Agent skill

Continuous Learning

by affaan-m in affaan-m/ECC

Claude Codeセッションから再利用可能なパターンを自動的に抽出し、将来の使用のために学習済みスキルとして保存します。

MITAuto-check passed

Install Continuous Learning

skills CLI
$ npx skills add affaan-m/ECC --skill continuous-learning -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install affaan-m/ECC continuous-learning --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/affaan-m/ECC.git skills-src && mkdir -p .claude/skills && cp -r skills-src/docs/ja-JP/skills/continuous-learning .claude/skills/continuous-learning && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
continuous-learning
GitHub stars
276k
Used in
2 other repos
Token cost
~587 tokens
SKILL.md length
97 words
Files
1
Skills in repo
673
Repo updated
First seen
Licence
MIT

At a glance

Claude Codeセッションから再利用可能なパターンを自動的に抽出し、将来の使用のために学習済みスキルとして保存します。

  • Works in 3 steps: セッション評価: セッションに十分なメッセージがあるか確認(デフォルト: 10以上) → パターン検出: セッションから抽出可能なパターンを識別 → スキル抽出:…
  • SKILL.md covers 動作原理, 設定, パターンの種類 and フック設定, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Continuous Learning is an agent skill from affaan-m/ECC. Claude Codeセッションから再利用可能なパターンを自動的に抽出し、将来の使用のために学習済みスキルとして保存します。

Its SKILL.md is about 590 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond. The licence is MIT.

Example prompts

  • “/continuous-learning”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. セッション評価: セッションに十分なメッセージがあるか確認(デフォルト: 10以上)
  2. パターン検出: セッションから抽出可能なパターンを識別
  3. スキル抽出: 有用なパターンを~/.claude/skills/learned/に保存

What it can do on your machine

Read from SKILL.md and the folder at commit ef648e0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • x.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Continuous Learning loads about 587 tokens when it runs. Until then it costs about 21 tokens; SKILL.md has 97 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~21
When it runs · the whole SKILL.md, loaded when a task matches
~587

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from affaan-m/ECC at commit ef648e0, republished under its MIT licence (© affaan-m). 97 words, ~587 tokens.

Download SKILL.mdSave it as .claude/skills/continuous-learning/SKILL.md (or your agent's skills folder).
name
continuous-learning
description
Claude Codeセッションから再利用可能なパターンを自動的に抽出し、将来の使用のために学習済みスキルとして保存します。

継続学習スキル

Claude Codeセッションを終了時に自動的に評価し、学習済みスキルとして保存できる再利用可能なパターンを抽出します。

動作原理

このスキルは各セッション終了時にStopフックとして実行されます:

  1. セッション評価: セッションに十分なメッセージがあるか確認(デフォルト: 10以上)
  2. パターン検出: セッションから抽出可能なパターンを識別
  3. スキル抽出: 有用なパターンを~/.claude/skills/learned/に保存

設定

config.jsonを編集してカスタマイズ:

json
{
  "min_session_length": 10,
  "extraction_threshold": "medium",
  "auto_approve": false,
  "learned_skills_path": "~/.claude/skills/learned/",
  "patterns_to_detect": [
    "error_resolution",
    "user_corrections",
    "workarounds",
    "debugging_techniques",
    "project_specific"
  ],
  "ignore_patterns": [
    "simple_typos",
    "one_time_fixes",
    "external_api_issues"
  ]
}

パターンの種類

パターン説明
error_resolution特定のエラーの解決方法
user_correctionsユーザー修正からのパターン
workaroundsフレームワーク/ライブラリの癖への解決策
debugging_techniques効果的なデバッグアプローチ
project_specificプロジェクト固有の規約

フック設定

~/.claude/settings.jsonに追加:

json
{
  "hooks": {
    "Stop": [{
      "matcher": "*",
      "hooks": [{
        "type": "command",
        "command": "~/.claude/skills/continuous-learning/evaluate-session.sh"
      }]
    }]
  }
}

Stopフックを使用する理由

  • 軽量: セッション終了時に1回だけ実行
  • ノンブロッキング: すべてのメッセージにレイテンシを追加しない
  • 完全なコンテキスト: セッション全体のトランスクリプトにアクセス可能

関連項目

  • The Longform Guide - 継続学習に関するセクション
  • /learnコマンド - セッション中の手動パターン抽出

比較ノート (調査: 2025年1月)

vs Homunculus

Homunculus v2はより洗練されたアプローチを採用:

機能このアプローチHomunculus v2
観察Stopフック(セッション終了時)PreToolUse/PostToolUseフック(100%信頼性)
分析メインコンテキストバックグラウンドエージェント(Haiku)
粒度完全なスキル原子的な「本能」
信頼度なし0.3-0.9の重み付け
進化直接スキルへ本能 → クラスタ → スキル/コマンド/エージェント
共有なし本能のエクスポート/インポート

homunculusからの重要な洞察:

"v1はスキルに観察を依存していました。スキルは確率的で、発火率は約50-80%です。v2は観察にフック(100%信頼性)を使用し、学習された振る舞いの原子単位として本能を使用します。"

v2の潜在的な改善
  1. 本能ベースの学習 - 信頼度スコアリングを持つ、より小さく原子的な振る舞い
  2. バックグラウンド観察者 - 並行して分析するHaikuエージェント
  3. 信頼度の減衰 - 矛盾した場合に本能の信頼度が低下
  4. ドメインタグ付け - コードスタイル、テスト、git、デバッグなど
  5. 進化パス - 関連する本能をスキル/コマンドにクラスタ化

詳細: docs/continuous-learning-v2-spec.mdを参照。

© affaan-m, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in docs/ja-JP/skills/continuous-learning of affaan-m/ECC.

