manage-agent-instructions
This skill should be used when creating, auditing, refactoring, or syncing CLAUDE.md and AGENTS.md files that configure AI coding agent behavior.
What this skill does
<essential_principles>
## Core Principles
These principles apply to ALL agent instruction files (CLAUDE.md, AGENTS.md).
### 1. Minimal Root File
The root instruction file should be as small as possible. Every token loads on every request regardless of relevance.
**Absolute minimum content:**
- One-sentence project description (acts as role prompt)
- Package manager (if not npm)
- Non-standard build/test commands
Everything else belongs in progressive disclosure files.
### 2. Progressive Disclosure
Structure knowledge in layers:
```
Level 1: Root file (~100-300 words)
Level 2: docs/CONVENTIONS.md, docs/TYPESCRIPT.md, etc.
Level 3: Nested references within those files
```
Load context only when needed for the current task.
### 3. Describe Capabilities, Not Paths
File paths change constantly. Instead of "auth logic lives in src/auth/handlers.ts", write "Authentication is handled by the AuthService module" and let the agent discover current paths.
### 4. No Instruction Bloat
Curate ruthlessly. Remove redundant instructions (agent already knows), vague guidance ("write clean code"), contradicting rules, and auto-generated boilerplate.
### 5. Tool-Specific Files
Claude Code uses CLAUDE.md, not AGENTS.md. For multi-tool support, symlink or redirect between them.
### 6. Monorepo Strategy
| Level | Content |
|-------|---------|
| Root | Monorepo purpose, navigation, shared tools |
| Package | Package purpose, specific stack, local conventions |
Keep each level focused on its scope. Avoid duplication.
</essential_principles>
<intake>
What needs to be done?
1. Create new instruction file
2. Audit existing file
3. Refactor bloated file
4. Sync CLAUDE.md/AGENTS.md
5. Add nested package instructions
Wait for response before proceeding.
</intake>
<routing>
| Response | Workflow |
|----------|----------|
| 1, "create", "new" | `workflows/create-instructions.md` |
| 2, "audit", "review" | `workflows/audit-instructions.md` |
| 3, "refactor", "shrink", "clean" | `workflows/refactor-instructions.md` |
| 4, "sync", "symlink" | `workflows/sync-files.md` |
| 5, "nested", "package", "monorepo" | `workflows/nested-instructions.md` |
After reading the workflow, follow it exactly.
</routing>
<templates_index>
## Templates
Ready-to-use templates in `templates/`:
| Template | Use Case |
|----------|----------|
| [minimal-claude-md.md](./templates/minimal-claude-md.md) | Standard project CLAUDE.md |
| [package-claude-md.md](./templates/package-claude-md.md) | Package-level instructions in a monorepo |
| [monorepo-root.md](./templates/monorepo-root.md) | Root-level monorepo instructions |
</templates_index>
<reference_index>
## References
All in `references/`:
- [agents-md-standard.md](./references/agents-md-standard.md) -- AGENTS.md open standard details
- [claude-md-format.md](./references/claude-md-format.md) -- Claude Code specific CLAUDE.md format
- [progressive-disclosure.md](./references/progressive-disclosure.md) -- structuring knowledge hierarchies
- [common-problems.md](./references/common-problems.md) -- anti-patterns and how to fix them
</reference_index>
<workflows_index>
## Workflows
All in `workflows/`:
| Workflow | Purpose |
|----------|---------|
| create-instructions.md | Create new CLAUDE.md or AGENTS.md from scratch |
| audit-instructions.md | Analyze existing file for problems |
| refactor-instructions.md | Fix bloated/problematic instruction files |
| sync-files.md | Keep CLAUDE.md and AGENTS.md in sync |
| nested-instructions.md | Add package-level instructions in monorepos |
</workflows_index>
<success_criteria>
A well-managed instruction file:
- Root file under 500 words
- Uses progressive disclosure for detailed content
- Describes capabilities, not file paths
- Has no contradicting instructions
- Loads only relevant context per task
</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.