harness-hub

In the author's own words, from each skill's SKILL.md — showing the first 30 of 51 files.

• agent-interaction-audit

  Load when the user asks for private agent interaction audits from local Codex/Claude Code traces, task profiles, tool-call decisions, collaboration bottlenecks, prompt/rule or automation-log audits, closeout retrospectives, or evidence-backed Skill/project-rule/Eval/SOP/OKF improvements.

  skills/agent-interaction-audit/SKILL.md on GitHub (opens in a new tab)

• agent-introspection-debugging

  Load when a task needs agent run, tool loop, context drift, or recoverable harness/tool failure debugging; use diagnose for product/runtime bugs.

  skills/agent-introspection-debugging/SKILL.md on GitHub (opens in a new tab)

• agent-reach

  Load when a task needs read-only internet research or content retrieval through an already installed Agent Reach CLI; diagnose available backends first, never install, upgrade, authenticate, configure, or copy credentials on the user's behalf.

  skills/agent-reach/SKILL.md on GitHub (opens in a new tab)

• animation-vocabulary

  Load when a user describes a Web animation or motion effect without knowing its name and needs the precise term or close alternatives; use only for naming, not design, implementation, or review.

  skills/animation-vocabulary/SKILL.md on GitHub (opens in a new tab)

• apple-design

  Load when a frontend task needs Apple-platform design guidance or physical, gesture-driven, velocity-aware, interruptible interaction; skip generic visual styling and use review-animations for report-only motion review.

  skills/apple-design/SKILL.md on GitHub (opens in a new tab)

• beautiful-feishu-whiteboard

  Load when creating or restyling a polished editable Feishu or Lark whiteboard, infographic, diagram, poster, or visual explainer; do not load for generic SVGs, static images, or other whiteboard platforms.

  skills/beautiful-feishu-whiteboard/SKILL.md on GitHub (opens in a new tab)

• claude-api

  Load when a task needs Claude API or Anthropic SDK build, debug, migration, or tuning work; skip provider-neutral, OpenAI, or non-Anthropic model work.

  skills/claude-api/SKILL.md on GitHub (opens in a new tab)

• clone-website

  Load when the user explicitly asks to clone, reverse-engineer, or rebuild a website they own or are authorized to reproduce; do not load for generic redesign, inspiration, scraping, phishing, impersonation, or copying third-party brands.

  skills/clone-website/SKILL.md on GitHub (opens in a new tab)

• code-review

  Load when a task needs a deep, report-only review across independent Standards and Spec axes, using bounded read-only native Subagents when available and adding risk lenses only when the diff warrants them.

  skills/code-review/SKILL.md on GitHub (opens in a new tab)

• codebase-design

  Load when a change needs module-boundary, dependency-direction, interface-depth, or architecture simplification decisions; do not use for routine style or formatting rules.

  skills/codebase-design/SKILL.md on GitHub (opens in a new tab)

• codebase-to-course

  Load when a user wants a source-backed interactive HTML course that explains how a codebase works; do not load for chat tutoring, repository review, articles, slide decks, or general browser artifacts.

  skills/codebase-to-course/SKILL.md on GitHub (opens in a new tab)

• decision-ui

  Load when Codex 即将要求用户在 2-3 个互斥方案中做真实决定、准备询问阻塞性澄清问题或需要确认高影响取舍；将选择转换为宿主原生可点击 UI，并在工具不可用时诚实文本回退。不要用于低风险实现细节、只有一个合理答案的问题、普通信息采集或不需要用户决策的完成汇报。

  skills/decision-ui/SKILL.md on GitHub (opens in a new tab)

• design-taste-frontend

  Load when a task needs anti-template frontend visual direction, design-read calibration, or pre-flight critique for landing pages, portfolios, marketing pages, or redesigns; do not load for dashboards, data tables, multi-step product UI, routine frontend logic, HTML reports, slide decks, or generic code explanation.

  skills/design-taste-frontend/SKILL.md on GitHub (opens in a new tab)

• diagnose

  Load when a task needs hard bugs and performance regressions, failing commands, hard-to-reproduce behavior, or unknown root causes diagnosed; use agent-introspection-debugging instead for agent/tool harness failures.

  skills/diagnose/SKILL.md on GitHub (opens in a new tab)

• doc-coauthoring

  Load when a task needs to collaboratively draft, restructure, or reader-test docs, PRDs, RFCs, proposals, specs, or decision records; skip implementation itself.

  skills/doc-coauthoring/SKILL.md on GitHub (opens in a new tab)

• documentation-lookup

  Load when a task needs current library, framework, SDK, API, CLI, or cloud-service documentation; fetch docs instead of relying on training data or ordinary repo evidence.

  skills/documentation-lookup/SKILL.md on GitHub (opens in a new tab)

• e2e-testing

  Load when a task needs durable Playwright E2E suites, Page Object Models, fixtures, CI browser tests, or flaky-test strategy; use webapp-testing for one-off local inspection.

  skills/e2e-testing/SKILL.md on GitHub (opens in a new tab)

• effective-interact

  Load when agent pauses to report relatively complex information needing Chinese-first clear complex communication, alignment, multi-option choice, status/incident, long-task fact ledgers, implementation plans, reviews, maps, explainers, evidence, risks, validation, handoff; choose plain text/Markdown/visual Markdown/HTML by decision cost; do not load merely because answer is long; skip trivial ch…

  skills/effective-interact/SKILL.md on GitHub (opens in a new tab)

• frontend-design

  Load when a task needs polished product UI, web pages, landing pages, dashboards, React components, HTML/CSS layouts, or styling; skip routine frontend logic and reports.

  skills/frontend-design/SKILL.md on GitHub (opens in a new tab)

• frontend-patterns

  Load when a task needs React or Next.js frontend logic, component patterns, state, forms, routing, accessibility, or responsive behavior; use frontend-design for visual direction.

  skills/frontend-patterns/SKILL.md on GitHub (opens in a new tab)

• frontend-slides

  Load when a task needs a browser-based HTML presentation, talk or pitch deck, existing-deck enhancement, or PPT/PPTX-to-web conversion; do not load for reports, product UI, or interactive courses.

  skills/frontend-slides/SKILL.md on GitHub (opens in a new tab)

• grill-me

  Load when beginning every repository mutation task to run one dependency-layered batch interview; a fully aligned task takes the zero-question path, while durable documentation work uses grill-with-docs to reuse the same decision graph.

  skills/grill-me/SKILL.md on GitHub (opens in a new tab)

• grill-with-docs

  Load when a repository mutation creates or materially changes durable project contracts, OKF knowledge, specs, ADRs, or architecture/API/design documents; run a source-backed alignment pass that reuses grill-me's dependency-frontier batch protocol.

  skills/grill-with-docs/SKILL.md on GitHub (opens in a new tab)

• handoff

  Load when a task needs to hand off current work, compact a conversation for another agent/session, or create restart notes; do not load for visual HTML repo reports.

  skills/handoff/SKILL.md on GitHub (opens in a new tab)

• internal-comms

  Load when a task needs internal communications such as status reports, leadership updates, 3P updates, newsletters, FAQs, incident reports, or project updates; skip public marketing copy.

  skills/internal-comms/SKILL.md on GitHub (opens in a new tab)

• karpathy-guidelines

  Load when a task needs a coding behavior baseline for writing, reviewing, or refactoring code: surface assumptions, avoid overcomplication, keep changes surgical, and define verifiable success criteria; do not use as the top-level owner or for trivial one-line edits.

  skills/karpathy-guidelines/SKILL.md on GitHub (opens in a new tab)

• mcp-builder

  Load when a task needs MCP server design, build, review, testing, tool schema, resource, or prompt work; skip ordinary REST clients and non-MCP integrations.

  skills/mcp-builder/SKILL.md on GitHub (opens in a new tab)

• openspec-apply-change

  Load when a task needs to implement or continue an existing OpenSpec change; use the repository's normal development contract for non-OpenSpec implementation.

  skills/openspec-apply-change/SKILL.md on GitHub (opens in a new tab)

• openspec-archive-change

  Load when a task needs to archive a completed OpenSpec change after implementation and spec sync decisions are resolved.

  skills/openspec-archive-change/SKILL.md on GitHub (opens in a new tab)

• openspec-explore

  Load when a task needs explicit OpenSpec exploration, discovery, or requirement clarification; use the repository's normal development contract for default change alignment.

  skills/openspec-explore/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 270k stars · 1 skill
• agent-skillsby addyosmani Production-grade engineering skills for AI coding agents. 107k stars · 25 skills
• taste-skillby Leonxlnx Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages 97.3k stars · 13 skills
• archifyby tt-a1i Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more. 84.1k stars · 2 skills
• diagram-designby cathrynlavery Editorial diagram design for Claude Code, Codex, GitHub Copilot, Cursor, Factory Droid, and Pi. 44 diagram types. Self-contained HTML + SVG… 55.9k stars · 1 skill
• cherry-studioby CherryHQ AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs 52.7k stars · 30 skills