メニュー
This skill should be used when the user says "list loaded skills", "disable skills", "skills are wasting tokens", "too many skills loaded", "which skills are active", "unload skills", "skill token cost", or "skills killing my budget".
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | Manage Skills |
| description | This skill should be used when the user says "list loaded skills", "disable skills", "skills are wasting tokens", "too many skills loaded", "which skills are active", "unload skills", "skill token cost", or "skills killing my budget". |
| version | 1.0.0 |
Audit and reduce skill token overhead. Skills silently consume 1,000-28,000 tokens each when loaded.
Each loaded skill SKILL.md body costs tokens every response:
To identify which skills are active, instruct user to run:
# List all installed plugins and their skills
ls ~/.claude/plugins/
# Check active plugin config
cat ~/.claude/settings.json | grep -i plugin
Then read and report:
Edit ~/.claude/settings.json and set plugin enabled to false, or remove plugin from active list.
Tell user to add to their claude.md:
## Skill Loading Policy
Only load skills when explicitly requested with /skill-name.
Do not auto-load skills based on conversation context.
Disabled plugins: [list plugins not needed]
Keep only skills actively needed for current work. Disable:
Use autoLoadSkills: false in settings.json to prevent all skills from loading automatically.
For each skill directory, estimate cost:
# Count words in all SKILL.md files
find ~/.claude/plugins -name "SKILL.md" -exec wc -w {} \; | sort -n
Skills over 3,000 words = high cost. Consider disabling or requesting optimization.
references/skill-audit.md — Full audit procedure and cost reduction strategiesThis skill should be used when the user says "check claude.md size", "is my claude.md too big", "claude.md token cost", "how big is claude.md", or when triggered automatically on session start to warn about oversized claude.md files.
This skill should be used when the user asks to "show recent changes", "show forge changelog", "show changelog for <project>", "what did I add this week", "what files did I touch today", "what packages keep recurring", "what drifts from the template", "review template suggestions", "show pending forge suggestions", "sync forge templates", "apply template suggestion", or "compute back-mapping suggestions". Provides read, drift-discovery, and template back-mapping workflows that wrap the `forge-db` MCP tools (`get_changelog`, `compute_suggestions`, `apply_suggestion`).
This skill should be used when the user says "build a wiki", "maintain a wiki", "ingest docs into wiki", "query my wiki", "set up llm wiki", "wiki-based knowledge base", "stop re-reading docs every session", "persistent knowledge base", or "compress my docs into wiki pages".
This skill should be used when the user says "auto compact", "enable auto compact", "compact on context full", "automatic context compression", "prevent context limit errors", "set up auto compaction", or "context keeps hitting limit".
This skill should be used when the user says "show settings diff", "what changed in settings", "compare settings before after", "settings optimization preview", "preview settings changes", or "show me what tune-settings will change".
Use this skill when the user says "/task_brain", "break down this task", "plan this", "decompose this problem", or when a task has multiple moving parts, unclear dependencies, or high ambiguity.