AGENT SKILLS · 任务装备
值得安装的 Agent Skills
汇总公开仓库中已验证的 Skills。安装前先看清它能做什么、包内包含什么、热度如何，以及来源是否可靠。
- 目录范围
- 已验证
- Skills
- 23,389
- 仓库
- 3599
- 最近同步
- 2026年11月6日
stefanoskarakasismeta-learn
Captures a completed skill session in depth: three extraction questions (what surprised you, what was wrong, what was missing) become falsifiable pattern statements, logged to /context/skill-sessions.md for meta-synthesis. Trigger on: "capture what we learned", "log this session", "save the learnings", "what did we learn", or any request to encode deeper insights from a completed skill session.
- 安装量
- —
- GitHub Stars
- 9
- 最近更新
- 11月3日
stefanoskarakasismeta-review
Audits any SKILL.md against SKILL-SPEC.md, the repo's skill authoring standard, and returns a scored checklist with prioritized fixes. Trigger on: "review this skill", "audit this SKILL.md", "does this skill meet spec", "is this skill done", "quality check this skill", or any request to validate a skill file against the repo's authoring standard.
- 安装量
- —
- GitHub Stars
- 9
- 最近更新
- 11月3日
stefanoskarakasismeta-synthesis
Reads /context/skill-sessions.md to detect patterns that repeat across 2+ sessions, proposes new guardrails for /context/meta-patterns.md, and proposes brain updates for confirmed learnings. Run on demand or roughly weekly, not as a background job. Trigger on: "run meta-synthesis", "what patterns are emerging", "detect cross-skill signals", "update guardrails", "compound our learnings", "what should we remember".
- 安装量
- —
- GitHub Stars
- 9
- 最近更新
- 11月3日
stefanoskarakasismeta-verify
Runs a second-pass quality check on a skill's output before it goes out, re-checking it against the originating skill's Quality Gate and Operating Rules and returning specific fixes, not just pass/fail. Trigger on: "verify this", "check this before I send it", "second-pass this brief", "did that pass quality gate", or any request to re-check a skill's output before it's delivered externally.
- 安装量
- —
- GitHub Stars
- 9
- 最近更新
- 11月3日
stefanoskarakasispmm-metrics
Defines a North Star Metric and 3-5 Input Metrics, then builds a capped 8-16 metric scorecard across Financial, Customer, Product & GTM, and Process & Growth, flagging vanity and unowned metrics. Trigger on: "what should we measure", "North Star metric", "build a PMM scorecard", "what metrics should I track", "define our key metrics", "set up a metrics framework".
- 安装量
- —
- GitHub Stars
- 9
- 最近更新
- 11月3日
stefanoskarakasispositioning-ideas
Generates 3-5 positioning angles anchored to your named alternatives: different territory to choose from, not five ways of saying "we're better". Use it before positioning-messaging, not instead of it: nothing ships until your pick passes that skill's gate.
- 安装量
- —
- GitHub Stars
- 9
- 最近更新
- 11月3日
stefanoskarakasispositioning-messaging
Builds or audits positioning statements, messaging hierarchies, homepage copy and persona cards using April Dunford's Obviously Awesome framework, in five modes (build, audit, fletch, sales-enablement, homepage). Refuses to generate without a named primary persona and 3+ alternatives including status quo, and blocks output until a 7-point verification gate passes. Use when your messaging is scattered, or sales cannot explain what you do in one sentence.
- 安装量
- —
- GitHub Stars
- 9
- 最近更新
- 11月3日
stefanoskarakasisprd
Co-writes a full Product Requirements Document with an embedded Solution Story, anchored in your brain's positioning and ICP. Use when a PM or PMM needs a PRD, a standalone Solution Story for GTM communications, or help structuring a feature or launch spec.
- 安装量
- —
- GitHub Stars
- 9
- 最近更新
- 11月3日
stefanoskarakasispre-mortem
Runs a cross-functional pre-mortem on a strategic initiative (product launch, pricing change, GTM pivot, new market entry, feature rollout) and surfaces the Tigers, the deal-blocking risks, with owner-assigned action plans. Use before a launch or major move, while what could go wrong is still cheap to fix.
- 安装量
- —
- GitHub Stars
- 9
- 最近更新
- 11月3日
stefanoskarakasisproduct-messaging-playbook
Assembles a single Sales/CS-ready playbook for a new product or feature: problem, story, one named competitive comparison, discovery questions and objection handling. Use when you say "build a messaging playbook," "give sales something they can use for this feature," "handoff doc for sales and CS," or "solution guide for this launch." Assembles from message-house, positioning-messaging and proof-points; does not derive strategy itself.
- 安装量
- —
- GitHub Stars
- 9
- 最近更新
- 11月3日
stefanoskarakasissignal-monitor
Turns the signals you name into at most five opportunities, each tied to a brain field and a Section 7 priority, with evidence, a confidence label and one suggested next move; it never edits your brain. Trigger on: "what changed this week", "weekly opportunities", "signal monitor", "what should we act on", "competitor moves this week", "scan these signals". Related: alternatives-map, positioning-messaging, pmm-okrs, workflow-orchestrator. Not for a leadership brief on competitors (competitive-br
- 安装量
- —
- GitHub Stars
- 9
- 最近更新
- 11月3日
stefanoskarakasisstakeholder-maps
Builds a political map, not an org chart, showing who can kill your launch, who champions it and what to say to each stakeholder, with a Power × Interest grid, conflict map and weekly Sprint Cards. Use when aligning stakeholders around a launch or GTM initiative.
