Agent Skills › poteto/noodle › ruminate

ruminate

GitHub

该技能用于挖掘历史对话记录,提取未被捕获的模式、纠正措施和知识。通过读取大脑快照、定位并提取Claude与Codex会话,并行分析用户修正、偏好及技术经验,最终整合到知识库中。

.agents/skills/ruminate/SKILL.md poteto/noodle

触发场景

ruminate mine my history what have I been working on review past sessions extract learnings

安装

npx skills add poteto/noodle --skill ruminate -g -y
更多选项

非标准路径

npx skills add https://github.com/poteto/noodle/tree/main/.agents/skills/ruminate -g -y

不安装直接使用

npx skills use poteto/noodle@ruminate

指定 Agent (Claude Code)

npx skills add poteto/noodle --skill ruminate -a claude-code -g -y

安装 repo 全部 skill

npx skills add poteto/noodle --all -g -y

预览 repo 内 skill

npx skills add poteto/noodle --list

SKILL.md

Frontmatter
{
    "name": "ruminate",
    "description": "Mine past Claude Code and Codex conversations for uncaptured patterns, corrections, and knowledge. Cross-references with existing brain content. Triggers: \"ruminate\", \"mine my history\", \"what have I been working on\", \"review past sessions\", \"extract learnings\"."
}

Ruminate

Mine conversation history for brain-worthy knowledge that was never captured. Complements reflect (current session) and meditate (brain vault audit) by looking at the full archive of past conversations across both providers.

Process

Use Tasks to track progress. Create a task for each step below (TaskCreate), mark each in_progress when starting and completed when done (TaskUpdate). Check TaskList after each step.

1. Read the brain

Build a brain snapshot: sh .claude/skills/meditate/scripts/snapshot.sh brain/ /tmp/brain-snapshot-ruminate.md. Pass the snapshot path to each analysis agent. This avoids loading the full brain into the ruminate orchestrator's context.

2. Locate conversations

Find both provider roots:

  1. Claude project directory: ~/.claude/projects/-<cwd-with-dashes-replacing-slashes>/
  2. Codex sessions root: ~/.codex/sessions/

For example, /Users/lauren/code/noodle maps to ~/.claude/projects/-Users-lauren-code-noodle/ for Claude and uses ~/.codex/sessions/ for Codex.

3. Extract conversations

Run the extraction script to parse both JSONL formats into readable text and split into batches:

SKILL_DIR="$(dirname "$(realpath "$0")")/.."  # adjust path as needed
CLAUDE_DIR="$HOME/.claude/projects/-<project-slug>"
CODEX_DIR="$HOME/.codex/sessions"
OUT_DIR="/tmp/ruminate-$(date +%s)"

python3 "$SKILL_DIR/scripts/extract-conversations.py" "$OUT_DIR" \
  --claude-dir "$CLAUDE_DIR" \
  --codex-dir "$CODEX_DIR" \
  --cwd "$PWD" \
  --batches N

Choose N based on total extracted conversations (Claude + Codex): ~1 batch per 20 conversations, minimum 2, maximum 10.

4. Spawn analysis team

Create an agent team (TeamCreate) with N agents (one per batch, matching the batch count from step 3), each with subagent_type: general-purpose and model: opus. Run all N in parallel.

Each agent's prompt should include:

  • The batch manifest path ($OUT_DIR/batches/batch_N.txt)
  • The output path ($OUT_DIR/findings_N.md)
  • The list of topics already captured in the brain (compiled from step 1) — so agents skip known knowledge
  • A reminder that each extracted file includes provider/source metadata headers ([PROVIDER], [CWD], [SOURCE_FILE]) and should be used as evidence context
  • Instructions to extract from each conversation:
    • User corrections: times the user corrected the assistant's approach, code, or understanding
    • Recurring preferences: things the user explicitly asked for or pushed back on repeatedly
    • Technical learnings: codebase-specific knowledge, gotchas, patterns discovered
    • Workflow patterns: how the user prefers to work
    • Frustrations: friction points, wasted effort, things that went wrong
    • Skills wished for: capabilities the user expressed wanting

Agents write structured findings to their output files.

