jianzhichun/emerge/distill-from-pattern

Claude Code and agent skill by jianzhichun/emerge

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Use when an Emerge event stream contains pattern_observed, local_pattern_observed, pattern_aggregated, or pattern_pending_synthesis and Claude must turn raw runner/operator facts into one conservative pipeline candidate through normal mechanism tools.

Install

npx vskill@latest install jianzhichun/emerge/distill-from-pattern

SKILL.md

Distill From Pattern

Use this when pattern_observed, local_pattern_observed, pattern_aggregated, or pattern_pending_synthesis appears in the event stream. The Python layer only emits facts; Claude performs the judgment.

Handoff Contract

scripts/synthesis_events.py is the deterministic packaging boundary. It can append pattern_pending_synthesis and synthesis_job_ready facts for a selected event window, but it does not choose whether the pattern matters, call an LLM provider, smoke-test generated code, or materialize a pipeline.

When the stream only contains pattern_observed, local_pattern_observed, or pattern_aggregated, inspect the facts first. If they justify distillation, package or reference the selected window as synthesis facts, then continue from pattern_pending_synthesis / synthesis_job_ready. Do not reintroduce a Python coordinator.

Workflow

  1. Read the referenced event window from events/events-<profile>.jsonl, events/events-local.jsonl, or events/events.jsonl.
  2. Read connector-local NOTES.md and optional synthesis_hints.yaml.
  3. Infer the smallest repeated operation and choose a generic connector.mode.name intent.
  4. Write conservative exploratory code that assigns __result for reads or __action for writes.
  5. Run one icc_exec with explicit intent_signature and representative args.
  6. If execution fails or verification is ambiguous, report the blocker instead of retrying indefinitely.

Rules

  • Keep product-specific knowledge in connector-local files, not this skill.
  • Parameterize only values that vary across event samples.
  • Prefer a narrow pipeline candidate over a broad one with weak verification.
  • Never write lifecycle state directly; use the mechanism tools that record WAL and evidence.

Output

Return a concise report with intent signature, source events inspected, icc_exec verification result, and any remaining blocker.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
106
Repository forks
13
7-day trend score
23

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/jianzhichun/emerge/distill-from-pattern/badge)](https://verified-skill.com/skills/jianzhichun/emerge/distill-from-pattern)

Something wrong with this skill or its page? Tell us.