- 安装量
- —
- GitHub Stars
- 9
- 最近更新
- 11月3日
stefanoskarakasisvalue-prop-statements
Fans an existing positioning statement out into segment- and channel-specific value-prop copy variants for marketing, sales and onboarding, without re-running positioning. Trigger with "write value prop statements for [segment]", "adapt our positioning for [channel]", "sales copy for this persona", or any request for segment-specific messaging variants once a canonical positioning statement already exists.
- 安装量
- —
- GitHub Stars
- 9
- 最近更新
- 11月3日
stefanoskarakasiswriting-assistant
Rewrites, sharpens and drafts B2B writing in the writer's real voice: Slack messages, emails, memos, PRDs, decks, plus marketing content (blog, landing page, press release, case study, newsletter, social). Use whenever someone wants to rewrite, tighten, draft or audit copy, asks why copy isn't landing or converting, or says "write a blog post", "landing page copy", "press release", "case study", "LinkedIn post", "draft the newsletter", or "does this sound like AI?"
- 安装量
- —
- GitHub Stars
- 9
- 最近更新
- 11月3日
temporaliotemporal-workflow-design-critic
Critique, audit, or score a Temporal workflow design for correctness, production readiness, and best-practice compliance. Use when asked to review a Temporal architecture, evaluate whether a design is production ready, identify anti-patterns or risks, assess Temporal fitness for a use case, or give a design a thumbs up/down. Not for writing or debugging Temporal code — use temporal-developer for that.
- 安装量
- —
- GitHub Stars
- 8
- 最近更新
- 5月21日
albertaz1992albert-imagebook
Transform photos into illustrations, stickers, paper cutouts and pixel art with reusable style directions, open space and exact-size exports. Use for photo-to-art, 照片转插画, 照片贴纸, named Imagebook styles, or original-and-art comparisons.
- 安装量
- —
- GitHub Stars
- 7
- 最近更新
- 9月19日
temporaliotemporal-serverless
Deploy and operate Temporal Workers on serverless compute (AWS Lambda, GCP Cloud Run) driven by the Worker Controller Instance (WCI). Use when the user mentions: "serverless worker", "Temporal serverless", "Worker Controller Instance", "WCI", "deploy Temporal worker on Lambda", "Lambda packaging", "Lambda timeout", "WCI inspection", "CloudFormation Temporal", "Cloud Run worker", "deploy Temporal worker on Cloud Run".
- 安装量
- —
- GitHub Stars
- 6
- 最近更新
- 10月27日
agent-rigrig-debug
Systematic root-cause debugging for a failing test, production bug, flaky behavior, or unexplained error. Spawns the debugger agent through Phase 1 → 4 (root-cause → pattern analysis → hypothesis → minimal fix). Refuses to propose fixes before evidence is gathered. Triggers on: 'debug', 'why is X failing', 'root cause', 'this isn't working'.
- 安装量
- —
- GitHub Stars
- 3
- 最近更新
- 10月20日
greedy-coabto
Map frontend and backend repository boundaries, inventory LLM API call sites for approval, install and wire the minimum ABTO Browser, App, or Server SDKs, preserve deviceid correlation and Server SDK run IDs, recommend opt-in system or custom events, and verify the resulting ABTO integration. Use for ABTO setup, updates, troubleshooting, Gateway calling, event collection, key placement, or end-to-end integration checks across browser JavaScript, Node.js, Python, Java/Kotlin servers, Flutter/Dart
- 安装量
- —
- GitHub Stars
- 1
- 最近更新
- 11月5日
goldsky-iocompose
Always load this skill whenever the conversation is about Goldsky Compose (the offchain-to-onchain TypeScript framework for oracles, keepers, circuit breakers, and cross-chain automation) — no matter what the user wants to do with it. That includes: asking what Compose is, its docs, pricing, functionality, or limits; building, deploying, or iterating on an app; wiring cron / HTTP / onchain-event triggers, smart wallets, gas sponsorship, secrets, or collections; deploying a worked example (bitcoi
- 安装量
- —
- GitHub Stars
- 0
- 最近更新
- 11月5日
goldsky-iocompose-doctor
Diagnose an existing Goldsky Compose app with failing tasks, crashloops, missed events, cron not firing, HTTP 500s, wallet or gas sponsorship failures, missing secrets, bundler errors, manifest validation failures, or esbuild failures. Use when an app is named alongside a problem involving goldsky compose, including 'No bundler provider available', named wallets without a private key in local dev, and 'Transaction Receipt failed with status'. Load /compose first; inspect status, logs, secrets, a
- 安装量
- —
- GitHub Stars
- 0
- 最近更新
- 11月5日
goldsky-ioonchain-automation
Route event-driven onchain automation that detects activity, applies logic, and submits a transaction in response. Use for 'when X happens onchain, do Y', monitor-and-execute workflows, smart contract calls triggered by events, keepers, protocol automation, auto-claiming or compounding rewards, liquidations, rebalancing, and settlement automation. Combine Turbo/Subgraphs/Mirror for detection with Compose for decisions and execution, including wallets, gas sponsorship, and writeContract. Load /co
- 安装量
- —
- GitHub Stars
- 0
- 最近更新
- 11月5日
priabyinwoven
Inwoven backlog, goals, maps. Use to set up Inwoven, start or resume (Start T318), add, move X above Y, reorder, block, accept, reopen, which goal, propose or save a lesson, validate files
- 安装量
- —
- GitHub Stars
- 0
- 最近更新
- 11月5日
quentin-hickamawb-brainstorm
Propose questions from an analytics workbench investigation's questions, findings, and available data. Use for \"what else should we ask?\", \"what else could we investigate?\", or when open questions run out.
- 安装量
- —
- GitHub Stars
- 0
- 最近更新
- 10月20日