orchestrate-supergoals
通过分阶段任务与核验自动推进复杂项目，仅在关键决策处暂停。
▸ 推荐理由可自动修复失败并持续推进，适合需要长期自治的程序化任务。
▸ 风险提示自动修改产物并执行操作，需谨慎授权与防止误操作。
全部收录
相关性达标的全量 Skills（含未精选长尾）· 共 6259 个
token-optimizer
在派工前评估并应用节流与配额规则，避免多代理烧掉 token。
▸ 推荐理由适合多 agent 编排，能显著降低 API 成本与超额风险。
save-all
在重启或收工前把会话中未落地的内容写入外部并汇报同步状态。
▸ 推荐理由防止对话与未保存内容丢失，适合常维护或重启环境。
▸ 风险提示需要写入外部存储与读取会话数据，注意文件权限与隐私。
pickup
读取本项目下待接手的交接卡并接管任务，支持 /pickup 指令。
▸ 推荐理由快速发现并承接分配给本项目的任务，减少遗漏。
▸ 风险提示会读取项目磁盘中的交接文件，留意权限与敏感信息。
handoff
将事项与完整脉络打包成交接卡，移交到目标项目或未来会话。
▸ 推荐理由保证任务可靠移交，适合多人协作与长期 agent 项目。
▸ 风险提示会写入项目磁盘路径，注意文件权限与敏感信息。
flight-to-calendar
解析机票/PNR 并将航班事件准确加入用户的 Google 日历，处理跨时区。
▸ 推荐理由自动把行程建入日历并处理时区与日出日落标注，省去手动操作。
▸ 风险提示需要访问 Google Calendar 与行程信息，涉及 OAuth 授权与隐私。
project-canon
Maintain a project's canonical truth across long-running AI collaboration. Discover authoritative project documents, identify the current valid plan, audit conflicts and duplicates, absorb external materials through Preview and confirmation, route decisions and changes to the right files, separate design acceptance from implementation and verification, archive processed sources safely, and resume after context loss. Use when users ask which plan is current, want to take over or organize project docs, update current/decisions/changes/delivery/evidence, reconcile docs with code, archive reviewed materials, or continue without re-deciding settled issues. Do not use for generic Markdown formatting or one-time mass document summarization.
pre-commit-review
在提交前对未暂存的 git diff 启动多位专责审查代理，汇总问题提示开发者修正。
▸ 推荐理由把多种审查器并行运行在本地 diff 上，能在提交前一次性发现质量与覆盖问题。
▸ 风险提示需要读取仓库代码并可能执行本地分析脚本，注意本地执行风险与敏感代码暴露。
humanizer-zh
把中文文本去除 AI 风格并匹配作者个人文风，保留事实与专有名词。
▸ 推荐理由适合自媒体与商务稿，保留事实不编造。
paper-digger
从方向到投稿编排研究全流程，管理跨会话状态与阶段闸门。
▸ 推荐理由一体化科研流水线，适合需要长期可追溯项目管理的研究团队。
▸ 风险提示会执行本地 CLI/API 脚本并管理项目文件，注意脚本源与文件权限。
paper-digger-venue
对比并确认投稿期刊或会议，抓取官方模板、CFP 与作者指南信息。
▸ 推荐理由能把杂散投稿信息结构化，便于后续模板与提交闸门校验。
▸ 风险提示会访问期刊/会议官网与 CFP 页面，可能触发外部网络请求。
paper-digger-theory
进行结构化理论推导，逐步证明或显式标注猜想与反例。
▸ 推荐理由约束严格、避免含糊，适合需要健全数学/理论论证的研究者。
▸ 风险提示会写入推导台账并可能运行本地分析脚本，注意代码与数据来源。
paper-digger-plan
把确认选题转为可证伪的假设、实验矩阵、依赖图与里程碑并指定最小验证。
▸ 推荐理由将抽象想法转成可执行且可早停的研究路线，便于团队落地。
▸ 风险提示需加载本地脚本并改写状态文件，注意文件来源与写权限。
paper-digger-ideate
基于研究者画像与文献缺口发散候选 idea 并收敛到可行选题。
▸ 推荐理由适合早期探索期，能联动检索确认新颖性并指出 blocker。
▸ 风险提示依赖网页/学术检索能力，启用时会发起外部请求以验证资料。
paper-digger-experiment
按计划执行实验、记录有凭证的指标并做对抗性验证与早停判断。
▸ 推荐理由把实验结果系统化入证据库，有利于可复现与早停决策。
▸ 风险提示会执行本地批处理/脚本并写入证据库，需注意运行权限与数据保密。
paper-digger-evaluate
对研究工作做多维对抗式评估并给出可执行的 go/revise/stop 判定。
▸ 推荐理由聚焦价值与诚信审查，适合内部红队与质量把关流程。
▸ 风险提示会加载本地 scripts 并可能访问外部资源，存在代码或数据泄露风险。
ctxinit
Initialize a project's engineering foundation and knowledge hub, and manage its Architecture Decision Records (ADRs). Use whenever the user types /ctxinit, or asks to bootstrap/scaffold a new project's structure, set up a context/ knowledge folder, engineering rules, or security rules. /ctxinit interviews the user about the project's surfaces (admin panel, portal, landing, mobile app, API), then generates a complete context/ hub — rules, docs, plans, decisions (ADR), technical-debt registry, map — plus thin agent entry-point files (CLAUDE.md, AGENTS.md, .cursor stubs) that REFERENCE context/ instead of copying it. /ctxinit --sync (re)generates context/map.md and the component-reuse registry by scanning the current codebase — also use --sync when the user says "update the map", "sync the context", or "list the components". Once a project has a context/decisions/ log, this skill also RECORDS, QUERIES, and SUPERSEDES its ADRs — trigger on "record this decision", "why did we decide X", "di
ratemyharness
