Agent Workflow Claude Skills
4 122 agent workflow skills from 665 authors. They configure the agents themselves: memory, prompts, context and other skills. Half of them fit into 1 844 tokens or less — that is what one costs your context window when the agent loads it. 778 ship runnable scripts rather than instructions alone. 5 of them cannot work without an MCP server, most often task. We also found 589 copies of these same skills sitting in other people's repositories — counted once here, not 589 times.
4 122 unique 665 authors 4 updated this month 506 from vendors
Use multiple Claude agents to investigate and fix independent problems concurrently
Execute implementation plan by dispatching fresh subagent for each task, with code review between tasks
Skills wiki intro - mandatory workflows, search tool, brainstorming triggers
Use when executing implementation plans with independent tasks in the current session
自动汇总团队内 agent、cron、skill 进展与关键事件，生成并推送结构化日报。
Evaluate, score, and review an Agent Skill or SKILL.md using Tessl as the primary evaluator. Use when asked to measure skill quality, score a skill, review a skill against best practices, compare before/after skill revisions, or generate structured improvement feedback for a skill directory or SKILL.md file.
Intercept the response flow to offer the user a choice about response depth **before** Claude answers Offers the user an informed choice about how much response depth to consume before answering. Use this skill when the user explicitly wants to control response length, depth, or token budget. "response length", "answer depth", "short version", "brief answer", "detailed answer", "exhaustive answer", "respuesta corta vs larga", "cuántos tokens", "ahorrar tokens", "responde al 50%", "dame la versión corta", "quiero controlar cuánto usas", or clear variants where the user is explicitly asking to control answer size or depth. session (maintain it), the request is clearly a one-word answer, or "token" refers to auth/session/payment tokens rather than response size.
工作即技能：每次完成一项有复用价值的工作后，自动评估并封装为可复用 Skill。让团队在工作中持续进化。
小红书（创作者中心）登录拿 cookies、发布笔记、导出数据的单一入口技能（浏览器交互委托 agent-browser-stealth）
> Audit system prompts, agent prompts, router prompts, tool/function-call prompts, and coding-agent instructions as executable contracts. Use before writing or seeding prompts; blocks vague "fix this / write code" tasks missing ownership and verification. Works with Hermes, Claude Code, Codex, OpenCode, OpenClaw.
Diagnose Commonplace project layout, promoted-skill discovery, command paths, package commands, and launch-environment failures.
Experimentally revise a note with fresh critic, author, synthesizer, and blind-judge agents while retaining the incumbent as fallback.
Write one KB note under its collection and type contracts, validate it, and hand broader graph discovery to cp-skill-connect.
Write or update a local code-grounded agent memory system review from a GitHub repository reference, including checkout refresh, optional sub-agent drafting, semantic QA, and validation.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.
把执行性编码/调查任务整包交给 DeepSeek 后台执行，省主会话额度。后台运行，完成后自动通知。支持并行多任务，支持续接（resume）上次会话继续派发后续任务。
向 Codex (GPT-5.6) 咨询复杂问题 / 要第二意见 / 派发需要强推理的任务。后台运行，完成后自动通知。支持并行多任务，支持续接（resume）上次会话继续派发后续任务。
把执行性编码/调查任务整包交给 gemini 后台执行，省主会话额度。后台运行，完成后自动通知。支持并行多任务，支持续接（resume）上次会话继续派发后续任务。
把关键决策/验收类任务交给 Claude Opus 执行。后台运行，完成后自动通知。支持并行多任务，支持续接（resume）上次会话继续派发后续任务。
Operate HitKeep safely in isolated Git worktrees. Use when inspecting workspace state, resolving ports or URLs, starting or stopping development services, coordinating concurrent agents or QA runs, reusing active runs, reading bounded logs, or preparing a secret-free handoff.
> Receive and verify Anthropic Claude Managed Agents (CMA) webhooks. Use when setting up Claude Managed Agents webhook handlers, debugging signature verification, or handling agent session and vault events like session.status_idled, session.status_terminated, session.thread_created, vault.created, or vault_credential.refresh_failed.
