Skip to content
Agentmart
Submit a tool

distill

Synthesizes related learnings into reusable knowledge base patterns.

Skill by goffity

IndexedMIT
Write a review

Chalk Labs

Need help deploying distill?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/goffity-distill

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Synthesizes related learnings into reusable knowledge base patterns.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/distill

What's inside

Skill name
distill
Description
Synthesizes related learnings into reusable knowledge base patterns.
License
MIT
Instructions
146 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • files: referenced but missing: references/language-guide.md, references/bash-helpers.md

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Distill - Extract Patterns & Lessons

สังเคราะห์ความรู้จาก /mem learnings เป็น patterns (Layer 2)

## Usage

```
/distill [topic-name]
```

**Input:** `kb/05-ai-reviewed/learnings/` (vault via symlink)
**Output:** `kb/02-patterns/<domain>/<Name>.md`

> Note: `kb/` is a symlink to the Obsidian second-brain vault.
> Legacy path `docs/learnings/` + `docs/knowledge-base/` is deprecated — scan `kb/` only.

## Instructions

### Language Setting

> Check `LANGUAGE` in `docs/current.md`. If `th`, translate output per `references/language-guide.md`. See `references/bash-helpers.md` for detection snippet.

1. **Scan learnings** for related content (3+ files on same topic)
   ```bash
   find $PROJECT_ROOT/kb/05-ai-reviewed/learnings -name "*.md" -type f
   ```
2. **Analyze** for patterns, anti-patterns, insights
3. **Pick domain folder** under `kb/02-patterns/` (grpc, observability, database, k8s, websocket, workflow, auth, architecture, testing). Create new domain folder if needed.
4. **Create** knowledge entry with template below — use Title Case filename (e.g. `Consumer Retry Pattern.md`)
5. **Add frontmatter** per vault convention:
   ```yaml
   ---
   tags: [pattern, <domain>]
   type: pattern
   domain: <domain>
   services: [<services-using-this>]
   date: YYYY-MM-DD
   status: stable
   ---
   ```
6. **Mark sources** as "Distilled" (append `> **Distilled:** → [[<Pattern Name>]]`)
7. **Commit**: `git commit -m "knowledge: [topic] - [summary]"`

## Template

```markdown
# [Topic Name]

| Field | Value |
|-------|-------|
| **Created** | YYYY-MM-DD |
| **Sources** | learnings ที่ใช้ |
| **Tags** | `tag1` `tag2` |

---

## Key Insight

> One-sentence summary

---

## The Problem

| Attempt | Result |
|---------|--------|
| ทำแบบ X | เกิดปัญหา Y |

---

## The Solution

### Pattern: [Name]

```go
// Code example
```

**Why this works:**
- Reason 1

---

## Anti-Patterns

| Don't Do This | Do This Instead |
|---------------|-----------------|
| Bad | Good |

---

## When to Apply

- ใช้เมื่อ...
- ไม่ใช้เมื่อ...

---

## Decision Rationale (Optional)

> ใช้เมื่อ knowledge นี้เกี่ยวข้องกับการตัดสินใจสำคัญ

### Decision

[สรุปการตัดสินใจ]

### Alternatives Considered

| Option | Pros | Cons |
|--------|------|------|
| Option A | ... | ... |
| **Chosen** | ... | ... |

### Why This Choice?

- เหตุผล 1
- เหตุผล 2

### Trade-offs Accepted

From goffity/dev-km, MIT.

More from goffity/dev-km

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Jun 19, 2026 (4 months ago)
Last release
Oct 12, 2026 (18 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from goffity

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get distill running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying distill?

CallGet help
Cite this page

distill skill. Agent Mart. https://agentmart.dev/skills/goffity-distill (last updated 2026-10-24)