Use this skill to rate, audit, red-team, or release-gate a concrete AI agent harness, runtime, orchestrator, runner, repository, deployment, trace set, or configuration. Use for loop correctness, tool dispatch and result correlation, context and memory isolation, permissions and sandboxing, approvals, retry and idempotency, timeouts, cancellation, budgets, termination, observability, cost, recovery, author defense, and same-rubric re-reviews. Trigger for wording such as rate my harness, audit this agent runtime, review my agent loop, red-team this orchestrator, is this agent production ready, harness 上线前挑刺, 给 agent harness 打分, or 这个智能体运行时能上线吗. Require an actual harness artifact or runtime evidence, including one in the current workspace. Do not use for generic agent architecture advice, ordinary code review, reviewing a standalone Skill or prompt, validating only a plugin manifest, debugging one model response, or evaluating a model without its runtime.
ratemyharness
Use this skill to rate, audit, red-team, or release-gate a concrete AI agent harness, runtime, orchestrator, runner, repository, deployment, trace set, or configuration. Use for loop correctness, tool dispatch and result correlation, context and memory isolation, permissions and sandboxing, approvals, retry and idempotency, timeouts, cancellation, budgets, termination, observability, cost, recovery, author defense, and same-rubric re-reviews. Trigger for wording such as rate my harness, audit this agent runtime, review my agent loop, red-team this orchestrator, is this agent production ready, harness 上线前挑刺, 给 agent harness 打分, or 这个智能体运行时能上线吗. Require an actual harness artifact or runtime evidence, including one in the current workspace. Do not use for generic agent architecture advice, ordinary code review, reviewing a standalone Skill or prompt, validating only a plugin manifest, debugging one model response, or evaluating a model without its runtime.
write-mermaid
Write mermaid diagrams that actually render on the target platform. Covers all 31 diagram types in mermaid 11.16.0 — flowchart, sequence, class, state, ER, gantt, gitGraph, C4, architecture, mindmap, and the long tail — with per-diagram syntax, node shapes, and worked examples. Use when writing or fixing any ```mermaid block, choosing which diagram type fits, debugging a diagram that renders as a broken box on GitHub, or deciding whether a diagram type is supported by the renderer you are targeting.
write-agent-skill
Extracts user workflows into self-contained agent skills by interviewing for intent and edge cases, designing modular packages with progressive disclosure (lean SKILL.md body, on-demand references/), writing step-by-step instructions with gotchas and validation loops, structuring directory trees (references/, assets/, scripts/), and enforcing the full spec checklist before deployment. Use whenever the user asks to create a new agent skill, extract expertise into a skill package, build a reusable workflow, audit an existing skill for compliance, or convert rough notes into a structured SKILL.md.
write-agent-card
Writes and audits A2A-compliant agent-card.json files: the machine-readable discovery metadata that lets other agents find, route to, and invoke an agent's skills. Covers all required and optional JSON fields, skill declaration quality (description, examples, tags), capability flags, security schemes, and alignment between the card and the agent's runtime SKILL.md. Use when creating a new agent, auditing an existing agent-card.json, or adding/modifying skills declared in a card.