Guide, workflow guide, 流程导航、我该用哪个 skill、下一步做什么。Use when: 需要扫描当前项目已有文档和准出状态，判断 testany-eng 主流程所处阶段，并推荐下一步最合适的 skill；当 Test Spec 已具备下游 handoff 条件时，也可推荐进入 testany-bot 自动化落地分支。
撰写提示词、优化提示词、改写 Prompt、Prompt 优化。将模糊的想法转化为精确有效的 AI 提示词，支持 ChatGPT、Claude、Gemini、DeepSeek、豆包、智谱等多平台。
Apply agent-starter patterns to an EXISTING project - audits the codebase, proposes components by invasiveness tier (hooks, skills, CLAUDE.md, lint configs, patterns), and applies only what the developer approves. Use when the user says adopt, retrofit, "apply agent-starter to this project", or wants starter patterns in an existing codebase.
>- Use when asked to set up PR attestation, install harness-scs attestation hook, configure agent attestor, troubleshoot why agent attestation isn't uploading, or reconfigure an existing attestation hook (different SCM, new cosign key, updated Harness identity). why isn't my agent attestation uploading, set up agent attestation, configure PR signing, install attestation hook, configure claude attestation.
>- Create and update Harness AI agent instances - standalone templates for agentic workflows in pipelines. Use when asked to create agent, update agent, modify agent spec, build autonomous systems, or work with AI agents.
>- Author and execute "prompt packs" — a big job broken into a sequence of self-contained, independently-shippable prompts, each run in its own fresh chat so a single change never dies to a context/token limit. Also writes paste-ready handoff briefings to resume a dying chat or relay work to another tool (e.g. Codex). ALWAYS invoke when the user says any of "make a prompt pack", "turn this into prompts", "break this into phases", "prompts I can run in separate chats", "I'm running out of tokens/context", "write me a handoff", "a prompt I can paste into a new chat", "this is too big for one chat", "build plan I can hand off", or "execute Pxx / phase X from the pack". Also invoke proactively when a requested change is too large or too risky to finish safely in one session and should be decomposed into ordered, verifiable steps.
>- Run the idea-to-ship pipeline AUTONOMOUSLY, in character as a grounded founder-persona — composing ideate → deep-dive → prompt-pack → build-loop to take a real, grounded niche to a near-finish-line-AIMED first-draft product plus an honest ledger of what only a human or the market can finish. ALWAYS invoke when the user says any of "run autopilot", "build this idea→ship autonomously", "spin up a grounded founder and build it", "fly the whole pipeline end to end", or "autonomous first-draft from a concept". It composes the existing skills, never reimplementing them, and states its honest bounds — a near-finish-line first draft, NOT a finished or market-validated product (~80% craft ceiling; grounding firewall; its go/kill calls are a signal). Do NOT use to drive each phase by hand (use the skills directly), when there's no real grounding (you'd be inventing demand), or when you need market validation (the human handoff).
>- Take a fuzzy idea (or an existing thing you want to improve) through a disciplined funnel — explore → pressure-test → converge — and produce one honest co-founder (permission to overrule you), forces a success metric and a kill criterion before any roadmap, and hands off cleanly to the prompt-pack skill for building. ALWAYS invoke when the user says any of "help me figure out what to build", "I have an idea for…", "is this idea any good", "pressure-test this idea", "should I build / should I rebuild X", "evaluate whether my app/idea is worth building", "where are we really at", "is this idea or app worth pursuing", "iron out / scope / spec this concept", or "turn my idea into a plan/roadmap". Also invoke proactively when someone is reasoning about WHAT to build or WHETHER an idea is worth it — before any code or prompt pack exists.
Use when the user wants to AUTHOR an unattended dispatch for either: (1) a goal-driven evaluator-optimizer loop of the GENERATE-AND-SELECT kind (generate candidates → grade against a rubric → iterate by reason-code → keep the best; the human picks the final selection), or (2) a lean build-to-spec run whose build spec is ALREADY FROZEN (approved ADR / locked design / accepted machine-checkable AC) and the only missing piece is the unattended-execution wrapper. A fresh-session agent runs the dispatch hands-off while the human only watches traffic-light push notifications. Interview-style forcing questions lock the spec, then it emits a self-contained dispatch markdown + a channel-agnostic notification protocol. This is the upstream SPEC AUTHOR, NOT a runtime: the dispatch is run by Claude Code's /goal, a headless `-p` session, or any unattended agent — /goal is the engine, this writes what you feed it. It NEVER authors build specs, product decisions, or AC — creating a build spec / PRD from raw input is prd-create. NOT a time scheduler (/loop or cron), NOT a recurring-push registrar (skill-cron).
