自我提升

工程开发 社区

技能解读

当前原文的自动摘译,尚未人工审校。

首次使用初始化

在记录任何内容之前,请确保项目或工作区根目录中存在.learnings/目录和文件。如果缺少任何文件,请创建它们:切勿覆盖现有文件。如果 .learnings/ 已经初始化,则这是一个空操作。不要记录机密、令牌、私钥、环境变量或完整源/配置文件,除非用户明确要求提供该级别的详细信息。与原始命令输出或完整记录相比,更喜欢简短的摘要或经过编辑的摘录。

快速参考

情况 · 操作命令/操作失败 · 记录到 .learnings/ERRORS.md 用户纠正您 · 记录到 .learnings/LEARNINGS.md,类别为 correction 用户想要缺少的功能 · 记录到 .learnings/FEATURE_REQUESTS.md API/外部工具失败 · 记录到 .learnings/ERRORS.md 并包含集成详细信息

OpenClaw 设置(推荐)

OpenClaw 是这项技能的主要平台。它使用基于工作区的提示注入和自动技能加载。

安装

通过 ClawdHub(推荐):手册:从原始存储库为 openclaw 重制:https://github.com/pskoett/pskoett-ai-skills - https://github.com/pskoett/pskoett-ai-skills/tree/main/skills/self-improvement

工作区结构

OpenClaw 从代理的工作区注入文件(每个代理都有自己的树)。示例:在您正在运行的工作区(不是单个共享文件夹)内的.learnings/中记录学习内容。

流狐档案 运行与权限由流狐静态检查推断,不代表作者声明或实际测试结果。
领域
工程开发
作者声明的智能体
未找到明确声明;不据此推断已兼容或已测试
静态检查
88 / 100 · 启发式扫描,不代表运行安全
运行环境证据
未执行;当前没有隔离运行测试证据
作者 / 版本 / 许可证
@00Blacksheep00 · 未声明许可证
上下文用量评级
中等消耗
接入复杂程度
需手动接入
是否需要外部接口密钥
不需要
兼容的系统
Docker
运行环境要求
Docker
检测到的文件与系统行为
  • 只读
  • 允许写入 / 修改
  • 命令执行
  • 读取环境变量
网络行为
仅限本地
安装命令数
无(仅作为资料)

需要注意: 未声明工具权限范围;实际权限由运行环境决定。

作者说明文件(原文) SKILL.md

# Self-Improvement Skill

Log learnings and errors to markdown files for continuous improvement. Coding agents can later process these into fixes, and important learnings get promoted to project memory.

## First-Use Initialisation

Before logging anything, ensure the `.learnings/` directory and files exist in the project or workspace root. If any are missing, create them:

```bash
mkdir -p .learnings
[ -f .learnings/LEARNINGS.md ] || printf "# Learnings\n\nCorrections, insights, and knowledge gaps captured during development.\n\n**Categories**: correction | insight | knowledge_gap | best_practice\n\n---\n" > .learnings/LEARNINGS.md
[ -f .learnings/ERRORS.md ] || printf "# Errors\n\nCommand failures and integration errors.\n\n---\n" > .learnings/ERRORS.md
[ -f .learnings/FEATURE_REQUESTS.md ] || printf "# Feature Requests\n\nCapabilities requested by the user.\n\n---\n" > .learnings/FEATURE_REQUESTS.md
```

Never overwrite existing files. This is a no-op if `.learnings/` is already initialised.

Do not log secrets, tokens, private keys, environment variables, or full source/config files unless the user explicitly asks for that level of detail. Prefer short summaries or redacted excerpts over raw command output or full transcripts.

If you want automatic reminders or setup assistance, use the opt-in hook workflow described in [Hook Integration](#hook-integration).

## Quick Reference

| Situation | Action |
|-----------|--------|
| Command/operation fails | Log to `.learnings/ERRORS.md` |
| User corrects you | Log to `.learnings/LEARNINGS.md` with category `correction` |
| User wants missing feature | Log to `.learnings/FEATURE_REQUESTS.md` |
| API/external tool fails | Log to `.learnings/ERRORS.md` with integration details |
| Knowledge was outdated | Log to `.learnings/LEARNINGS.md` with category `knowledge_gap` |
| Found better approach | Log to `.learnings/LEARNINGS.md` with category `best_practice` |
| Simplify/Harden recurring patterns | Log/update `.learnings/LEARNINGS.md` with `Source: simplify-and-harden` and a stable `Pattern-Key` |
| Similar to existing entry | Link with `**See Also**`, consider priority bump |
| Broadly applicable learning | Promote to `AGENTS.md`, `SOUL.md`, `TOOLS.md`, or `MEMORY.md` (OpenClaw); in repo generici anche `.github/copilot-instructions.md` se lo usi |
| Workflow improvements | Promote to `AGENTS.md` (OpenClaw workspace) |
| Tool gotchas | Promote to `TOOLS.md` (OpenClaw workspace) |
| Behavioral patterns | Promote to `SOUL.md` (OpenClaw workspace) |

## OpenClaw Setup (Recommended)

OpenClaw is the primary platform for this skill. It uses workspace-based prompt injection with automatic skill loading.