Open the folder on GitHubat commit ef648e0

Used in 2 other repositories

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in affaan-m/ECC, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Continuous Learning next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Continuous Learning compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Continuous Learning this skillaffaan-m/ECC276k2 repos~587Automated safety check: PassMIT
Continuousaiblueprinthq/ai-blueprint463—~4.7kAutomated safety check: PassMIT
Continuetelegramdesktop/tdesktop33k2 repos~9.4kAutomated safety check: PassGPL-3.0
Continuityparcadei/Continuous-Claude-v33.9k1 repos~292Automated safety check: NotesMIT
Continueudecode/plate17k—~2.6kAutomated safety check: PassCustom licence
Continue PRClickHouse/ClickHouse50k—~5.5kAutomated safety check: NotesApache-2.0

Similar skills

  • Continuous

    aiblueprinthq/ai-blueprint

    Build every remaining planned feature serially in explicit Continuous Mode, with one local branch, verification cycle, commit, archive, and local merge per feature.

    463 GitHub stars~4.7k tokensUpdated today
    Auto-check passed
  • Continue

    telegramdesktop/tdesktop

    Continue autonomous Telegram Desktop development from the shared ai-tdesktop repository.

    33k GitHub starsUsed in 2 repos~9.4k tokens
    Productivity & AutomationAuto-check passed
  • Continuity

    parcadei/Continuous-Claude-v3

    Problem-solving strategies for continuity in real analysis. An agent skill from parcadei/Continuous-Claude-v3.

    3.9k GitHub starsUsed in 1 repo~292 tokens
    Research & ScienceAuto-check: notes
  • Continue

    udecode/plate

    Use after an execution slice to reassess whether the current tactic still serves the user's north star, then keep course, pivot, replan, or stop.

    17k GitHub stars~2.6k tokensUpdated today
    Auto-check passed
  • Continue PR

    ClickHouse/ClickHouse

    Continue work on an existing PR - resolve conflicts, fix CI failures, address reviewer feedback, and push updates.

    50k GitHub stars~5.5k tokensUpdated today
    DevelopmentAuto-check: notes
  • Continue PR Auto

    ClickHouse/ClickHouse

    Unattended variant of continue-pr for automation (driven by utils/continue-all-prs.sh).

    50k GitHub stars~8.6k tokensUpdated today
    DatabasesAuto-check: notes

More from affaan-m/ECC

All 673 skills in this repo
  • Skill Stocktake

    affaan-m/ECC

    Audits your installed Claude skills and commands for quality, with a quick mode for recently changed skills and a full mode that evaluates all of them through subagents.

    276k GitHub starsUsed in 5 repos~1.9k tokens
    Auto-check passed
  • Ingests, indexes, searches, edits and monitors video, audio and live streams through the VideoDB Python SDK, returning stream links, clips and timestamps.

    276k GitHub starsUsed in 3 repos~3.5k tokens
    Auto-check: notes
  • Rules Distillation

    affaan-m/ECC

    Scans installed skills for principles that recur across them and proposes rule-file changes: append, revise, add a section, create a file or leave as covered.

    276k GitHub starsUsed in 2 repos~2.3k tokens
    Auto-check passed
  • Builds DRAFT counterparty agreements from one markdown template and a small JSON spec per party, with clauses picked by the party's role.

    276k GitHub stars~2.9k tokensUpdated 4 days ago
    Auto-check passed
  • Measures whether agents actually follow a skill, rule or agent definition by generating scenarios at three strictness levels and scoring tool-call traces.

    276k GitHub starsUsed in 1 repo~623 tokens
    Auto-check passed
  • Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.

    276k GitHub stars~3.5k tokensUpdated 4 days ago
    Auto-check passed

Questions about Continuous Learning

What does Continuous Learning do?

Claude Codeセッションから再利用可能なパターンを自動的に抽出し、将来の使用のために学習済みスキルとして保存します。. Continuous Learning is an agent skill from affaan-m/ECC.

How do I install Continuous Learning in Claude Code?

Run `npx skills add affaan-m/ECC --skill continuous-learning -a claude-code`. Or copy the skill folder (docs/ja-JP/skills/continuous-learning in affaan-m/ECC) into .claude/skills/continuous-learning in your project. Claude Code loads it when a task matches its description.

How do I install Continuous Learning in Codex?

Run `npx skills add affaan-m/ECC --skill continuous-learning -a codex`. Or copy the skill folder (docs/ja-JP/skills/continuous-learning in affaan-m/ECC) into .agents/skills/continuous-learning in your project. Codex loads it when a task matches its description.

Can I use Continuous Learning in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add affaan-m/ECC --skill continuous-learning -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/continuous-learning, .gemini/skills/continuous-learning, .github/skills/continuous-learning and .opencode/skills/continuous-learning in your project.

What does Continuous Learning need to run?

SKILL.md names no scripts, command-line tools or credentials: Continuous Learning is instructions for the agent only.

Does Continuous Learning access the network?

SKILL.md names 1 domain. As links in the text: x.com. This is read from the text; nothing was executed.

Is Continuous Learning safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Continuous Learning use?

Continuous Learning is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Continuous Learning use?

About 587 tokens (SKILL.md is roughly 2.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Continuous Learning?

Skills that share tags, products or a category with Continuous Learning: Continuous (aiblueprinthq/ai-blueprint, 463 stars), Continue (telegramdesktop/tdesktop, 33k stars), Continuity (parcadei/Continuous-Claude-v3, 3.9k stars) and Continue (udecode/plate, 17k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Continuous Learning?

affaan-m (a GitHub user) maintains it in affaan-m/ECC, which has 275,546 GitHub stars. The repository holds 673 skills in this directory. The repository was last updated on October 5, 2026.

Source: affaan-m/ECC on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.