Skill Claude CodeCodex
../../../dotclaudefolder/skills/okforge-maintain/SKILL.md.
919 tagged documentation, measured the same way as everything else here.
Browse within: claude-code-plugin 194business-processes 126skill-library 126skills-as-code 126architecture 53knowledge-management 53agent-sdk 52markdown 52documentation-as-code 47documentation-generator 45adr 42ai-skill 41builderstudio 40skill-catalog 40
Skill Claude CodeCodex
../../../dotclaudefolder/skills/okforge-maintain/SKILL.md.
marceloeatworld/mdbook-ai-skill
Skill Claude CodeCodex
This skill should be used when the user asks about "mdBook", "mdbook", "book.toml", "SUMMARY.md", "mdbook build", "mdbook serve", "mdbook init", "mdbook watch", "mdbook test", "mdbook clean", "mdBook configuration", "mdBook preprocessor", "mdBook renderer", "mdBook backend", "mdBook theme", "mdBook syntax…
compilet-dev/agent-skill-uselink
Skill Claude CodeCodex
Scan a codebase and generate a new-developer onboarding guide as HTML, then publish to uselink. Use when the user wants to create a getting-started guide, onboard a new team member, or share 'how to work in this repo' docs.
Skill Claude CodeCodex
Answers questions across the configured sources. References load on demand from references/. Use when working in any of this contextualizer's source domains.
Skill Claude CodeCodex
Use when working with MQL4, MQL5, MetaTrader 4/5, Expert Advisors (EAs), custom indicators, or scripts. Covers OrderSend, iMACD, iRSI, CopyBuffer, trade operations, indicator buffers, and MQL4-to-MQL5 migration. Triggers on any .mq4/.mq5/.mqh file or MetaEditor compilation.
Skill Claude CodeCodex
Use when driving a running Unreal Engine 5.8.0 editor over the official UE MCP server — to pick the correct toolset and tool for an editor-automation task (spawn/edit actors, Blueprints, materials, Niagara, animation/Sequencer, meshes, GAS, UMG, StateTree, data tables, run automation tests, inspect Slate, etc.).…
Skill Claude CodeCodex
Check whether a project's documentation still matches its code, and report stale or wrong claims with suggested fixes. Use this after editing, renaming, moving, or deleting source files, CLI flags, environment variables, or functions, to catch docs you may have just made inaccurate; when the user asks whether the…
Skill Claude CodeCodex
Autonomous documentation research using docsearch CLI - inspired by karpathy/autoresearch.
Skill Claude CodeCodex
Maintain long-running, cross-session goals for an agent (Copilot CLI, Claude Code, Codex, etc.) using a declarative goals.md file. Use when the user wants the agent to remember objectives across sessions, when they say "let's set a goal", "remember to keep working on X", "what are we working on?", "resume the goal"…
Skill Claude CodeCodex
Create, standardize, or audit a Howells project. Covers repo shape, tooling, package boundaries, UI, data, AI, agent workflow, deployment, and launch checks.
Skill Claude CodeCodex
Complete skill compression documentation — all options, modes, and calibration details (2,500 tokens).
Skill Claude CodeCodex
Drop into any repo and generate a structured architecture overview. Maps the codebase, identifies entry points, frameworks, and dependencies — then produces a "start here" guide for new contributors.
Skill Claude CodeCodex
This skill should be used when the task involves designing, building, and managing enterprise reporting and analytics -- from KPI selection through dashboard layout, scheduled distribution, and data security.
luqiang-code/claude-code-skills
Skill Claude CodeCodex
Review database migrations for safety: locking, rollback, data loss, and performance risks. Triggers on "review migration", "check migration", "migration safety".
hawkongz/github-format-standards
Skill Claude CodeCodex
Use when the user wants to share a project to GitHub. Runs a full pipeline: root audit, file naming and structure, document fixes (headings, code-block language tags, table alignment, explicit command interpreters), generate missing files (LICENSE, .gitignore, CONTRIBUTING.md, Issue/PR templates), README rewrite…
Skill Claude CodeCodex
Choose the correct Knights Radiant order for the task before starting execution.
Skill Claude CodeCodex
Use after implementation changes to update OKF from git diff or changed files. Extract durable behavior, architecture, domain, data, and playbook changes into relevant OKF documents and log entries. Do not use for temporary task notes or changes with no durable project knowledge impact.
pueraeternis/agentic-project-template
Skill Claude CodeCodex
This skill transforms an approved project architecture into concrete engineering decisions.
Hhh2178/project-harness-governance
Skill Claude CodeCodex
Use when starting or restructuring a medium/large software project that needs durable agent rules, documentation architecture, harness verification, visual standards, component registries, project overview files, logs, plans, indexes, and ongoing governance boundaries.
Skill Claude CodeCodex
Use when installing, running, and troubleshooting DocShark as an MCP server, including client setup for STDIO mode and endpoint checks for HTTP mode.
Skill Claude CodeCodex
Use when creating or improving a README for any project — open source libraries, CLI tools, GUI applications, APIs, or internal tools. Triggers on: writing README, improve README, project documentation, onboarding docs.
cjcsecurity/readme-demo-recorder
Skill Claude CodeCodex
Record a polished, scripted-flow browser demo of an HTML page (or URL) for a README hero. Drives Playwright with a fake cursor + click pulse, then encodes WebM → MP4 + GIF tuned for GitHub asset rendering. Use when the user asks to "record a demo", "make a README gif", "capture a screencast of an HTML app", or ships a…
dltkddns833/ko-official-doc-style
Skill Claude CodeCodex
A Korean-language writing and review guide for formal documents such as contracts, agreements, official letters, and reports.
Skill Claude CodeCodex
Documentation architecture discipline for AI agents. Use when creating, updating, auditing, or organizing software project documentation so docs stay clear, non-duplicated, source-of-truth driven, and token-efficient.
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: