Crystallize

Distils repeating patterns from session logs and lessons.md into draft skill files. Run after ≥10 sessions to extract durable knowledge. Output: draft skills/ files + promotion report.

38 stars 11 forksOther

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add jeremybrasher/grokbot-skills --skill crystallize
Manual install
git clone --depth 1 https://github.com/jeremybrasher/grokbot-skills.git /tmp/grokbot-skills
mkdir -p ~/.claude/skills
cp -r /tmp/grokbot-skills/collections/great-cto/skills/crystallize ~/.claude/skills/crystallize

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Crystallize — distil session patterns into reusable skills

Invoke when the CTO says `/crystallize`, "crystallize", "extract knowledge", or
"what have we learned?". Also auto-suggested when session count is a multiple
of 10 (the session-end hook checks `.great_cto/.last-crystallize`).

The `knowledge-extractor` agent (Opus) does the heavy lifting. This skill
orchestrates the workflow and emits the final report.

**Session-end hint integration:** The session-end hook checks
`.great_cto/.last-crystallize` and suggests running `/crystallize` when the
session count exceeds `last_sessions + 10`. Run this skill after ≥10 sessions
to keep extracted skills current.

---

## Step 1 — Gather raw material

```bash
# Count sessions
SESSION_COUNT=$(ls .great_cto/logs/session-*-end.md 2>/dev/null | wc -l | tr -d ' ')
echo "Sessions: $SESSION_COUNT"

# Read lessons
cat .great_cto/lessons.md 2>/dev/null || echo "(no lessons yet)"

# Read cross-project decisions
cat ~/.great_cto/decisions.md 2>/dev/null | head -200 || echo "(none)"

# Find patterns that appear in ≥3 sessions
grep -h "^## pattern:" .great_cto/logs/session-*-end.md 2>/dev/null | sort | uniq -c | sort -rn | head -20

# Recent git log for context
git log --oneline --since="30 days ago" | head -30
```

If `SESSION_COUNT` is 0, tell the CTO: "No session logs found in
`.great_cto/logs/`. Run at least 10 sessions before crystallizing." Exit.

If `SESSION_COUNT` < 10, tell the CTO: "Only `{N}` sessions found. Patterns
Read the full skill on GitHub

Details

Skill name
crystallize
Path
collections/great-cto/skills/crystallize/SKILL.md
Repo updated
15 September 2026

FAQ

What does the Crystallize skill do?

Distils repeating patterns from session logs and lessons.md into draft skill files. Run after ≥10 sessions to extract durable knowledge. Output: draft skills/ files + promotion report.

How do I install the Crystallize skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add jeremybrasher/grokbot-skills --skill crystallize. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Crystallize popular?

It lives in jeremybrasher/grokbot-skills, which has 38 GitHub stars and 11 forks.

Related skills

Anti Patterns

38

jeremybrasher/grokbot-skills

Catalogue of known SDLC anti-patterns that great_cto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).

Software Development11

Anydesign

38

jeremybrasher/grokbot-skills

Analyze images, websites, and Figma files to extract their design and generate a `design.md` with token system, component inventory, and reconstruction notes. Use this skill whenever the user wants to understand, document, replicate, or audit the design of something visual: a screenshot, a URL, a Figma link, a Pinterest reference, a mockup, a competitor's site, a component, a dashboard, a landing page. Also when they ask 'extract the design system from X', 'document the style of Y', 'analyze this visually', 'convert this image into tokens', 'help me replicate this design', 'what palette does t

Frontend & Design11

Archetype Review Base

38

jeremybrasher/grokbot-skills

Shared review framework that every domain reviewer (pci, oracle, gov, edtech, healthcare, mlops, etc.) MUST follow. Defines the output artifact (TM-{slug}.md), mandatory sections, severity scale, verdict format, the workflow scaffold (when-invoked, Step-0 read-inputs, HANDOFF), and the "domain heuristic vs generic check" boundary. Eliminates duplication across the ~30 reviewer prompts.

Finance & Crypto11

No Comments

38

jeremybrasher/grokbot-skills

Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints. Observe required inputs first; HOLD when they are missing rather than guessing.

Other11

Bro

38

jeremybrasher/grokbot-skills

Restate the last message in plain human language, with no jargon. Observe required inputs first; HOLD when they are missing rather than guessing.

Other11

Swarm

38

jeremybrasher/grokbot-skills

Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration. Observe required inputs first; HOLD when they are missing rather than guessing.

Other11

Browse the most popular Claude skills, all other skills, or write your own with the skills generator.