### Installation

**Via ClawdHub (recommended):**
```bash
clawdhub install self-improving-agent
```

**Manual:**
```bash
git clone https://github.com/peterskoett/self-improving-agent.git ~/.openclaw/skills/self-improving-agent
```

Remade for openclaw from original repo : https://github.com/pskoett/pskoett-ai-skills - https://github.com/pskoett/pskoett-ai-skills/tree/main/skills/self-improvement

### Workspace Structure

OpenClaw injects files from **the agent’s workspace** (each agent has its own tree). Example:

```
~/.openclaw/workspace/              # White (default)
├── AGENTS.md
├── SOUL.md
├── TOOLS.md
├── MEMORY.md
├── memory/
│   └── YYYY-MM-DD.md
└── .learnings/                     # White — do not share with other agents
    ├── LEARNINGS.md
    ├── ERRORS.md
    └── FEATURE_REQUESTS.md

~/.openclaw/workspace-zero/         # Zero — same layout, own .learnings/
~/.openclaw/workspace-wolf/        # Wolf — same layout, own .learnings/
```

Log learnings in **`.learnings/` inside the workspace you are running in** (not a single shared folder).

### Create Learning Files

```bash
mkdir -p ~/.openclaw/workspace/.learnings
mkdir -p ~/.openclaw/workspace-zero/.learnings
mkdir -p ~/.openclaw/workspace-wolf/.learnings
```

Then create the log files (or copy from `assets/`):
- `LEARNINGS.md` — corrections, knowledge gaps, best practices
- `ERRORS.md` — command failures, exceptions
- `FEATURE_REQUESTS.md` — user-requested capabilities

### Promotion Targets

When learnings prove broadly applicable, promote them to workspace files:

| Learning Type | Promote To | Example |
|---------------|------------|---------|
| Behavioral patterns | `SOUL.md` | "Be concise, avoid disclaimers" |
| Workflow improvements | `AGENTS.md` | "Spawn sub-agents for long tasks" |
| Tool gotchas | `TOOLS.md` | "Git push needs auth configured first" |

### Inter-Session Communication

OpenClaw provides tools to share learnings across sessions:

- **sessions_list** — View active/recent sessions
- **sessions_history** — Read another session's transcript  
- **sessions_send** — Send a learning to another session
- **sessions_spawn** — Spawn a sub-agent for background work

Use these only in trusted environments and only when the user explicitly wants cross-session sharing. Prefer sending a short sanitized summary and relevant file paths, not raw transcripts, secrets, or full command output.

### Integration with Ralph (anti-loop)

If the task was executed under **ralph-router** plus **ralph-small**, **ralph-medium**, or **ralph-huge**, each of those skills ends with **Closure: self-improvement**: after **verified** success, evaluate a short entry in `.learnings/` or promotion to `TOOLS.md` / `AGENTS.md`, and skill extraction only when this skill’s criteria (or the user) say so. Hooks cannot detect “Ralph finished”; this closure is the reliable trigger.

### Optional: Enable Hook

Istruzioni aggiornate (copia file, `openclaw hooks`, riavvio gateway): [references/openclaw-integration.md](references/openclaw-integration.md).

---

## Altri contesti (non OpenClaw)

Se l’agente lavora in un **repo Git normale** senza workspace OpenClaw: crea `.learnings/` nella root del progetto come in [First-Use Initialisation](#first-use-initialisation). Promuovi i learning nei file di contesto che **quel** flusso legge (es. `AGENTS.md`, README, istruzioni team) — non mescolare con i path sotto `~/.openclaw/workspace/`.

## Logging Format

### Learning Entry

Append to `.learnings/LEARNINGS.md`:

```markdown
## [LRN-YYYYMMDD-XXX] category

**Logged**: ISO-8601 timestamp
**Priority**: low | medium | high | critical
**Status**: pending
**Area**: frontend | backend | infra | tests | docs | config

### Summary
One-line description of what was learned

### Details
Full context: what happened, what was wrong, what's correct

### Suggested Action
Specific fix or improvement to make

### Metadata
- Source: conversation | error | user_feedback
- Related Files: path/to/file.ext
- Tags: tag1, tag2
- See Also: LRN-20250110-001 (if related to existing entry)
- Pattern-Key: simplify.dead_code | harden.input_validation (optional, for recurring-pattern tracking)
- Recurrence-Count: 1 (optional)
- First-Seen: 2025-01-15 (optional)
- Last-Seen: 2025-01-15 (optional)

---
```

### Error Entry

Append to `.learnings/ERRORS.md`:

```markdown
## [ERR-YYYYMMDD-XXX] skill_or_command_name

**Logged**: ISO-8601 timestamp
**Priority**: high
**Status**: pending
**Area**: frontend | backend | infra | tests | docs | config

### Summary
Brief description of what failed

### Error
```
Actual error message or output
```

### Context
- Command/operation attempted
- Input or parameters used
- Environment details if relevant
- Summary or redacted excerpt of relevant output (avoid full transcripts and secret-bearing data by default)

### Suggested Fix
If identifiable, what might resolve this

### Metadata
- Reproducible: yes | no | unknown
- Related Files: path/to/file.ext
- See Also: ERR-20250110-001 (if recurring)

---
```

