Distill
- 300 installs
- 1 repo stars
- Updated May 26, 2026
- camacho/ai-skills
distill is a Claude Code skill that runs a three-stage pipeline to extract imperatives from AGENTS.md and rules/, compose policy algebra, and render Mermaid diagrams for developers who need to audit and restructure agent
About
distill is a Claude Code skill from camacho/ai-skills that orchestrates a three-stage pipeline on AGENTS.md and rules/ directories when agent instruction files grow past readable size. Stage one /imperatives extracts structured imperatives into JSONL artifacts. Stage two /policy-algebra composes them with policy algebra into Starlark. Stage three /visualize renders decision trees as Mermaid diagrams. Artifacts land in ai-workspace/research with date-stamped outputs, and each stage can run independently via /distill --stage flags. The forced pause between extraction and composition lets developers review what rules actually exist before restructuring policies. Developers reach for distill before major agent-governance refactors, when onboarding new agent runtimes, or when rules need trimming, deduplication, and visual documentation of decision logic.
- Full pipeline: extract imperatives → compose with policy algebra → visualize as Mermaid
- Stage flags run imperatives-only, compose-only, or visualize-only when prior artifacts exist
- Defaults target ai-workspace/rules/*.md and AGENTS.md with JSONL and Starlark outputs
- Human checkpoint asks you to review extraction before composition
- Summaries report imperative counts with level and scope breakdowns
Distill by the numbers
- 300 all-time installs (skills.sh)
- Ranked #2,296 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Security screen: LOW risk (skills.sh audit)
- Data as of Jul 28, 2026 (Skillselion catalog sync)
npx skills add https://github.com/camacho/ai-skills --skill distillAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 300 |
|---|---|
| repo stars | ★ 1 |
| Security audit | 3 / 3 scanners passed |
| Last updated | May 26, 2026 |
| Repository | camacho/ai-skills ↗ |
How do you analyze and visualize AGENTS.md rules?
Run a three-stage pipeline to extract imperatives from AGENTS.md and rules/, compose them with policy algebra, and render Mermaid diagrams of your agent rule system.
Who is it for?
Developers governing large AGENTS.md and rules/ trees who need extraction, policy composition, and Mermaid visualization before refactoring agent instructions.
Skip if: Repos with a handful of cursor rules and no AGENTS.md, or teams wanting one-off lint fixes without a multi-stage policy pipeline.
When should I use this skill?
AGENTS.md or rules/ directories are bloated, need audit before refactor, or a developer asks to visualize agent policy as Mermaid diagrams.
What you get
JSONL imperatives file, Starlark policy composition, Mermaid decision-tree diagrams, and date-stamped artifacts under ai-workspace/research.
- JSONL imperatives extract
- Starlark policy file
- Mermaid rule-system diagram
By the numbers
- Orchestrates a three-stage pipeline: imperatives extraction, policy algebra composition, and Mermaid visualization
Files
/distill
Distill agent instruction files into structured imperatives, compose with policy algebra, and visualize the rule system. Three-stage pipeline.
Usage
/distill # full pipeline on default files
/distill ai-workspace/rules/*.md # specific targets
/distill --stage imperatives # run only extraction
/distill --stage compose # run only policy algebra (requires prior extraction)
/distill --stage visualize # run only visualization (requires prior composition)Pipeline
┌─────────────┐ ┌──────────────┐ ┌─────────────┐
│ /imperatives │────▶│/policy-algebra│────▶│ /visualize │
│ extract │ │ compose │ │ render │
└─────────────┘ └──────────────┘ └─────────────┘
│ │ │
JSONL file Starlark block Mermaid diagramsStage 1 — Extract (/imperatives)
1. Invoke /imperatives with the target files (or defaults: ai-workspace/rules/*.md + AGENTS.md). 2. Save output to ai-workspace/research/<name>-imperatives.jsonl. 3. Present the summary (count, level breakdown, scope breakdown).
Ask the user: "Review the extraction before composing? (y/continue)"
- If yes: present the JSONL for review, wait for feedback, re-extract if needed.
- If continue: proceed to Stage 2.
Stage 2 — Compose (/policy-algebra)
1. Project the JSONL to natural-language bullets: <level>[ NOT] <subject> <predicate>[ when <when>] — one bullet per imperative. 2. Invoke /policy-algebra with the projected bullets. 3. Save the Starlark composition to ai-workspace/research/<name>-policy.md. 4. Present the surfaced structure (decision functions, branching points).
Stage 3 — Visualize (/visualize)
1. For each major decision function in the Starlark output, invoke /visualize. 2. Content shape is typically graph (decision trees) → Mermaid flowcharts. 3. Append diagrams to the policy doc.
Naming
The <name> slug defaults to the current date + "distill" (e.g., 2026-05-04-distill). Override with --name <slug>.
Output
All artifacts land in ai-workspace/research/:
<name>-imperatives.jsonl— structured extraction<name>-policy.md— Starlark composition + diagrams
Failure modes
| Condition | Behavior |
|---|---|
| /imperatives finds zero imperatives | Report and stop. No point composing empty input. |
| /policy-algebra unavailable | Skip Stage 2, warn. Stage 3 can still visualize the JSONL directly. |
| User interrupts between stages | Artifacts from completed stages are preserved. Resume with --stage. |
When to use
- AGENTS.md or rules/ grew past a size threshold and needs trimming
- Before a major restructuring of agent instruction files
- To audit what rules actually exist vs what you think exists
- As input to a plan that modifies the rule system
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10How it compares
Pick distill when AGENTS.md and rules/ need multi-stage extraction, policy composition, and diagrams—not a single-pass summary of cursor rules.
FAQ
What are the three stages of distill?
distill runs /imperatives to extract JSONL imperatives from AGENTS.md and rules/, /policy-algebra to compose Starlark policy, and /visualize to render Mermaid decision-tree diagrams. Each stage can run independently with --stage flags.
Where does distill save output?
distill saves date-stamped artifacts under ai-workspace/research, including JSONL imperatives, composed Starlark policy, and Mermaid diagrams. The pause between extraction and composition supports manual review before restructuring rules.
Is Distill safe to install?
skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.