Use when the user wants to register, inspect, manually run, or remove scheduled Claude skills with Telegram push notifications. Presents a menu, discovers schedulable skills with headless-prompt frontmatter, converts natural-language schedules into cron entries with conflict confirmation, writes managed config, and verifies notification delivery. NOT for one-off task execution without scheduling or for running skills that lack a headless prompt.
Use when the user is unsure which kc_ai_skills workflow skill to use, or describes work involving PRD, SD/software design, FR, AC/acceptance criteria, ADR, tickets, implementation, debugging, release checks, or unattended agent execution. Triage the request with at most one clarifying question when needed, explain the route in plain language, then hand off to the right specialist skill. This is an entry router only: it does not write PRDs, specs, ADRs, tickets, or dispatches itself.
Create modular skill documents (SKILL.md files) for Claude Code. Use this skill whenever a task requires generating reusable knowledge documents, capturing domain expertise, or building skills that encode workflows, APIs, or specialized techniques. Invoke this whenever you need to write a SKILL.md from scratch, even if the user doesn't explicitly ask for a "skill".
Use the xlsx skill tool to create, read, modify and analyze Excel spreadsheets with formulas and formatting.
Refined skill for enforcing Anthropic corporate brand identity with precise HEX token usage.
Methods for calculating or retrieving the number of tokens consumed during an LLM inference task.
Use this to structure the final output into the required JSON schema, calculating precise token usage based on the retrieved context.
Extracts and tracks the consumed token usage from an LLM API response to monitor API cost and utilization.
openInvest multi-asset AI investment committee — **daily use**. Read portfolio / live prices / strategy / decision history / adjust positions / run a 4-role LLM committee for an investment verdict. Supports any yfinance symbol (A-share / HK / US / ETF / crypto / commodities) and any currency. **Two paths** — (1) Coordinator, Claude Code spawns 4 subagents, saves DeepSeek tokens; (2) Direct, any agent (Codex / Hermes / OpenClaw / Cursor / Cline / plain script) runs `run.sh run_committee <SYM>` for a one-shot verdict. **Trigger scenarios** — "show portfolio / 看看我的持仓", "how is my P&L / 我现在涨了多少", "should I buy/sell X / 该不该买卖X", "analyze X / 分析一下X", "run committee on X / 跑委员会", "track AAPL / 跟踪苹果", "add/trim a position, log a trade / 加仓减仓记一笔". **First-time install uses a separate skill `invest-setup`** (switch to it when `doctor` returns `needs_setup`). Backend — longsizhuo/openInvest.
>- Install AI agent skills as roles & behaviors from any source — local folder, GitHub, GitLab, SSH git URL. Zero-dependency CLI with 86+ agent targets.
Set up persistent agent identity files (AGENT.md, USER.md, MEMORY.md) and teach the agent to read them at every session start. Works in any Claude Code project — no external dependencies required. Trigger words: who am I, identity, remember me, agent name, my principles, who are you, what are my values.
Teach cross-session memory patterns using MEMORY.md — what to save, how to organize it, how to maintain it over time, and how to structure topic files as memory grows. Works in any Claude Code project with no external dependencies. Trigger words: remember this, save for later, across sessions, persistent memory, don't forget, note this, keep this, write this down.
View this agent's digital passport (identity + trust + allowed/forbidden actions) and verify a peer's passport against a proposed action (EXO 3.0).
Score a task or workflow on its coordination-vs-judgment ratio to tell whether it's a good agent candidate (EXO 3.0 task-decomposition matrix).
Establish and recover persistent agent identity that survives context compaction, session restarts, and autonomous operation. Use when an agent needs to know who it is, recover after context compression, orient at session start, or understand the identity infrastructure. Trigger words: who am I, remember, identity, after restart, compaction, context loss, who am I working with, my principles.
Instar-specific development skill used by the instar-developing agent (Echo, or any agent assigned instar-dev responsibilities). Wraps /build with mandatory side-effects review, signal-vs-authority principle check, and artifact generation. Structural enforcement via pre-commit/pre-push hooks — the instar repo refuses commits and pushes that didn't come through this skill. NOT a user-facing skill — end users should never invoke it.
Spawn, monitor, and communicate with persistent Claude Code sessions running in the background. Use when a task needs to run without blocking the current session, when the user asks to do something in the background, or when a long-running task needs its own context window. Trigger words: background task, spawn session, persistent, run in background, parallel, separate session, async task.