instruction-hygiene
Audit and trim Claude Code instruction setups that have grown bloated over time. Use when outputs feel worse, rules have accreted across CLAUDE.md/skills/context files, or you want a recurring setup hygiene check.
What this skill does
<essential_principles> ## Core Principles ### 1. Audit the whole setup, not just one file Instruction rot rarely lives only in `CLAUDE.md`. Check all active instruction sources you can access: - root `CLAUDE.md` - nested `CLAUDE.md` files - skill files - context or docs folders used as prompt scaffolding - any extra instruction files loaded by workflow ### 2. Score every rule against the same five filters For each instruction, ask: 1. Is this something Claude already does by default? 2. Does this contradict another rule elsewhere? 3. Does this duplicate something already covered? 4. Does it look like a bandaid for one bad output? 5. Is it vague enough that it could be interpreted differently every time? Rules that fail any filter are candidates for removal or rewrite. ### 3. Prefer fewer, sharper instructions A short, specific setup beats a long defensive one. Keep durable constraints, project facts, and non-obvious workflows. Cut vague style rules, generic quality advice, duplicated reminders, and stale one-off patches. ### 4. Report before editing Do not silently rewrite instruction systems. First produce: - a cut list with one-line reasons - any contradictions or overlaps - a proposed cleaned version of the root instruction file Then let the user review before destructive edits. ### 5. Validate by task outcomes, not by aesthetics After trimming, test the leaner setup on the user's 3 most common tasks. If outputs stay the same or improve, leave the deleted rules out. If one specific behavior regresses, add back only the minimum rule that restores it. ### 6. Treat setup hygiene as recurring maintenance Instruction creep comes back. When useful, generate a reusable prompt or scheduled task so the setup gets re-audited regularly. </essential_principles> <intake> What would you like to do? 1. Audit my current instruction setup 2. Propose a trimmed version of my setup 3. Generate a recurring audit prompt/task Wait for the user's choice before proceeding. </intake> <routing> | Response | Workflow | |----------|----------| | 1, "audit", "inspect", "review" | `workflows/run-setup-audit.md` | | 2, "trim", "clean", "refactor", "rewrite" | `workflows/trim-and-validate.md` | | 3, "schedule", "recurring", "weekly", "automation" | `workflows/schedule-recurring-audit.md` | After reading the workflow, follow it exactly. </routing> <reference_index> ## References - `references/five-filters.md` - The five audit filters and how to apply them consistently - `templates/weekly-audit-prompt.md` - Reusable recurring audit prompt </reference_index> <workflows_index> ## Workflows - `workflows/run-setup-audit.md` - Inspect the full setup and produce an audit report - `workflows/trim-and-validate.md` - Draft a leaner setup, then validate it on common tasks - `workflows/schedule-recurring-audit.md` - Create a reusable or scheduled recurring hygiene audit </workflows_index> <success_criteria> Instruction hygiene work is complete when: - The full active instruction surface was identified - Each rule was evaluated with the five filters - Redundant, conflicting, vague, and bandaid rules were flagged - A cleaned-up root instruction file was proposed or produced - The trimmed setup was validated on common tasks or a clear validation plan was given - A reusable recurring audit prompt exists if the user wants ongoing hygiene </success_criteria>
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.