crystallize SKILL.md skillA

crystallize from avelikiy/great_cto is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add avelikiy/great_cto/crystallize@git:20260729.248d2fd

Pins git:20260729.248d2fd in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
avelikiy/great_cto
Path
skills/crystallize/SKILL.md
Versions recorded
3
Latest version
git:20260729.248d2fd, committed Jul 29, 2026
First version recorded
May 21, 2026
Size
4,603 bytes
Repository stars
105
License
MIT

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.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 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
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add avelikiy/great_cto/crystallize@sha256:77f62696c4c7c037

The line at the top of this page pins the label git:20260729.248d2fd, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_lcyywpmbsyrydt2d.svg)](https://markdownregistry.com/a/art_lcyywpmbsyrydt2d)

5 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between May 21, 2026 and Jul 29, 2026, about one every 34 days.

versioncommittedcommitsizeaudit
git:20260729.248d2fd latest2026-07-29 248d2fd 4,603 BA view · diff
git:20260528.4d681c02026-05-28 4d681c0 4,601 BA view · diff
git:20260521.503d8682026-05-21 503d868 4,588 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the 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 (4603 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

avelikiy/great_cto · 105 stars · license MIT · pushed 2026-10-22 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_lcyywpmbsyrydt2d
GET https://markdownregistry.com/api/v1/resolve?ref=avelikiy/great_cto/crystallize
GET https://markdownregistry.com/api/v1/blob/77f62696c4c7c0379990a1e20043c6e83a8a0f9b725b10dfeb1771846dd183be

Your AI assistant 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.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from avelikiy/great_cto

AGENTS.md AGENTS.md file
avelikiy/great_cto · AGENTS.md
git:20261011.ebc6f66 · audit A · 105 stars
CLAUDE.md CLAUDE.md file
avelikiy/great_cto · CLAUDE.md
git:20261005.a2ada06 · audit A · 105 stars
aesthetic-instrument SKILL.md skill
avelikiy/great_cto · skills/aesthetic-instrument/SKILL.md · great_cto's own committed aesthetic — the instrument panel. Dark five-step surface ladder, exactly one accent, two…
git:20260901.dad9527 · audit A · 105 stars
anti-patterns SKILL.md skill
avelikiy/great_cto · skills/anti-patterns/SKILL.md · Catalogue of known SDLC anti-patterns that great_cto agents must actively reject when reviewing architecture, plans…
git:20260921.0ea58e1 · audit A · 105 stars
anydesign SKILL.md skill
avelikiy/great_cto · skills/anydesign/SKILL.md · Analyze images, websites, and Figma files to extract their design and generate a `design.md` with token system…
git:20260618.ed2305f · audit B · 105 stars
archetype-review-base SKILL.md skill
avelikiy/great_cto · skills/archetype-review-base/SKILL.md · Shared review framework that every domain reviewer (pci, oracle, gov, edtech, healthcare, mlops, etc.) MUST follow…
git:20261005.332f2df · audit A · 105 stars
brainstorming SKILL.md skill
avelikiy/great_cto · skills/brainstorming/SKILL.md · Structured idea generation + multi-LLM debate for the product-owner stage. Diverge (generate genuinely different bets)…
git:20260905.acbbd88 · audit A · 105 stars
codex-host SKILL.md skill
avelikiy/great_cto · skills/codex-host/SKILL.md · Run the great_cto controlled Codex lifecycle with controller-owned writes, verifier evidence, human gates and optional…
git:20261022.0db13a3 · audit A · 105 stars
committed-aesthetic SKILL.md skill
avelikiy/great_cto · skills/committed-aesthetic/SKILL.md · How to write — and how to use — a skill that IS one aesthetic rather than a catalogue of them. A catalogue lets an…
git:20260901.c285651 · audit A · 105 stars
cost-model SKILL.md skill
avelikiy/great_cto · skills/cost-model/SKILL.md · Standardized cost-estimation framework for great_cto plans. Forces explicit LLM cost, infra cost, human-supervision…
git:20260528.4d681c0 · audit A · 105 stars
decision-eval SKILL.md skill
avelikiy/great_cto · skills/decision-eval/SKILL.md · Spawns the decision-scorer agent after architect proposes 2+ variants in an ADR. Produces a weighted scoring table and…
git:20260828.11c2979 · audit A · 105 stars
deploy-landed SKILL.md skill
avelikiy/great_cto · skills/deploy-landed/SKILL.md · Prove a deploy landed — the served revision is the commit you meant, its env is present, and the product does its job —…
git:20260922.935dbd1 · audit A · 105 stars

Every file in avelikiy/great_cto

Browse by kind, by grade A, or by owner.