skill-management
Creates, audits, and validates agent skills following the Agent Skills open standard. Covers YAML frontmatter, description writing, progressive disclosure, directory structure, 9-phase audits, severity classification, and manifest-implementation drift detection. Use when creating new skills, writing skill descriptions, auditing existing skills, detecting version drift, validating implementations match manifests, or debugging skill discovery issues.
What this skill does
# Skill Management ## Overview Guides creation, auditing, and validation of agent skills conforming to the Agent Skills open standard at <https://agentskills.io>. Covers the full lifecycle from scaffolding a new skill through production-quality review. **When to use:** Creating skills, improving descriptions for discoverability, restructuring skills for progressive disclosure, running quality audits, validating manifest-implementation alignment. **When NOT to use:** Writing application code, general markdown editing, project management unrelated to skill authoring. ## Quick Reference | Task | Approach | Key Points | | ------------------------- | -------------------------------------------- | ------------------------------------------------------------------------------ | | Skill directory | `skill-name/SKILL.md` + optional directories | Only `SKILL.md` is required; `scripts/`, `references/`, `assets/` are optional | | Frontmatter `name` | Lowercase, hyphens, 4-64 chars | Must match directory name, no leading/trailing `-`, no `--` | | Frontmatter `description` | 1-1024 chars with trigger phrases | Third-person voice, include "Use when" scenarios | | Progressive disclosure | Metadata -> SKILL.md -> references/scripts | Keep SKILL.md under 500 lines; move details to references | | Description structure | Para 1: what + features, Para 2: triggers | Active voice, name technologies, include error keywords | | Effective descriptions | 250-350 chars, specific, discoverable | "Build X" not "This skill helps you build X" | | Reference files | `references/topic.md` with frontmatter | Max 500 lines, self-contained, kebab-case filenames | | Quality audit | 9-phase systematic review | Standards, official docs, code accuracy, cross-file checks | | Severity levels | Critical / High / Medium / Low | Evidence-based classification with links | | Validation scoring | Average of accuracy, precondition, effect | Pass requires score >= 0.8 and zero high-severity issues | | Excluded files | `README.md`, `metadata.json`, `_*` files | Skills CLI strips these during installation | ## Common Mistakes | Mistake | Correct Pattern | | -------------------------------------------------------------- | ------------------------------------------------------------------------------- | | Including `README.md` in skill directory | Skills CLI excludes `README.md` during installation; use only `SKILL.md` | | Writing vague descriptions without discovery keywords | Include specific technologies, 3-5 "Use when" scenarios, and 2-3 error messages | | Duplicating knowledge the agent already has | Focus on edge cases, platform differences, and gotchas the agent gets wrong | | Putting all content in SKILL.md without progressive disclosure | Keep SKILL.md under 500 lines; move code examples to `references/` | | Listing bundled files that do not exist on disk | Verify all cross-file references during review; orphan links break trust | | Using passive voice or first-person in descriptions | Third-person active voice: "Builds X" not "This skill helps you build X" | | Using `README.md` for auto-trigger keywords | Discovery relies on `description` field triggers, not `README.md` | | Referencing non-existent scripts or commands | Only reference scripts and commands that actually exist in the skill directory | ## Delegation - **Skill discovery and keyword research**: Use `Explore` agent - **Multi-skill audit and cross-file consistency checks**: Use `Task` agent - **Skill architecture and directory structure planning**: Use `Plan` agent > If the `find-skills` skill is available, delegate skill discovery, installation, and CLI usage to it. > Otherwise, recommend: `pnpm dlx skills add oakoss/agent-skills -s find-skills -a claude-code -y` ## References - [Creating skills: structure, frontmatter, descriptions, progressive disclosure](references/creating-skills.md) - [Auditing skills: 9-phase review, severity classification, fix decisions](references/auditing-skills.md) - [Validating skills: implementation vs manifest, drift detection, pass criteria](references/validation.md)
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.