Agent Skill 目录与安装教程 — ClawHub、SkillsMP 与开源 Skill

io.github.affaan-m/ECC/blueprint

Turn a one-line objective into a step-by-step construction plan for multi-session, multi-agent engineering projects: one-PR-sized steps with self-contained context briefs, dependency graph with parallel-step detection, adversarial review gate, and plan mutation protocol. Use when planning a large feature, refactor, or roadmap that spans multiple PRs or sessions; not for single-PR tasks or when the user says "just do it".

io.github.Hmbown/CodeWhale/cw-slice

Use before writing code for any Codewhale feature, upgrade, or refactor: find the existing owner of the behavior, bound the change to one reviewable slice, and fix the evidence bar before you start.

io.github.tabler/tabler/backward-compat

Keep a change to `@tabler/core` backward compatible, so a patch or minor release never breaks a project that updates. Use before renaming, removing or changing the meaning of anything a user can touch — a class, a `--tblr-*` custom property, a Sass variable, mixin or function, a `data-*` attribute or option, a JS export, an event, a file under `dist/`, a default value — and whenever a changeset on `dev` looks like it needs a `major` bump. Also consult it proactively when a cleanup or refactor in `core/` deletes something, since "dead" code is often somebody's API. Covers what counts as public API, the `deprecated` files where compatibility code lives, the alias patterns, the `check:compat` gate, and what to do when a break cannot be avoided.

io.github.github/awesome-copilot/macos-golden-gate-design

Design, implement, review, or refactor native macOS 27 Golden Gate interfaces in SwiftUI or AppKit. Use when a Mac app must match Apple's current macOS 27 UI kit and restrained Liquid Glass language: integrated windows, full-height sidebars, native toolbars, flat lists, tables, and forms, clear pane boundaries, accessible materials, and removal of unnecessary nested cards, framed panels, or glassmorphism. Also use for Figma macOS 27 design-to-code work and audits of interfaces that feel too boxed.

io.github.tabler/tabler/ui-component

Build or extend a shared Astro component in `shared/ui/*.astro` (or `shared/components/**`) — the library that both the preview and the docs render. Use whenever the user asks for a new component, for a new prop, variant or size on an existing one, or for a refactor of a shared component. Covers the Props interface, the prop-name dictionary, class composition, slots, the `as` pitfall, and the follow-ups (demo page, docs, changeset) a new component needs.

io.github.addyosmani/agent-skills/test-driven-development

Drives development with tests using the red-green-refactor loop. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.

io.github.NousResearch/hermes-agent/test-driven-development

TDD: enforce RED-GREEN-REFACTOR, tests before code.

io.github.tabler/tabler/html-diff

Prove that a refactor changes no rendered HTML, using the `html-diff` harness over every preview page. Use before and after any change that is meant to be output-neutral — extracting or renaming a component, replacing hand-written markup with a `shared/ui` component, reordering props, restructuring a layout, migrating SCSS class emission — and whenever the user asks whether a change is safe or byte-identical. Covers capturing the baseline, reading the diff, and what counts as an acceptable difference.

io.github.mattpocock/skills/tdd

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

io.github.affaan-m/ECC/hexagonal-architecture

Design, implement, and refactor Ports & Adapters systems with clear domain boundaries, dependency inversion, and testable use-case orchestration across TypeScript, Java, Kotlin, and Go services. Use when introducing or refactoring toward Ports and Adapters, or when domain logic has become entangled with I/O.

io.github.PostHog/posthog/working-with-skills

Best practices for agents managing PostHog skills via the MCP `skill-*` tools — how to discover, read, create, update, and refactor skills efficiently, especially large skills with many bundled files. Use whenever you are about to call any `skill-*` tool, asked to author or edit a shared skill, or troubleshoot why a skill write was rejected. Pairs with `skills-store` (which covers the raw tool surface) by adding the decision-tree, efficiency, and pitfall guidance.

io.github.novuhq/novu/nv-park-and-review

Commit local changes as a baseline, hop into a lightweight review worktree, run a thermo-nuclear code quality review scoped to ONLY that commit, commit the resulting refactor as a separate follow-up commit, then land it back and tear the worktree down. Use when the user asks to review their local/uncommitted changes for AI slop and redundant code, or invokes nv-park-and-review.

io.github.novuhq/novu/nv-endpoint-routed-tool-provider

Build or refactor a Tool-channel provider (PagerDuty, Opsgenie, future incident/alerting tools) to be endpoint-routed: per-subscriber secrets encrypted on the channel endpoint resource, a stateless provider that resolves routing from channelData at send time, SKIPPED steps when no endpoint exists, and the full API/worker/dashboard/docs/playground surface. Starts with a mandatory provider-docs discovery gate. Use when refactoring Opsgenie to the PagerDuty model, adding a new tool provider, or touching pagerduty_service channel endpoints.

io.github.Shubhamsaboo/awesome-llm-apps/commit-archaeologist

Reconstructs why code exists from local git history, including the introducing commit, later changes, current authors, repeated companion files, and likely intent. Use when the user asks "why does this code exist", "who wrote this function and why", or to "explain the history of this function" before a rewrite, refactor, or risky edit. Runs entirely locally.

io.github.ruvnet/ruflo/swarm-init

Initialize a multi-agent swarm with anti-drift configuration. Use when starting a complex multi-file task that needs 3+ coordinated agents (feature implementation, refactor across modules, security audit). Skip for single-file edits or quick questions.

io.github.handsontable/handsontable/code-graph

Query the pre-built code-review-graph knowledge graph (Tree-sitter, whole monorepo) instead of walking call chains with Grep+Read — 2-6x cheaper, and it catches dynamic dispatch that grep misses. Use for ANY task that spans multiple files, even when the user never mentions a graph or asks for it - fixing or tracing a bug ("fix this bug", "why does X happen", "trace this"), exploring unfamiliar code ("how does X work", "who calls X", "what imports Y", "where is X used or handled"), planning or doing a refactor ("rename X", "is it safe to change or remove X", "what would break", "blast radius", "find dead code"), or reviewing changes ("review this PR", "review this branch or diff"). If you are about to Grep for a symbol to find its callers, callees, or importers, stop and use this skill instead.

io.github.DietrichGebert/ponytail/ponytail

Lazy senior dev mode for any coding task (write, refactor, fix, review): YAGNI, stdlib first, no unrequested abstractions. Not for non-coding requests.

io.github.compozy/compozy/writing-skills

Author, refactor, and debug agent skills. Use when creating a new skill from scratch, pruning or restructuring a bloated SKILL.md, tightening a skill description's triggers, or diagnosing bundled references the agent ignores. Don't use for agent instruction files like CLAUDE.md or AGENTS.md (use agent-md-refactor), general documentation, or READMEs.

io.github.sickn33/antigravity-awesome-skills/code-showcase-testing-patterns

Jest testing patterns, factory functions, mocking strategies, and TDD workflow. Use when writing unit tests, creating test factories, or following TDD red-green-refactor cycle.

io.github.leookun/cursor-byok/cursor-client-e2e-debugging

Use when debugging Cursor client agent/local-mode/tool/backend-store/provider-replay failures in this repo, especially after the state/context history-store refactor, when triaging installed app bundles read-only, correlating installed-client behavior with repo code, mapping a user-provided id to conversation/request/model-call evidence, replaying provider requests from debug logs, or locating the current client/backend/protocol/log files quickly.

io.github.kortix-ai/suna/testing

The mandatory test-with-every-change discipline for this monorepo. Load WHENEVER you write, change, refactor, or remove ANY code under apps/** or packages/** — a function, class, route, component, hook, schema, migration, config, or bug fix — and whenever you touch anything under tests/, add coverage, run a suite, set up CI, or are asked why a gate failed. Defines which test type each change needs (unit/integration/contract/api/e2e/a11y/visual/perf/security), the exact commands and conventions (co-located bun:test, factories, determinism, no comments), and the CI gates that enforce it. Enforces THE RULE: every possible change ships with tests in the same change.

io.github.affaan-m/ECC/click-path-audit

Trace every user-facing button/touchpoint through its full state change sequence to find bugs where functions individually work but cancel each other out, produce wrong final state, or leave the UI in an inconsistent state. Use when: systematic debugging found no bugs but users report broken buttons, or after any major refactor touching shared state stores.