizer. Use when asked to audit, optimise, slim down, or fix those agents: set a proper tools allowlist on a Claude subagent (one with no tools field inherits every tool on each launch), remove Claude keys that make Codex skip an agent, cut bloated or duplicated system prompts, tighten descriptions so they trigger reliably, and right-size the model and reasoning effort. Triggers: "optimize my subagents", "optimise my agents", "audit my subagents", "subagent optimizer", "audit my codex agents", "my agent uses too many tokens", "fix my agent's tools list", "review .claude/agents", "review .codex/agents", "make my agents cheaper".
sd-prose-lint
platypeeps
Use when prose written on the user's behalf — skill bodies, docs, README text, commit or PR text, release notes, outbound drafts — needs a prose lint, style lint, or AI-tell check before it is committed or sent; runs the deterministic Vale gate where it exists and assigns every finding a disposition, degrading gracefully where Vale is absent.
sd-explain
platypeeps
Use when the user wants one complex topic explained accurately for a stated audience, purpose, prior-knowledge level, and depth, with explicit analogy and limitation boundaries.
sd-review
platypeeps
Review the exact current diff with local providers and dispose of the findings locally, never posting them.
sd-grill
platypeeps
Use when the user wants their own proposal, plan, claim, or half-formed idea interrogated one question at a time until it survives an outsider, producing a hardened statement of intent, or an honest account of where it stopped, rather than an implementation.
sd-premortem
platypeeps
Use when the user wants to stress-test an accepted plan before execution by assuming failure, ranking plausible failure modes, and defining indicators, prevention, contingencies, and stop conditions.