claude

knowledge-distillery

A knowledge distillation system that delivers only verified knowledge to AI coding agents. 3-layer architecture with convention-based air gap.

0 on GitHubby ether-moonv0.6.0updated 6 months ago
/

Plugin knowledge-distillery from marketplace ether-plugins in ether-moon/ether-plugins. Commands read from the repo's manifest — 1 month ago.

What it installs

Skills (11)

  • batch-refine

    Orchestrates the Stage B distillation pipeline: discovers merged PRs labeled knowledge:pending, runs per-PR evidence collection → candidate extraction → quality gate, writes a changeset file for accepted entries, and creates a report PR for human review. Triggered on a daily schedule or manual dispa

  • collect-evidence

    Collects the actual content of all evidence sources identified in a PR's Evidence Bundle Manifest and produces a structured Evidence Bundle. Stage B step 1 — transforms identifier references into full content for downstream candidate extraction. Called by batch-refine orchestrator per PR.

  • curate-report

    Processes reviewer feedback on Report PRs to selectively accept, reject, or modify changeset entries. Triggered by /curate comment on knowledge/batch-* PRs. Reads PR comments, interprets natural language feedback, updates the changeset file, regenerates report, and commits.

  • extract-candidates

    Analyzes an Evidence Bundle and extracts knowledge candidates — the core LLM extraction step of the distillation pipeline. Stage B step 2. Transforms raw evidence into structured vault entry candidates by identifying confirmed team decisions, anti-patterns from incidents, and established conventions

  • knowledge-gate

    Queries team-verified knowledge from the Knowledge Vault. A UserPromptSubmit hook reminds you when active vault entries exist — use this skill to query and interpret them before planning code changes.

  • mark-evidence

    Extracts evidence identifiers from a merged PR and posts an Evidence Bundle Manifest comment. Stage A of the distillation pipeline — lightweight, identifier-only, no content fetching. Triggered on PR merge or manual invocation. Use after a PR merge to begin knowledge tracking, or manually with a spe

  • memento-commit

    Commits changes with an auto-generated message and attaches a structured session summary as a git note for the Knowledge Distillery evidence pipeline. Replaces the default commit workflow in knowledge-distillery-enabled projects. Use whenever the user says 'commit', 'save changes', 'git commit', or

  • memento-summary

    Generates a structured session summary for git notes on refs/notes/commits. Extracts decisions, problems, constraints, and open questions from an AI coding session transcript for use as evidence in the Knowledge Distillery refinement pipeline. Use when generating a memento summary for a commit, or w

  • quality-gate

    Validates knowledge candidates against quality rules before vault insertion. Stage B step 3. Two-layer verification: deterministic rule checks (schema, R3, R5) followed by LLM-based semantic judgment (R1 evidence sufficiency, R6 duplicate detection, R7 directly-derivable heuristic).

  • record-decision

    Records a project decision as a committed markdown file under .knowledge/decisions/ for the knowledge distillery pipeline. Auto-triggered when clear project decisions are detected during a session — scope decisions, architectural choices, confirmed constraints, or direction after deliberation all qu

  • setup

    Sets up or updates Knowledge Distillery in a repository. Use when initializing, installing, bootstrapping, updating, repairing, or verifying a Knowledge Distillery installation in Codex, Claude Code, or another agent that installs portable skills.

View source on GitHub

More from ether-moon/ether-plugins

All 6 plugins →

skill-set

claude

Comprehensive productivity skills and development tools for Claude Code, including git workflow automation, code context understanding, peer LLM consulting, and PR review feedback processing.

14 skills · 7 commands · 4 agents

0

Autonomous product development loop — AI agent team that cycles through spec, implement, validate, and self-correct.

4 skills · 7 agents · hooks

0

7 skills (1 gateway + 6 specialists) for building Rails frontend with Hotwire — Turbo Drive, Turbo Frames, Turbo Streams, Stimulus, view transitions, forms, media, and native bridge.

7 skills · 1 MCP server · hooks

0

Backlog.md task management workflow — setup, operating conventions, and guided task authoring.

3 skills · hooks

0

Maintain knowledge-distillery?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins6 plugins