skills-repo-maintenance
Add or update skills in a skills repository for Codex and/or Claude Code. Use when creating new skills, packaging .skill files for Codex, or converting a skill into a Claude Code plugin (marketplace.json + plugin.json).
What this skill does
# Skills Repo Maintenance
## Overview
Maintain a skills repository and keep Codex and Claude Code artifacts in sync.
## Workflow
### 0) Defaults to apply
- Target runtime: **Codex + Claude Code** (both).
- Package output: **must be specified by the user every time** (no default).
### 1) Identify the repo root
- Use the current repo (git root) as the base.
- Example: `git rev-parse --show-toplevel`
### 2) Decide the target runtime(s)
- Default is **both**. If the user explicitly asks for only one runtime, confirm before skipping the other.
- **Codex**: add a skill folder with `SKILL.md` at repo root.
- **Claude Code**: add a plugin folder with `.claude-plugin/plugin.json` and update `.claude-plugin/marketplace.json`.
- For both, do both and package `.skill` files for Codex distribution.
### 3) Create or update the skill content
- Skill folder must contain `SKILL.md` with YAML frontmatter (`name`, `description`).
- Use lowercase + hyphens for skill names.
- Put extra materials under `references/`, `scripts/`, `assets/` as needed.
### 4) Claude Code plugin requirements (if applicable)
- Plugin lives at repo root (e.g. `drawio/`, `gh-fix-ci/`, `cli-design/`).
- Add `.claude-plugin/plugin.json` inside the plugin folder.
- Add an entry to `<repo-root>/.claude-plugin/marketplace.json`:
- `name`, `source`, `description`, `version`, `category`, `keywords`
- If the plugin contains multiple skills, place them under
`<plugin>/skills/<skill-name>/SKILL.md`.
### 5) Codex packaging (if applicable)
- Package to the **user-specified output directory** using the skill packager.
- On Windows, set UTF-8 to avoid decode errors.
```powershell
$env:PYTHONUTF8=1
$codexHome = $env:CODEX_HOME
if (-not $codexHome) { $codexHome = "$env:USERPROFILE\.codex" }
$outDir = "<output-dir>"
python "$codexHome\skills\.system\skill-creator\scripts\package_skill.py" `
"<repo-root>\\<skill-folder>" `
$outDir
```
```bash
export PYTHONUTF8=1
codex_home="${CODEX_HOME:-$HOME/.codex}"
out_dir="<output-dir>"
python "$codex_home/skills/.system/skill-creator/scripts/package_skill.py" \
"<repo-root>/<skill-folder>" \
"$out_dir"
```
Repeat for each Codex-supported skill.
### 6) Update documentation
- `README.md`
- Add to **Available Plugins** and **Usage (Claude Code)** when pluginized.
- Add to **Available Codex skills** and **Usage (Codex)** when packaged.
### 7) Commit + push
- Ensure `codex-skills/dist/*.skill` are tracked for Codex delivery.
- Push changes and open PR if required by your workflow.
## Notes
- Codex reads skills from `.codex/skills` folders; `.skill` is a packaged zip for distribution.
- Claude Code requires the plugin entry in `.claude-plugin/marketplace.json`.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.