agentleFS
Sign inStart free
TheophilusChinomonaTheophilusChinomona/idev/skills/continuous-learning/SKILL.md

continuous-learning

Skill0 starsChanged 5 months agoMITView on GitHub

Automatically extracts reusable patterns from sessions and saves them as learned skills. Use when asked to learn from a session, extract patterns, or review what was learned.

42 other projects use a version of this, 21 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use project-guidelines-example, clickhouse-io and 6 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • HABUBUSSSkill

    project-guidelines-example

    Also in 7 projects that use this

  • HABUBUSSSkill

    clickhouse-io

    ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.

    Also in 6 projects that use this

  • mstuder-slalomSkill

    continuous-learning-v2

    Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.

    Also in 7 projects that use this

  • Microsoft AzureSkill

    iterative-retrieval

    Max-3-cycle protocol for agent sub-tasks with WHY context and coordinator validation. Use when spawning sub-agents to complete scoped work.

    Also in 9 projects that use this

  • mstuder-slalomSkill

    django-verification

    Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.

    Also in 4 projects that use this

  • nek1987Skill

    postgres-patterns

    PostgreSQL patterns for reviewing migrations and writing efficient queries. Use when reviewing Alembic migrations, optimizing queries, or debugging database issues.

    Also in 7 projects that use this

  • +1 more from mstuder-slalom
  • +1 more from HABUBUSS

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 37 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do NOT extract trivial patterns (typos, one-off fixes)

    line 58
  2. Distinctive:

    Do NOT extract patterns without evidence (must be observed 2+ times)

    line 59
  3. Distinctive:

    Do NOT overwrite existing instincts — update confidence instead

    line 60

“Common” is measured: kept by at least 6 in 10 of the 37 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Continuous Learning Skill

Purpose

Automatically evaluate sessions and extract reusable patterns that improve future sessions.

How It Works

Runs as a Stop hook at session end:

  1. Checks if session has enough activity (default: 10+ tool calls)
  2. Identifies extractable patterns (error resolutions, user corrections, workarounds)
  3. Saves patterns to ~/.claude/homunculus/instincts/personal/

Configuration

config.json in this skill directory:

{
  "min_session_length": 10,
  "extraction_threshold": "medium",
  "patterns_to_detect": [
    "error_resolution",
    "user_corrections",
    "workarounds",
    "debugging_techniques",
    "project_specific"
  ],
  "ignore_patterns": [
    "simple_typos",
    "one_time_fixes",
    "external_api_issues"
  ]
}

Pattern Types

PatternDescription
error_resolutionHow specific errors were resolved
user_correctionsPatterns from user corrections
workaroundsSolutions to framework quirks
debugging_techniquesEffective debugging approaches
project_specificProject-specific conventions

Integration with Auto-Learning

This skill feeds into the existing auto-learning system:

  • Extracted patterns become instincts in ~/.claude/homunculus/instincts/personal/
  • High-confidence instincts can evolve into skills via /idev:evolve

Anti-Patterns

  1. Do NOT extract trivial patterns (typos, one-off fixes)
  2. Do NOT extract patterns without evidence (must be observed 2+ times)
  3. Do NOT overwrite existing instincts — update confidence instead

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free