5. Synthesize

After all agents complete, read all findings files. Cross-reference with existing brain content. Deduplicate across batches.

Filter by frequency and impact. Most findings won't be worth adding. Apply these filters before presenting:

  • Frequency: Did this come up in multiple conversations, or was the user correcting the same mistake repeatedly? One-off corrections are usually not worth a brain entry — the brain should capture patterns, not incidents.
  • Factual accuracy: Is something in the brain now wrong? (e.g. a rule was disabled but the brain still documents it as active). These are always worth fixing regardless of frequency.
  • Impact: Would failing to capture this cause repeated wasted effort in future sessions? A gotcha that cost 5 minutes once is low-impact. A pattern that caused 3 rounds of corrections is high-impact.

Discard aggressively. It's better to present 3 high-signal findings than 9 that include noise. If a finding only happened once and isn't a factual correction, skip it.

6. Present and apply

Present findings to the user in a table with columns: finding, frequency/evidence, and proposed action. Be honest about which findings are one-offs vs. recurring patterns — let the user decide what's worth adding.

Route skill-specific learnings. Check if any findings are about how a specific skill should work — its process, prompts, edge cases, or troubleshooting. Update the skill's SKILL.md or references/ directly. Read the skill first to avoid duplicating or contradicting existing content.

Apply only the changes the user approves. Follow brain writing conventions:

  • One topic per file, organized in directories
  • Use [[wikilinks]] to connect related notes
  • Update brain/index.md after all changes
  • Default to updating existing notes over creating new ones

7. Clean up

Remove the temporary extraction directory:

rm -rf "$OUT_DIR"

Guidelines

  • Filter aggressively. Most conversations will have low signal — automated tasks, trivial exchanges, already-captured knowledge. Only surface what's genuinely new and impactful.
  • Prefer reduction. If a finding is a special case of an existing brain principle, update the existing note rather than creating a new one.
  • Quote the user. When a finding stems from a direct user correction, include the user's words and source file path — they carry the most signal about what matters.
  • Shut down agents when analysis is complete. Don't leave them idle.

版本历史

  • 82d2921 当前 2026-11-19 21:08

同 Skill 集合

.agents/skills/adversarial-review/SKILL.md
.agents/skills/ast-grep/SKILL.md
.agents/skills/brain/SKILL.md
.agents/skills/codex/SKILL.md
.agents/skills/commit/SKILL.md
.agents/skills/debugging/SKILL.md
.agents/skills/execute/SKILL.md
.agents/skills/find-skills/SKILL.md
.agents/skills/frontend-design/SKILL.md
.agents/skills/go-best-practices/SKILL.md
.agents/skills/interaction-design/SKILL.md
.agents/skills/make-interfaces-feel-better/SKILL.md
.agents/skills/meditate/SKILL.md
.agents/skills/noodle/SKILL.md
.agents/skills/oops/SKILL.md
.agents/skills/plan/SKILL.md
.agents/skills/quality/SKILL.md
.agents/skills/react-best-practices/SKILL.md
.agents/skills/refine/SKILL.md
.agents/skills/reflect/SKILL.md
.agents/skills/review/SKILL.md
.agents/skills/schedule/SKILL.md
.agents/skills/skill-creator/SKILL.md
.agents/skills/testing/SKILL.md
.agents/skills/todo/SKILL.md
.agents/skills/unslop/SKILL.md
.agents/skills/worktree/SKILL.md
examples/minimal/.agents/skills/execute/SKILL.md
examples/minimal/.agents/skills/schedule/SKILL.md
examples/multi-skill/.agents/skills/execute/SKILL.md
examples/multi-skill/.agents/skills/schedule/SKILL.md
skills/skill-creator/SKILL.md
.agents/skills/ts-best-practices/SKILL.md
examples/multi-skill/.agents/skills/deploy/SKILL.md
examples/multi-skill/.agents/skills/test/SKILL.md

元信息

文件数
0
版本
82d2921
Hash
948821ca
收录时间
2026-11-19 21:08

首页 - Wiki
Copyright © 2011-2026 iteam. Current version is 2.156.0. UTC+08:00, 2026-11-20 05:29
浙ICP备14020137号-1