Auto-generate new skills from learnings, approved patterns, and repeated user preferences. The meta-skill that makes the harness self-improving. Core to AutoLab.
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
## When to Use
- After discovering a repeatable pattern across 2+ sessions
- When the user explicitly approves a workflow ("always do X")
- When LEARNINGS.md has 3+ entries about the same topic
- When a sub-agent finds a new capability worth capturing
- During AutoLab nightly improvement cycles
## Process
### 1. Source Mining
Scan these sources for skill candidates:
- `memory/LEARNINGS.md` — repeated corrections = skill gaps
- `memory/MEMORY.md` — confirmed patterns = skill candidates
- `memory/daily/*.md` — workflows that worked = codify them
- `resources/read/*.md` — external techniques worth internalizing
- Session transcript — what did the user approve? correct? praise?
- `packages/web/features.json` — feature patterns that recur
### 2. Skill Candidate Evaluation
For each candidate, score on 4 axes:
| Axis | Question | Threshold |
| --------------- | ---------------------------------------------- | --------------------- |
| **Frequency** | How often would this skill be triggered? | 2+ times/week |
| **Complexity** | Does it need multi-step instructions? | 3+ steps |
…
The line at the top of this page pins the label git:20260526.f887f6c, 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.
GET https://markdownregistry.com/api/v1/artifacts/art_v3tv2gnukc2hmwvd
GET https://markdownregistry.com/api/v1/resolve?ref=naman10parikh/agentgrid/skill-creator
GET https://markdownregistry.com/api/v1/blob/273bc02abd9bf9935cf7ec306658815b4b1c0b005a2d490894ac972e37cac31e
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.
naman10parikh/agentgrid · .claude/skills/anthropic-frontend-design/SKILL.md · Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to…
naman10parikh/agentgrid · .claude/skills/architect/SKILL.md · Use when making architectural decisions for the Energy/NRG platform. Loads architecture from VISION.md and debates…
naman10parikh/agentgrid · .claude/skills/ecosystem-reference/SKILL.md · Quick-access directory of Claude Code ecosystem repos, skills, plugins, MCPs, and patterns. Use when improving the…
naman10parikh/agentgrid · .claude/skills/harness-review/SKILL.md · Review an agent's harness (scaffold) for quality, token efficiency, and correctness. Based on harness engineering…
naman10parikh/agentgrid · .claude/skills/integrate-resources/SKILL.md · Process new resources dropped into resources/unread/. Extracts Claude Code tips, tools, patterns and updates the setup…
naman10parikh/agentgrid · .claude/skills/llm-council-critique/SKILL.md · Run a 6-hat brutal LLM Council self-critique on any deliverable, session output, or status update. Surfaces what's…
naman10parikh/agentgrid · .claude/skills/loop-create/SKILL.md · Scaffold a new agent with the full file structure. Use when creating any new agent for the Energy platform. NOTE —…
anthropics/skills · skills/skill-creator/SKILL.md · Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a…
bytedance/deer-flow · skills/public/skill-creator/SKILL.md · Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a…
cherryhq/cherry-studio · resources/skills/skill-creator/SKILL.md · Create, edit, evaluate, and optimize skills, including benchmarking and description tuning for better triggering.
anthropics/claude-plugins-official · plugins/skill-creator/skills/skill-creator/SKILL.md · Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a…
volcengine/openviking · bot/workspace/skills/skill-creator/SKILL.md · Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
garrytan/gbrain · plugin/skills/skill-creator/SKILL.md · Create new skills following the GBrain conformance standard. Generates SKILL.md
with frontmatter, Contract, Phases…
garrytan/gbrain · skills/skill-creator/SKILL.md · Create new skills following the GBrain conformance standard. Generates SKILL.md
with frontmatter, Contract, Phases…
eigent-ai/eigent · resources/example-skills/skill-creator/SKILL.md · Guide for creating effective skills. Use when creating a new skill or updating an existing skill that extends agent…