distill is agent-read markdown (skill) from komluk/scaffolding: Knowledge distillation methodology: candidate extraction, confidence scoring, tier routing, conversation-scoped mode. TRIGGER when: running /learn or /distill, deciding if an insight is memory-worthy, or scoring a knowledge candidate. SKIP: ad-hoc memory reads/writes (use agent-memory); vector storage (use semantic-memory-store)..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Distill Methodology
Guidelines for automated knowledge extraction and consolidation across memory systems.
## Knowledge Candidate Criteria
An insight qualifies as a knowledge candidate when it meets ANY of these:
| Criterion | Source | Example |
|-----------|--------|---------|
| Cross-conversation pattern | 3+ context.md files contain the same insight | "Redis pool exhaustion under SSE load" |
| Architectural decision | design.md contains explicit Decision/Rationale section | "Use pgvector for semantic search" |
| Recurring gotcha/bug | Keyword match in specs: gotcha, bug, pattern, lesson | "POST 301 redirect strips body" |
| Stale reference | File path in memory points to non-existent file | "app/backend/old_module.py" |
| Cross-tier duplicate | Same entry in both KNOWLEDGE.md and agent MEMORY.md | Duplicated bullet point |
## Confidence Scoring
| Occurrences | Confidence | Tier Recommendation |
|-------------|------------|---------------------|
| 5+ conversations | 0.5 - 1.0 | shared (KNOWLEDGE.md) |
| 3-4 conversations | 0.3 - 0.5 | shared (with review) |
| 1-2 conversations | 0.1 - 0.2 | agent-specific MEMORY.md |
| Decision section | 0.7 fixed | shared |
…
Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
A 17 of 17 checks passed. Deterministic, no model, same answer every run.
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (5030 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag
Source
GitHub
komluk/scaffolding · 15 stars · license MIT · pushed 2026-09-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ntuepc4w5smim2n2
GET https://markdownregistry.com/api/v1/resolve?ref=komluk/scaffolding/distill
GET https://markdownregistry.com/api/v1/blob/52a4674afe73f488f5bd77a7c6afc208f15d9b74c633f1e026b2ccc8b0db5390
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
komluk/scaffolding · skills/github-actions-template/SKILL.md · GitHub Actions CI pipeline templates and workflow YAML patterns. TRIGGER when: creating or editing a CI workflow…
komluk/scaffolding · skills/mcp-tools/SKILL.md · MCP tool decision tree and MCP-first fallback strategy. TRIGGER when: choosing whether to use an MCP tool versus a…
7xuanlu/wenlan · plugin/skills/distill/SKILL.md · Synthesize wiki pages from related memories. One endpoint, one flow: daemon clusters and synthesizes what it can; agent…
7xuanlu/wenlan · plugin-codex/skills/distill/SKILL.md · Synthesize or refresh source-backed Wenlan pages from Codex. Invoked as /distill [target], /distill deep, or /distill…
borda/ai-rig · plugins/cc_foundry/skills/distill/SKILL.md · One-time snapshot extracting patterns from work history and accumulated lessons, distills into concrete improvements —…
mikeprasad/aria-knowledge · plugin-claude-code/skills/distill/SKILL.md · Turn raw task text into a tiered executable spec per TASK.schema.md. Auto-tiers by complexity (micro/standard/full)…
mikeprasad/aria-knowledge · plugin-antigravity/skills/distill/SKILL.md · Turn raw task text into a tiered executable spec per TASK.schema.md. Auto-tiers by complexity (micro/standard/full)…
mikeprasad/aria-knowledge · plugin-openai-codex/skills/distill/SKILL.md · Shape messy task input into an implementation-ready task spec with scope, criteria, risks, dependencies, and execution…
donald-ada/workinggenius · skills/distill/SKILL.md · Retroactively distill the logs of finished work — delete what the repo now answers, keep what code cannot say. Done…
yuno15-bb/greymatter-engine · skills/distill/SKILL.md · Turn what was just worked out into a C Brain note — filed in the right zone, linked to what it relates to, indexed. Use…
