Charles Agent Skills — Development skill for Claude Code
Production-quality agent skills for Claude Code and OpenAI Codex: session handoff (putdown/pickup), knowledge harvesting (takenotes), project bootstrap, skill catalog, and plan interrogation.
How to install Charles Agent Skills
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open cabaynes/charles-agent-skills and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Charles Agent Skills does
Production-quality agent skills for Claude Code and OpenAI Codex: session handoff (putdown/pickup), knowledge harvesting (takenotes), project bootstrap, skill catalog, and plan interrogation. One source, two tested versions.
Alternatives in Development
- Implementation Plan — You are tasked with creating detailed implementation plans through an interactive, iterative process 10k ★
- n8n Validation Expert — Fix n8n validation errors with error catalog 3.6k ★
- Contributing To Claude Code Skills Marketplace — Thank you for your interest in contributing 653 ★
README
charles-agent-skills
Production-quality agent skills for **[Claude Code](https://claude.com/claude-code)** and **[OpenAI Codex](https://developers.openai.com/codex)**. Both tools use the same open [Agent Skills](https://agentskills.io/specification) format, so every skill here ships in two versions: one per tool, built from a single source so they never drift apart.
- Claude Code: evaluated against Anthropic's
writing-skills+skill-creatorrubric, with 100% trigger accuracy on a 20-query precision/recall benchmark per skill. - Codex: every skill tested end to end through the real Codex CLI (30/30 checks), plus a spec check and a behavior rubric.
   
Renamed from `charles-claude-skills` on 2026-09-29, when the Codex versions shipped. Old links redirect here. The Claude skills moved from `skills/` to `claude/`.
Pick your tool
| You use… | Install from | Run a skill with | Project instructions file |
|---|---|---|---|
| Claude Code | `claude/` → ~/.claude/skills/ |
/putdown |
CLAUDE.md |
| OpenAI Codex | `codex/` → ~/.agents/skills/ |
$putdown |
AGENTS.md |
| Both | Install each folder into its own tool | either | Handoffs in a repo's .putdowns/ work across both tools |
**How the repo is laid out:**
claude/ Claude Code versions — also the single source for everything
codex/ Codex versions — GENERATED from claude/, never edited by hand
codex-overlays/ only what differs for Codex, one file per skill
scripts/ snapshot.sh (refresh claude/), build-codex.py (build codex/)
tests/codex/ end-to-end Codex tests, spec check, results
workspace/ the multi
Related Skills
Pickup
Resumes work from a previous handoff session which are stored in .claude/handoffs.
Mine End Of Day
Capture session state as a handoff file for morning pickup.
CC Codex Gemini Companion Starter
Single-repository bootstrap framework for Claude Code, Codex, and Gemini with memory, IM bridge, and catalog-g
Commerce Agents Checkout
Python adapter that plugs Mercado Pago Checkout Pro into the StorefrontBackend handoff from anthropics/commerc
Claude Code Chive System
A battle-tested architectural governance and resilient self-healing skill system for Claude Code. Synthesizes
Claude Code Chive System Strict Remediation.
A battle-tested architectural governance and resilient self-healing skill system for Claude Code. Synthesizes
Related Agents
Session Orchestrator
Orchestrates LibreSessionFlow Grok skills for continuity — handoff, digest, absorb, pickup, resume. Use when e
Session Error Analyzer
Analyzes specific AI IDE sessions (Claude Code, OpenAI Codex, OpenCode) for LLM behavior errors and returns a
Kg Engineer
Senior Python Engineer for Knowledge Graph integration with CognivAgent. Specializes in Claude Agent SDK MCP t