Repository-first deterministic migration and atomic Skill source for Claude Code and Codex.
This repository also configures its own agents. See what harness-hub tells them →
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
Load when a task needs to implement or continue an existing OpenSpec change; use the repository's normal development contract for non-OpenSpec implementation.
Skill Claude CodeCodex
Load when a task needs to archive a completed OpenSpec change after implementation and spec sync decisions are resolved.
Skill Claude CodeCodex
Load when a task needs explicit OpenSpec exploration, discovery, or requirement clarification; use the repository's normal development contract for default change alignment.
Skill Claude CodeCodex
Load when a task needs an explicit OpenSpec proposal with design, spec deltas, and tasks; use product-capability for ordinary implementation contracts.
Skill Claude CodeCodex
Load when tracking newly published package or model-package releases across package registries and release feeds for AI/developer-tool monitoring; do not load for ordinary docs lookup, broad GitHub trend scanning, or implementing package clients.
Skill Claude Code
Load when coding work should be deliberately minimal: YAGNI, reuse existing code, prefer stdlib/native/already-installed dependencies, shortest correct diff, no unrequested abstractions, or over-engineering review; do not load for non-coding concise reports, general summaries, or communication artifact density.
Skill Claude CodeCodex
Load when accepted product intent must become a concise, implementation-ready local capability specification with explicit constraints, non-goals, test seams, and unresolved decisions.
Skill Claude CodeCodex
Load when an existing Web product, especially a dashboard, dense-data view, or multi-step app, needs a deep evidence-backed experience review; report findings only, and use design-taste-frontend for marketing-page direction, code-review for source diffs, web-design-guidelines for checklist compliance, or…
Skill Claude CodeCodex
Load when a task needs a throwaway prototype, state-model sanity check, UI variant, image-assisted visual mockup, mock interaction, or playable design; do not use for production feature work.
Skill Claude CodeCodex
Load when a task needs an explicit source-backed learning project, study plan, syllabus, book/technical topic coaching, teach-back, quizzes, or staged review; do not load for routine implementation, one-off facts, or article writing.
Skill Claude CodeCodex
Load when existing animation or motion code, a motion diff, or a rendered interaction needs an evidence-backed craft review; report findings only and use code-review for general source review.
Skill Claude CodeCodex
Load when a task needs security-sensitive code, auth, user input, secrets, API endpoints, payments, injection risk, or unsafe IO reviewed; use code-review for broader review.
Skill Claude CodeCodex
Load when creating, updating, adapting, or evaluating a standard agent skill; do not load for ordinary documentation edits or one-off prompt advice.
Skill Claude CodeCodex
Load when a task needs to create, optimize, or validate an animated GIF for Slack emoji or messages; skip static images, video editing, and non-Slack animation.
Skill Claude CodeCodex
Load when turning an external article, blog, release note, interview, or report into a source-backed public post with Chinese fidelity, media references, an effective-interact summary layer, and project-iteration review; do not load for ordinary summaries, full copyrighted reposts, or production site design.
Skill Claude CodeCodex
Load when the user asks to draft, edit, or review English prose for AI-writing tells; do not load for code explanation, Chinese output, technical specs, or routine status reports.
Skill Claude CodeCodex
Load when implementing a confirmed behavior change through red-green-refactor; diagnose first when the root cause is unknown, and use prototype for throwaway exploration.
Skill Claude CodeCodex
Load when a task needs a coherent visual theme for slides, docs, reports, HTML artifacts, or landing pages; skip product UI implementation and accessibility review.
Skill Claude CodeCodex
Load when an accepted specification must be decomposed into dependency-aware, project-owned implementation slices without creating a new tracker or publishing remote issues by default.
Skill Claude CodeCodex
Load when claiming completion requires the repository's actual deterministic build, type, lint, test, diff, smoke, and artifact gates; use diagnose while a failure's root cause is unknown.
Skill Claude CodeCodex
Load when a task needs complex standalone React/Tailwind/shadcn browser artifacts with state, routing, or bundled components; use effective-interact for reports and frontend-design for production UI.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: