active-self-improvement

Active self-improvement loop that reads learnings, errors, batch outputs, and memory — detects patterns — and UPDATES skills/protocols/behavior automatically. Use when the agent should get smarter without being prompted. Different from passive logging — this ACTS on what it learns. Triggers after Recorder at end of sessions, after batch processing, after project milestones, on explicit "improve" or "what have we learned" prompts, or on a weekly cron schedule.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "active-self-improvement" with this command: npx skills add dodge1218/active-self-improvement

Auto-Improve

Reads logs, detects patterns, rewrites the playbook. Not passive logging — this ACTS on what it learns.

SCAN (read logs) ──► PROPOSE (specific edits) ──► APPLY (low-risk auto, high-risk flag)

Input Sources

SourceWhat It Contains
.learnings/ERRORS.mdWhat broke and how it was fixed
.learnings/LEARNINGS.mdCorrections, insights, knowledge gaps, batch outcomes
workspace/OUTSTANDING.mdRanked ideas and opportunities
memory/permanent/*.mdCurrent knowledge state
workspace/DELEGATION_PLAN.mdAtom timing data (if delegation was used)

Step 1: SCAN

Detect:

  • Repeated errors — same mistake 3+ times → needs a prevention rule
  • Repeated corrections — user keeps fixing the same thing → behavior change needed
  • Emerging patterns — 3+ items connecting → thesis forming
  • Stale knowledge — facts in permanent memory contradicted by recent sessions
  • Unused wins — high-value items that haven't been acted on

Step 2: PROPOSE

For each detected pattern:

PROPOSAL: [short title]
EVIDENCE: [file#line references]
CHANGE: [exact edit — old text → new text]
RISK: [low/medium/high]
REVERSIBLE: [yes/no]
Pattern-Key: [hash(error+fix) for dedup]
Pattern TypeActionTarget File
Repeated errorAdd prevention rulerelevant skill's ## Learned section
Repeated correctionUpdate behavior guidelineSOUL.md or AGENTS.md
Emerging thesisWrite thesis + next stepsOUTSTANDING.md
Stale knowledgeUpdate the factmemory/permanent/*.md
Unused winCreate ticket or reminderNEXT_TICKET.md or cron

Step 3: APPLY

  • Low risk + reversible: Apply immediately. Log the change.
  • Medium risk: Apply but notify user on next interaction.
  • High risk: Write to OUTSTANDING.md and wait for approval.
  • Dry-run mode (--dry-run): Propose all changes but apply none. Output a report.

Use 3-occurrence threshold before proposing pattern-based changes. Track recurrence with Pattern-Key and Recurrence-Count.

Error→Skill Feedback Loop

After SCAN, for each error in ERRORS.md:

  1. Extract the Context column value
  2. Match against skill names (fuzzy: "SiteBlitz CSS" → webdev-sop)
  3. If match found and skill doesn't already have the fix in ## Learned:
    ## Learned
    - [date] [error summary] → [fix]. Source: .learnings/ERRORS.md#L[N]
    
  4. Use Pattern-Key: hash(error+fix) to prevent duplicates

Skills self-heal: every failure improves the relevant skill.

Delegation Feedback

After delegation plan completes:

  1. Read atom timing data from DELEGATION_PLAN.md
  2. Atom actual time > 2× estimated → flag estimation drift
  3. Atom model upgraded (flash→sonnet) → update routing suggestion in MODEL_ROUTING_PROTOCOL.md
  4. Append summary to .learnings/LEARNINGS.md

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

brand-sentinel

品牌舆情哨兵:搜索公开平台的品牌相关信息,自动去重和时效过滤,输出结构化结果供 LLM 做风险分级和预警。 触发场景:监控某品牌/产品的公开舆情、搜索负面信息并按时间筛选、定时巡查品牌口碑、竞品舆情对比。 关键词:品牌监控、舆情搜索、负面信息、口碑巡查、舆情预警、品牌声誉、sentinel、舆情哨兵。 不做的事:...

Registry SourceRecently Updated
General

Linkedin Thread Engagement

Tracks your LinkedIn comments for author replies within 72h, flags high-value engagement windows, and drafts timely follow-ups to maximize thread momentum.

Registry SourceRecently Updated
General

Daily Wechat Writer

Generates and uploads daily sincere, concise WeChat articles on trending AI/human topics with matched AI images, triggered at 10 AM or on command.

Registry SourceRecently Updated
General

tiktok-android-720p

使用 ADB 自动化 TikTok 互动。支持 AI 智能评论(Claude/GPT-4/OpenRouter 视觉分析)、搜索话题、评论、点赞、收藏视频、发布内容。无需网页抓取,无 CAPTCHA,智能 UI 识别实现 100% 成功率。

Registry SourceRecently Updated