llm-doc-writer
Write token-efficient documentation for LLM context. Use when creating CLAUDE.md, README, technical docs, agent instructions, or any documentation consumed by AI assistants.
What this skill does
# LLM-Optimized Documentation
## Core Principles
| Principle | Rule |
|-----------|------|
| **Density** | Max info, min tokens |
| **Format** | Tables > prose, bullets > paragraphs |
| **No fluff** | Ban filler words (see list below) |
| **Show don't tell** | Code examples > explanations |
| **Progressive disclosure** | TOC + separate files for details |
## Banned Patterns
```
# Filler words - NEVER use
simplement, il suffit de, en fait, basically, just, simply,
it's important to note, as mentioned, obviously, of course,
please note that, keep in mind, remember that
# Redundant structures - NEVER use
"This file contains..." (obvious from filename)
"In this section we will..." (just do it)
"The following example shows..." (just show it)
```
## Format Rules
### Tables over Prose
```markdown
# BAD - 45 tokens
The system supports three modes: development mode which
enables hot reload, production mode which optimizes for
performance, and test mode which mocks external services.
# GOOD - 20 tokens
| Mode | Behavior |
|------|----------|
| dev | Hot reload |
| prod | Optimized |
| test | Mocked services |
```
### Bullets over Paragraphs
```markdown
# BAD - Narrative
To run the project, first ensure Node.js is installed,
then install dependencies with npm install, and finally
start the dev server with npm run dev.
# GOOD - Scannable
## Run
1. Requires: Node.js 18+
2. `npm install`
3. `npm run dev`
```
### Code over Explanation
```markdown
# BAD - Explaining
To create a new user, call the createUser function
with an object containing name and email properties.
# GOOD - Showing
```ts
createUser({ name: "Jo", email: "[email protected]" })
```
```
## Structure Template
For CLAUDE.md / agent docs:
```markdown
# Project Name
## Stack
- Frontend: React/Vite
- Backend: FastAPI
- DB: PostgreSQL
## Commands
| Action | Command |
|--------|---------|
| Dev | `npm run dev` |
| Test | `npm test` |
| Build | `npm run build` |
## Architecture
[Brief description, link to detailed docs if needed]
## Conventions
- [Rule 1]
- [Rule 2]
```
## Progressive Disclosure
For long docs (>200 lines):
```markdown
# Main Doc
## Quick Reference
[Essential info here]
## Details
See [ARCHITECTURE.md](ARCHITECTURE.md)
See [API.md](API.md)
```
## Self-Check
Before finalizing, verify:
- [ ] No filler words?
- [ ] Tables used where possible?
- [ ] Bullet points, not paragraphs?
- [ ] Examples over explanations?
- [ ] < 500 lines (or split)?
- [ ] No redundant info?
## Examples
See [patterns.md](patterns.md) for before/after examples.
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.