codex-cli skills

4,268 tagged codex-cli, measured the same way as everything else here.

Browse within: gemini-cli 180codex-skills 171codex-plugin 147ai-coding 143codex-skill 127agentic-workflow 119ai-assistant 107agentic-coding 104context-engineering 95openai 93claude-plugin 74agents-md 67codex-external 60codexcli 60

handoffkit-scaffold

193

dyngai/handoffkit

Skill Claude CodeCodex

Built by DynG AI for PlatformPilot.ai-style Go agent runtimes. Use when the user wants to scaffold HandoffKit runtime primitives into a Go project: channel-backed mailboxes, select, router, broker, join/quorum barriers, trace, budget, corpus/compactor, supervisor/nursery, dead letters, and sketch interfaces. Trigger…

not rated 29 2mo ago C 108 tokens original MIT

handoffkit

194

dyngai/handoffkit

Skill Claude CodeCodex

Built by DynG AI for PlatformPilot.ai-style multi-agent systems. Use when designing or reasoning about message-passing agent coordination in ANY language: actor-style mailboxes, select, point-to-point routing, pub/sub, fan-in joins/quorums, ownership handoff, budgets, dead letters, and traces. Trigger words include…

not rated 29 2mo ago A 114 tokens original MIT

madrobotnet/hermes-codex-imagegen-skill

Skill Claude CodeCodex

Use a separate Codex CLI instance logged in via ChatGPT / OpenAI Codex OAuth to generate an image with Codex's built-in imagegen skill, then verify the saved PNG from /.codex/generatedimages.

not rated 28 4mo ago A 56 tokens original MIT

do-it-context

196

tdwhere123/do-it

Skill Claude CodeCodex

Part of do-it

Use when repo terms or invariants are drifting, or when user/docs/code naming disagrees and a canonical glossary is needed — .do-it/CONTEXT.md is the downstream source of truth for names, relationships, and facts.

not rated 27 22d ago A 51 tokens original MIT

do-it-handbook

197

tdwhere123/do-it

Skill Claude CodeCodex

Part of do-it

Use when a project needs a lean .do-it/handbook/ for stable project truth plus .do-it/worklog/ for daily or goal notes.

not rated 27 22d ago A 38 tokens original MIT

do-it-review

198

tdwhere123/do-it

Skill Claude CodeCodex

Part of do-it

Use when a diff needs PR-style review, or findings need atomic repair and same-scope re-review — Standards axis and Spec axis, kept separate.

not rated 27 22d ago A 34 tokens original MIT

boss-advanced

199

sehoon787/my-codex

Skill Claude CodeCodex

Advanced Boss orchestration patterns — Agent Teams leadership, 6-section delegation template, Skill vs Agent conflict resolution, Guardian pattern, and AI-slop detection.

not rated 25 5d ago A 35 tokens original MIT

boss-briefing

200

sehoon787/my-codex

Skill Claude CodeCodex

Vault health check — workflow pattern analysis, profile sync, session gap recovery, persona rule proposals.

not rated 25 5d ago A 23 tokens original MIT

gstack-sprint

201

sehoon787/my-codex

Skill Claude CodeCodex

3-Phase Sprint workflow — design → execute → review with user interaction at decision points.

not rated 25 5d ago A 22 tokens original MIT

agents

205

itsmostafa/llm-engineering-skills

Skill Claude CodeCodex

Patterns and architectures for building AI agents and workflows with LLMs. Use when designing systems that involve tool use, multi-step reasoning, autonomous decision-making, or orchestration of LLM-driven tasks.

not rated 23 4mo ago A 42 tokens original MIT

context-engineering

206

itsmostafa/llm-engineering-skills

Skill Claude CodeCodex

Strategies for managing LLM context windows effectively in AI agents. Use when building agents that handle long conversations, multi-step tasks, tool orchestration, or need to maintain coherence across extended interactions.

not rated 23 4mo ago A 42 tokens original MIT

lora

207

itsmostafa/llm-engineering-skills

Skill Claude CodeCodex

Parameter-efficient fine-tuning with Low-Rank Adaptation (LoRA). Use when fine-tuning large language models with limited GPU memory, creating task-specific adapters, or when you need to train multiple specialized models from a single base.

not rated 23 4mo ago A 50 tokens original MIT

sonol-agent-runtime

208

volition79/sonol-multi-agent

Skill Claude CodeCodex

Sonol runtime helper skill for sub-agents participating in Sonol multi-agent orchestration. Use when a sub-agent must report progress, artifacts, completion, or session status into the shared dashboard and SQLite-backed run history.

not rated 23 4mo ago A 49 tokens

sonol-multi-agent

209

volition79/sonol-multi-agent

Skill Claude CodeCodex

Sonol multi-agent orchestration skill. Use when a user wants one request decomposed into single-agent or multi-agent execution, with local-AI creative draft generation, hosted normalization/binding, adapter-backed sub-agent controls, runtime reporting, dashboard monitoring, plan/run persistence, and final result…

not rated 23 4mo ago A 65 tokens

ck-expand-folder

210

Fredrik-C/ContextKing

Skill Claude CodeCodex

List files in a folder with their signatures, filtered by an optional regex pattern. Use this in fallback folder-scoped exploration after ck find-files.

not rated 22 10d ago A 33 tokens

ck-find-files

211

Fredrik-C/ContextKing

Skill Claude CodeCodex

Source discovery over path, file, type, and member names. Use this as the default first step before signatures or method extraction.

not rated 22 10d ago A 30 tokens

ck-learn

212

Fredrik-C/ContextKing

Skill Claude CodeCodex

Record a new knowledge snippet — domain rules, architectural decisions, gotchas, or cross-module relationships discovered during a session.

not rated 22 10d ago A 28 tokens

ivfarias/ceo

Skill Claude CodeCodex

Use when starting work on any project (technical or non-technical) to understand structure, standards, and best practices before making changes.

not rated 22 5mo ago A 31 tokens

speckit

214

ivfarias/ceo

Skill Claude CodeCodex

Use when user wants to work with specifications or create feature requirements following the spec-driven development workflow.

not rated 22 5mo ago A 22 tokens

writing-skills

215

ivfarias/ceo

Skill Claude CodeCodex

Use when creating new skills, editing existing skills, or verifying skills work before deployment.

not rated 22 5mo ago A 20 tokens

component-builder

216

madebypan/FigCC

Skill Claude CodeCodex

Build reusable Figma components and variants with consistent auto layout and properties.

not rated 22 28d ago A 17 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: