Agent skill · Design & Presentation

distilling

Analyze a user canvas and distill structured fears, steering targets, and synthesis features into a cognition sidecar file.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill distilling-0xhoneyjar-construct-beehive --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 9 KB
Bundled scripts: none
Path: skills/analysis/distilling-0xhoneyjar-construct-beehive/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# /distill — Cognition Distillation Analyze a single user's canvas state and produce structured cognition output. This skill runs as a **prompt-only subagent** — it receives all data in its prompt and returns YAML text. The parent orchestrator (`/think` or `/follow-up` auto-refresh) handles filesystem operations. ## Input Contract The parent orchestrator provides these sections in the prompt: | Input | Description | |-------|-------------| | Canvas body | Full markdown of `grimoires/observer/canvas/{user}.md` | | Score API snapshot | JSON from `score-api-query.sh profile <wallet> --format snapshot` (or null if unavailable) | | Growth state | YAML from `grimoires/observer/growth/{user}.yaml` (or null if new user) | | Provenance records | Filtered JSONL entries for this user from `grimoires/mining/provenance/index.jsonl` | | Config | `observer.cognition.*` values (fear_types, max_fears_per_user, stale_after_cycles) | ## Output Contract Return a single YAML document matching the cognition sidecar schema (SDD §2). The parent validates this output against required keys and types before writing to disk. **Required top-level keys**: `schema_version`, `user`, `fears`, `steering_targets`, `

What's inside
Steps it walks through
  1. Input Contract
  2. Output Contract
  3. Algorithm
  4. Step 1: Inventory Hypotheses
  5. Step 2: Classify User State
  6. Step 3: Identify Fears
  7. Step 4: Generate Steering Targets
  8. Step 5: Build Synthesis Features
  9. Fear Type Classification Heuristic
  10. Validation Rules
  11. constraintmismatch Additional Fields
  12. Output Example
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the distilling skill do?

Analyze a user canvas and distill structured fears, steering targets, and synthesis features into a cognition sidecar file.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill distilling-0xhoneyjar-construct-beehive --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going