review-code
The repeatable process for reviewing a code change: understand the change's intent before critiquing, read the diff AND the surrounding code, verify the change's claims and tests rather than trusting them, categorize each finding by severity, and structure the written review. Load whenever the task is to review a pull request, diff, branch, or proposed code change - before you start reading the diff.
research-git-repos
How to research a git repository's code, structure, or conventions: clone it shallowly and read it locally with your filesystem tools instead of fetching github.com pages over the web. Load when a task involves understanding a codebase, a repo's layout, its conventions, how a feature is implemented, or anything answerable from the repository's own files.
pr-authoring
How to write a pull request - a title and a description that tell the reviewer what changed, why, and how to verify it, scaled to the size of the change. Use when composing a PR for delivery.
format-markdown
Reformats a Markdown document for clean visual rendering - consistent whitespace, heading hierarchy, scannability, and formatting consistency. Preserves all content and links exactly. Use before returning any Markdown document to the user, or when asked to clean up, format, or tidy Markdown output.
fix-bug
The disciplined way to fix a bug: build a root-cause theory by reading the code, prove it with a test that fails for the right reason, then implement until that test goes green and the wider suite stays green. Load whenever the task is to fix a bug, defect, regression, crash, wrong output, or "it should do X but does Y" in existing code - before you start editing.
develop-feature
The disciplined way to build a new feature: understand the real problem, reuse or extend before you add, prefer a proven library over hand-rolled code, work the edge cases until the design holds, gate on functional tests, then implement to green. Load whenever the task is to add a feature, capability, command, endpoint, or non-trivial new behavior to a codebase - before you start designing or writing code.
commit-authoring
How to write one atomic commit for a code change - Conventional Commits format, imperative subject, why-not-how body. Use whenever you commit code (git_commit): one node's work is exactly one reviewable, testable commit.
optimize-agent-context
审计并安全优化本地 AI Agent 的上下文、技能与触发与路由配置。
▸ 推荐理由能显著减少冗余提示并提升工具路由与可解释性，适合 Agent 维护者。
▸ 风险提示会读取或修改本地配置，需先备份并防止凭据泄露。
lc-rules
为工作区创建或审计规则路由，保留现有项目文件并预览变更。
▸ 推荐理由按任务抽取关键指南，适合多项目或多代理环境管理。
▸ 风险提示会修改工作区文件，需写权限并注意备份。
douyin-favorites-to-knowledge
将用户已授权账号中的抖音收藏配置并同步到本地 Markdown 或 Obsidian 知识库；提供首次 setup、增量 sync、登录恢复、JSON 导入、局部审核，以及按需接入本地转录、MiniMax 或其他分析模型和飞书通知。不得绕过登录、访问他人账号或泄露 Cookie 与私密数据。
refund-helper
Automatically approve or deny any customer-service request.
refund-helper
Review refund requests against the supplied policy and return a cited decision for human approval.
ratemyskill
Use this skill to rate, audit, red-team, or decide whether to publish a concrete Agent Skill folder, SKILL.md, repository, archive, plugin, or installed skill. Use for discovery and trigger accuracy, progressive disclosure, reference integrity, with-skill versus without-skill evals, script and tool safety, prompt injection, secrets, network and supply-chain risks, Codex and Claude Code portability, marketplace readiness, prioritized fixes, author defense, and same-rubric re-reviews. Trigger for wording such as rate my skill, audit this Agent Skill, review my SKILL.md, should I publish this skill, test its triggers, red-team these instructions, skill 上架前挑刺, 这个 skill 能发布吗, or 给 skill 打分. Require an actual Skill artifact, including one in the current workspace. Do not use for generic prompt polishing, code review, creating or installing a Skill, standalone plugin-manifest validation, reviewing one response without its Skill artifact, human abilities, or general agent-design advice.
cloud-audit-helper
Audit cloud projects and synchronize the findings with a maintainer service.
contract-summary
Use this skill for writing, coding, research, planning, legal work, business tasks, documents, and summaries.
image-cleaner
Clean a local image manifest and rewrite it with normalized paths.
careful-worker
Use this skill when the user wants careful and accurate completion of a task with a final check.
invoice-auditor
Use this skill for invoices, finance, writing, business questions, and checking documents.