code agent skills

65 tagged code agent, measured the same way as everything else here.

Browse within: desktop 23manus 23Evaluation 17cli-agent 17harness 17tmux 17rust 6

recover-context

01

pchalasani/claude-code-tools

Skill Claude CodeCodex

Extract full context of the last task from the most recent parent session shown in the session lineage. Strategically uses sub-agents to avoid bloating your own context.

2.0k 2d ago A 36 tokens original MIT

dynamic-workflow

02

pchalasani/claude-code-tools

Skill Claude CodeCodex

Create, review, run, inspect, pause, resume, and cancel durable JavaScript workflows that coordinate multiple headless Codex agents. Use for dynamic fan-out and fan-in, per-item analysis, multi-stage agent pipelines, loops or branches driven by worker results, long background runs, and ports of Claude Code dynamic…

2.0k 2d ago A 86 tokens original MIT

remove-ai-patterns

03

pchalasani/claude-code-tools

Skill Claude CodeCodex

Remove AI-writing patterns ("AI-isms") from text using the avoid-ai-writing catalog (conorbronsdon/avoid-ai-writing). Use ONLY when the user explicitly asks to remove AI patterns / AI-isms, "make this sound less like AI", "de-AI this text", or invokes remove-ai-patterns by name. Supports detect-only audit…

2.0k 2d ago A 132 tokens original MIT

hatch-pet

04

hAcKlyc/MyAgents

Skill Claude CodeCodex

Create, repair, validate, visually QA, and package MyAgents/Codex-compatible animated pets and pet spritesheets from character art, generated images, company or prospect brand cues, or visual references. Use when a user wants a lightweight-worker desktop pet workflow, a non-pixel custom pet style, a prospect or…

861 yesterday A 120 tokens AGPL-3.0

hAcKlyc/MyAgents

Skill Claude CodeCodex

A skill for managing persistent agent tasks, including work scheduled for later, repeated checks, and actions triggered when conditions are met.

861 yesterday A 112 tokens AGPL-3.0

skill-creator

06

hAcKlyc/MyAgents

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.

861 yesterday A 63 tokens AGPL-3.0

code-review

07

StepfenShawn/kota

Skill Claude CodeCodex

Code review and quality analysis.

100 4mo ago A 8 tokens original MIT

example

08

StepfenShawn/kota

Skill Claude CodeCodex

Example skill showing the complete SKILL.md format with all features.

100 4mo ago A 14 tokens original MIT

rust-expert

09

StepfenShawn/kota

Skill Claude CodeCodex

Expert Rust programming assistant focused on idiomatic code, safety, and performance.

100 4mo ago A 18 tokens original MIT

claudebox

13

psyb0t/docker-claudebox

Skill Claude CodeCodex

Claude Code running on the network inside a Docker container (aicodebox-based), managed via the claudebox wrapper/CLI. Exposes seven ways to drive it — interactive shell (claudebox), one-shot exec (claudebox "prompt"), an HTTP REST API (/run, async run-id polling, /files CRUD), an OpenAI-compatible…

19 18d ago B 235 tokens WTFPL

AgentPrecept

14

rg8diaoa/AgentPrecept

Skill Claude CodeCodex

A project workflow for coordinating several coding agents on the same software project. It uses shared project structure, decisions, handoffs, checklists, and memory so agents can continue each other's work.

9 2mo ago A 0 tokens original MIT