Chalk Labs
Need help deploying evolve?
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.
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/eroslifestyle-evolve-acb55e
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.
About
Reviews
Write a reviewNo 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/evolve
Tools it pre-approves 5
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
Read,Write,Edit,Glob,Grep
What's inside
- Skill name
evolve- Description
- Aggregate high-confidence instincts into reusable skills. Use when the user says /evolve or periodically to consolidate learnings.
- License
- MIT
- Allowed tools
- Read,, Write,, Edit,, Glob,, Grep
- Instructions
- 127 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Evolve Skill - Instinct-to-Skill Promotion
## Purpose
Transform proven instincts (confidence >= 0.7) into permanent, reusable skill files.
This is the second stage of the Continuous Learning System.
## Trigger
- User types `/evolve`
- Can also be suggested automatically when 3+ instincts reach confidence >= 0.7 in a tag group
## Algorithm
1. **Read instincts**: Load `~/.claude/learnings/instincts.json`
2. **Filter candidates**: Select instincts where confidence >= 0.7 AND evolved_to is null/missing
3. **Check threshold**: If fewer than 3 candidates total, show message and suggest using `/learn` more
4. **Group by tags**: Group candidates by ALL their tags (see Multi-Tag Grouping)
- An instinct contributes to every tag group it belongs to
5. **For each group with 3+ instincts**:
a. Generate skill name: `{tag}-learned` (e.g., `parallelism-learned`)
b. Check if skill already exists at `~/.claude/skills/{tag}-learned/SKILL.md`
- If exists: merge new patterns into existing skill (see Skill File Merging below)
- If not: create new skill directory and SKILL.md (Write tool)
c. Generate skill file with YAML frontmatter and consolidated patterns
d. Mark each source instinct: append `"{tag}-learned"` to `"evolved_to"` array
e. Update metadata: increment total_evolved, set last_evolution date
6. **Save**: Write updated instincts.json
7. **Display summary**: Show evolution results
## Generated Skill Format
```markdown
---
name: {tag}-learned
description: Auto-evolved best practices for {tag}, learned from {N} confirmed patterns.
user-invocable: false
allowed-tools: Read
---
# {Tag} Best Practices (Learned)
Auto-generated by the Continuous Learning System on YYYY-MM-DD.
Source: {N} instincts with average confidence {avg}.
## Patterns
### 1. {instinct.pattern}
- **Confidence:** {instinct.confidence}
- **Evidence:** {instinct.evidence count} confirmations
- **First seen:** {instinct.created}
### 2. {instinct.pattern}
...
## Application
These patterns should be applied automatically when the orchestrator
detects relevant context matching the tags: {tags}.
```
## Grouping Rules
- An instinct contributes to ALL tag groups it belongs to (not just primary)
- Minimum 3 instincts per group to trigger evolution
- Groups with fewer than 3 are skipped (instincts remain for future evolution)
- An instinct is excluded from a tag group only if that specific tag appears in its evolved_to array
### Multi-Tag Grouping
An instinct contributes to ALL its tag groups (not just primary).
Example: instinct with tags ["testing", "parallelism"] contributes to both groups.
Mark evolved_to as array: `"evolved_to": ["testing-learned", "parallelism-learned"]`
When an instinct evolves via one tag group, it remains eligible for other tag groups
until all its tags have been evolved or it is explicitly excluded.
## Output Format - Success
```
EVOLUTION COMPLETE
Instincts processed: N (of M total candidates)
Skills created: K
Skills updated: J
Created Skills:
- skills/parallelism-learned/SKILL.md (from 4 instincts)
- skills/testing-learned/SKILL.md (from 3 instincts)
Remaining candidates: X instincts (need more confirmations or group members)
Tip: Continue using /learn to build more instincts. Next evolution check at 3+ per tag.
```
## Output Format - Not Ready
```
EVOLUTION CHECK
High-confidence instincts (>= 0.7): N
Groups meeting threshold (3+): 0
Breakdown by tag:
- parallelism: 2 instincts (need 1 more)
- testing: 1 instinct (need 2 more)
Tip: Use /learn to capture more patterns. Instincts grow with repeated confirmation.
```
## Skill File Merging
When appending to an existing evolved skill:
1. Read existing skill file
2. Find last numbered pattern (e.g., `### 5.`)
3. Assign next number to new patterns (e.g., `### 6.`)
4. Append before "## Application" section
5. Update "auto-generated" and "Last updated" timestamps
6. Increment "Sources" countFrom eroslifestyle/Claude-Orchestrator-Plugin, MIT.
More from eroslifestyle/Claude-Orchestrator-Plugin
- 0.432score
learn
eroslifestyle
Capture a learning pattern from the current session with confidence scoring.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
debugging
eroslifestyle
When to use this skill for systematic debugging including root cause analysis, error tracing, performance profiling, and memory leak detection
SkillDFreshness: D★ 1Claude Code +9 - 0.431score
code-review
eroslifestyle
When to use this skill for automated code quality analysis and review
SkillDFreshness: D★ 1Claude Code +9 - 0.431score
git-workflow
eroslifestyle
When to use this skill for advanced Git operations and workflow management
SkillDFreshness: D★ 1Claude Code +9 - 0.429score
python-patterns
eroslifestyle
Python best practices, idioms, and patterns.
SkillDFreshness: D★ 1Claude Code +9 - 0.429score
plan
eroslifestyle
Decompose a feature request into a detailed implementation plan with task breakdown, dependencies, and risk assessment.
SkillDFreshness: D★ 1Claude Code - 0.429score
go-patterns
eroslifestyle
Go best practices, idioms, and patterns.
SkillDFreshness: D★ 1Claude Code +9 - 0.429score
prompt-engineering-patterns
eroslifestyle
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability.
SkillDFreshness: D★ 1Claude Code +9 - 0.426score
cleanup
eroslifestyle
Run session cleanup - delete temp files, NUL files, orphan artifacts
SkillDFreshness: D★ 1Claude Code +9 - 0.426score
build-fix
eroslifestyle
Diagnose and fix build errors automatically.
SkillDFreshness: D★ 1Claude Code - 0.426score
checkpoint
eroslifestyle
Save a named checkpoint of current session progress.
SkillDFreshness: D★ 1Claude Code +9 - 0.426score
metrics
eroslifestyle
Display detailed session metrics and agent performance.
SkillDFreshness: D★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Mar 3, 2026 (8 months ago)
- Last release
- Mar 3, 2026 (8 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from eroslifestyle
- 0.432score
debugging
eroslifestyle
When to use this skill for systematic debugging including root cause analysis, error tracing, performance profiling, and memory leak detection
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
learn
eroslifestyle
Capture a learning pattern from the current session with confidence scoring.
SkillDFreshness: D★ 1Claude Code +9 - 0.431score
git-workflow
eroslifestyle
When to use this skill for advanced Git operations and workflow management
SkillDFreshness: D★ 1Claude Code +9 - 0.431score
code-review
eroslifestyle
When to use this skill for automated code quality analysis and review
SkillDFreshness: D★ 1Claude Code +9 - 0.429score
prompt-engineering-patterns
eroslifestyle
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability.
SkillDFreshness: D★ 1Claude Code +9 - 0.429score
go-patterns
eroslifestyle
Go best practices, idioms, and patterns.
SkillDFreshness: D★ 1Claude Code +9
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 evolve 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.
Cite this page
evolve skill. Agent Mart. https://agentmart.dev/skills/eroslifestyle-evolve-acb55e (last updated 2026-10-24)