Skill Codex
A development workflow for building tasks and workflows with Agently, a framework for connecting language models to structured output, tools, and event streams.
not rated 50 5mo ago A 131 tokens
original MIT
ai-agent-prd
02Skill Claude CodeCodex needs its repo
Write comprehensive PRDs for AI Agent products—covering agent identity, capability architecture (skills, tools, memory, RAG, workflows), behavior specifications, safety guardrails, and evaluation frameworks. Use when: designing conversational agents, autonomous agents, copilots, multi-agent systems, or any LLM-powered…
not rated 50 5mo ago A 173 tokens
original MIT
bf-caprt-dev
03Skill Claude CodeCodex
A guide for delivering skills, agents, and workflows through capability-runtime, the runtime layer that executes these capabilities and reports their results.
not rated 50 5mo ago A 258 tokens
original MIT
Skill Claude CodeCodex needs its repo
A guide for developing business agents, skills, and workflows with the Skills Runtime SDK for Python, a software toolkit for running these components.
not rated 50 5mo ago A 132 tokens
original MIT
Skill Claude CodeCodex
Turn vague ideas into a validated design/spec through structured brainstorming. Use before any creative work - new features, UI/components, behavior changes, refactors, architecture decisions. Trigger whenever a user asks to brainstorm, define requirements, propose approaches, write a design doc, or says something…
not rated 50 5mo ago A 86 tokens
original MIT
Skill Claude CodeCodex
Extract complete, replicable engineering specifications from existing codebases. Produces documentation detailed enough to fully replicate a project without seeing the original source code—even using a different tech stack. Use when: analyzing existing projects, documenting legacy systems, creating technical specs…
not rated 50 5mo ago A 95 tokens
original MIT
Skill Claude CodeCodex
Trace and document the complete call chain / data flow of any feature or process in a codebase. Use this skill whenever the user asks to understand how a feature works end-to-end, trace a call chain, analyze code flow, map data flow across layers, reverse-engineer a process, or asks questions like "how does X call Y"…
not rated 50 5mo ago A 109 tokens
original MIT
Skill Claude CodeCodex
A toolkit for safely controlling interactive command-line programs inside tmux, a terminal tool that keeps programs running in separate panes.
not rated 50 5mo ago C 45 tokens
original MIT
Skill Claude CodeCodex
Send a critical mobile push through Day.app (Bark) with one GET request. Use when a task finishes, fails, is blocked, or needs immediate alerting, and you should summarize task name and summary from current task context before sending.
not rated 50 5mo ago A 55 tokens
original MIT
docx-offline
10Skill Claude CodeCodex
Tools and instructions for reading and editing Microsoft Word DOCX files while preserving document structure. DOCX is the standard file format used by modern Microsoft Word documents.
not rated 50 5mo ago B 67 tokens
copy · 94% MIT
Skill Claude CodeCodex
A tool for opening webpages in a browser that runs without a visible window and reading the page after its scripts have loaded.
not rated 50 5mo ago A 71 tokens
original MIT
loopback
12Skill Claude CodeCodex
An iterative coding workflow that repeatedly sends the same task to Codex, while preserving progress in files and Git history. It stops when a stated completion signal, iteration limit, or cancellation condition is reached.
not rated 50 5mo ago A 107 tokens
original MIT
cancel-loop
13Command Claude Code
Cancel active Loopback loop.
not rated 50 5mo ago A 5 tokens
original MIT
pdf-offline
14Skill Claude CodeCodex
Tools and instructions for working with PDF files without relying on an online document service. A PDF is a fixed-layout document commonly used for sharing, printing, and official forms.
not rated 50 5mo ago A 55 tokens
copy · 77% MIT
pptx-offline
15Skill Claude CodeCodex
A set of instructions for reading, editing, rearranging, unpacking, and creating PowerPoint presentation files without relying on an online service.
not rated 50 5mo ago B 65 tokens
copy · 91% MIT
Skill Claude CodeCodex
Transform PRD (Product Requirements Document) into actionable engineering specifications. Creates detailed technical specs that developers can implement step-by-step without ambiguity. Covers data modeling, API design, business logic, security architecture, deployment, and agent system design. Use when: converting…
not rated 50 5mo ago A 113 tokens
original MIT
Skill Claude CodeCodex
A documentation workflow that turns a product requirements document (PRD) into detailed UI and UX specifications for frontend implementation. It defines shared foundations, reusable components, page behavior, data and event rules, accessibility, and acceptance checks.
not rated 50 5mo ago A 118 tokens
original MIT
Skill Claude CodeCodex
Write complete, unambiguous PRDs that development teams can implement without guesswork. Includes requirement discovery framework, structured documentation methodology, completeness checklists, and common pitfall avoidance. Use when: writing new PRDs, reviewing PRD drafts, validating requirement completeness…
not rated 50 5mo ago A 155 tokens
original MIT
Skill Claude CodeCodex
A code-repository compliance audit that checks project rules, documentation, testing evidence, reproducibility, secrets, and repository cleanliness, then produces Markdown and JSON reports.
not rated 50 5mo ago A 160 tokens
original MIT
Skill Claude CodeCodex
End-to-end source code repository deep dive and review. Use when you need to understand a repo’s architecture, core abstractions, entrypoints and execution flow, extension points, and operational/developer setup; and when you must deliver a structured report (Markdown + standalone HTML) with diagrams (Mermaid)…
not rated 50 5mo ago A 76 tokens
original MIT
Skill Claude CodeCodex
Create new high-quality agent skills with a standalone, repeatable workflow (no dependency on other skills). Use when you want to go from a vague skill idea → narrow scope → extract expert frameworks → write SKILL.md + examples/evals/index/changelog artifacts → self-validate with test prompts.
not rated 50 5mo ago A 63 tokens
original MIT
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
not rated 50 5mo ago A 65 tokens
copy · 88% MIT
Skill Claude CodeCodex
Use when a user asks to review, interpret, or audit an AI agent skill (SKILL.md plus bundled scripts/references/assets) for capabilities, triggering behavior, tool/command usage, safety & privacy risk, supply-chain provenance, quality gaps, and improvement recommendations; also use when validating a skill before…
not rated 50 5mo ago B 71 tokens
original MIT
Skill Claude CodeCodex
A portable, reproducible UI/UX spec standard: scan a frontend repo for UI sources and scaffold a ui-ux-spec documentation bundle (tokens, global styles, components, patterns, pages, a11y). Also supports plan-driven UI-only refactors based on an existing ui-ux-spec. Excludes business logic and domain workflows.
not rated 50 5mo ago A 75 tokens
original MIT
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: