skill-cleaner
Audit Joel's Pi/joelclaw skills: loaded roots, duplicates, stale or unused skills, prompt-budget cost, and compact descriptions. Use when trimming skill prompt budget, finding duplicate skills, or deciding which skill copy should be canonical.
What this skill does
# Skill Cleaner Use this when trimming skill prompt budget, finding duplicate skills, auditing enabled/disabled skill roots, or deciding which skills/plugins to remove. This is adapted for Joel's system from Peter Steinberger's `agent-scripts` `skill-cleaner` skill. ## Joel System Contract - Canonical joelclaw skills live in `~/Code/joelhooks/joelclaw/skills/`. - Consumer skill dirs should usually symlink into canonical skills: - `~/.pi/agent/skills/<name>` - `~/.agents/skills/<name>` - `~/.claude/skills/<name>` - External skill packs may live under `~/.pi/agent/git/`, `~/.pi/agent/npm/node_modules/`, or extension directories. Do **not** copy those into joelclaw unless Joel explicitly wants a curated fork. - Preserve project-local skills and repo policy even when they look redundant. They often encode operational truth. ## Workflow 1. Run the analyzer from this skill directory or the joelclaw repo root: ```bash node --experimental-strip-types skills/skill-cleaner/scripts/skill-cleaner.ts --months 3 ``` Useful variants: ```bash node --experimental-strip-types skills/skill-cleaner/scripts/skill-cleaner.ts --no-logs node --experimental-strip-types skills/skill-cleaner/scripts/skill-cleaner.ts --months 6 --max-log-mb 800 --deep-logs node --experimental-strip-types skills/skill-cleaner/scripts/skill-cleaner.ts --context-tokens 272000 --budget-percent 2 --no-logs node --experimental-strip-types skills/skill-cleaner/scripts/skill-cleaner.ts --root ~/Code/badass-courses/skills --no-logs node --experimental-strip-types skills/skill-cleaner/scripts/skill-cleaner.ts --json --no-logs ``` 2. Read the report in this order: - `Skill Budget`: GPT-5.5-ish context size, 2% skill budget, model-budgeted usage, and pre-budget full-list pressure. - `Description candidates`: long descriptions where tighter plain language saves prompt budget. - `Duplicates`: same skill name or near-identical description/body across Pi, joelclaw canonical, external packs, Codex, and project roots. - `Unused candidates`: no recent `$skill` mention, `SKILL.md` read, or explicit skill-use trace in recent Pi/Codex/Claude logs. - `Root summary`: where skills came from and whether config marks them disabled. 3. Before deleting or editing: - Verify the kept copy exists and is loaded. - Prefer canonical joelclaw repo copies for Joel-owned operational skills. - Prefer external package copies for third-party skills unless we intentionally forked them. - Preserve trigger nouns in descriptions: product, tool, action, object. - Never delete ignored/untracked skill dirs without naming the destination or confirming they are disposable. ## Analyzer Notes - The script mirrors model-visible skill list line shape: `- name: description (file: path)`. - It applies Codex/Pi-like frontmatter rules: YAML frontmatter only, default name from parent dir, single-line sanitized `name` and `description`. - It follows the common 2% of raw `context_window` prompt-budget heuristic, token cost `ceil(utf8_bytes / 4)`, then full descriptions -> equal description truncation -> omitted minimum lines. - It searches `~/.pi/models_cache.json` then `~/.codex/models_cache.json`; fallback is 272,000 tokens and 95% effective context. - It scans Joel's normal skill roots by default: joelclaw canonical, Pi user skills, agents skills, Claude skills, Pi git/npm/extension skills, plus legacy Codex roots. - Extra folders such as project-specific skill roots are included only with `--root <path>`. - It realpath-dedupes roots, so symlinked roots do not create false duplicates. - For duplicate names, it reports description/body similarity and suggests deletion candidates only when bodies are near copies. - Usage evidence is heuristic: `$skill`, `Use $skill`, and paths like `skills/<name>/SKILL.md` in recent logs. ## Output Policy - Suggest first; edit only when the user asks. - If asked to apply cleanup, make small grouped commits: descriptions, deletes, config disables. - Do not delete ignored/untracked skill dirs without naming the destination or confirming they are disposable. - For broad cleanup, pair this with `skill-review` and keep the parent agent as the decision-maker. No silent axe murder. 🐀
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($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.