### Feature Request Entry

Append to `.learnings/FEATURE_REQUESTS.md`:

```markdown
## [FEAT-YYYYMMDD-XXX] capability_name

**Logged**: ISO-8601 timestamp
**Priority**: medium
**Status**: pending
**Area**: frontend | backend | infra | tests | docs | config

### Requested Capability
What the user wanted to do

### User Context
Why they needed it, what problem they're solving

### Complexity Estimate
simple | medium | complex

### Suggested Implementation
How this could be built, what it might extend

### Metadata
- Frequency: first_time | recurring
- Related Features: existing_feature_name

---
```

## ID Generation

Format: `TYPE-YYYYMMDD-XXX`
- TYPE: `LRN` (learning), `ERR` (error), `FEAT` (feature)
- YYYYMMDD: Current date
- XXX: Sequential number or random 3 chars (e.g., `001`, `A7B`)

Examples: `LRN-20250115-001`, `ERR-20250115-A3F`, `FEAT-20250115-002`

## Resolving Entries

When an issue is fixed, update the entry:

1. Change `**Status**: pending` → `**Status**: resolved`
2. Add resolution block after Metadata:

```markdown
### Resolution
- **Resolved**: 2025-01-16T09:00:00Z
- **Commit/PR**: abc123 or #42
- **Notes**: Brief description of what was done
```

Other status values:
- `in_progress` - Actively being worked on
- `wont_fix` - Decided not to address (add reason in Resolution notes)
- `promoted` - Elevated to workspace memory (`AGENTS.md`, `SOUL.md`, `TOOLS.md`, …) or altri file di contesto del progetto

## Promoting to Project Memory

When a learning is broadly applicable (not a one-off fix), promote it to permanent project memory.

### When to Promote

- Learning applies across multiple files/features
- Knowledge any contributor (human or AI) should know
- Prevents recurring mistakes
- Documents project-specific conventions

### Promotion Targets

| Target | What Belongs There |
|--------|-------------------|
| `AGENTS.md` | Procedure operative, workflow, regole runtime (OpenClaw o repo) |
| `SOUL.md` | Comportamento, stile, anti-pattern (OpenClaw workspace) |
| `TOOLS.md` | Integrazioni, path, comandi, limiti tool (OpenClaw workspace) |
| `MEMORY.md` | Memoria curata a lungo termine (OpenClaw, sessione principale) |
| `.github/copilot-instructions.md` | Solo se usi Copilot in quel repo |

### How to Promote

1. **Distill** the learning into a concise rule or fact
2. **Add** to appropriate section in target file (create file if needed)
3. **Update** original entry:
   - Change `**Status**: pending` → `**Status**: promoted`
   - Add `**Promoted**:` con il file usato (es. `AGENTS.md`, `TOOLS.md`)

### Promotion Examples

**Learning** (verbose):
> Project uses pnpm workspaces. Attempted `npm install` but failed. 
> Lock file is `pnpm-lock.yaml`. Must use `pnpm install`.

**In AGENTS.md o README di progetto** (conciso):
```markdown
## Build & Dependencies
- Package manager: pnpm (not npm) - use `pnpm install`
```

**Learning** (verbose):
> When modifying API endpoints, must regenerate TypeScript client.
> Forgetting this causes type mismatches at runtime.

**In AGENTS.md** (actionable):
```markdown
## After API Changes
1. Regenerate client: `pnpm run generate:api`
2. Check for type errors: `pnpm tsc --noEmit`
```

## Recurring Pattern Detection

If logging something similar to an existing entry:

1. **Search first**: `grep -r "keyword" .learnings/`
2. **Link entries**: Add `**See Also**: ERR-20250110-001` in Metadata
3. **Bump priority** if issue keeps recurring
4. **Consider systemic fix**: Recurring issues often indicate:
   - Missing documentation (→ promuovi in `AGENTS.md`, `TOOLS.md`, o istruzioni repo)
   - Missing automation (→ add to AGENTS.md)
   - Architectural problem (→ create tech debt ticket)

## Simplify & Harden Feed

Use this workflow to ingest recurring patterns from the `simplify-and-harden`
skill and turn them into durable prompt guidance.

### Ingestion Workflow

1. Read `simplify_and_harden.learning_loop.candidates` from the task summary.
2. For each candidate, use `pattern_key` as the stable dedupe key.
3. Search `.learnings/LEARNINGS.md` for an existing entry with that key:
   - `grep -n "Pattern-Key: <pattern_key>" .learnings/LEARNINGS.md`
4. If found:
   - Increment `Recurrence-Count`
   - Update `Last-Seen`
   - Add `See Also` links to related entries/tasks
5. If not found:
   - Create a new `LRN-...` entry
   - Set `Source: simplify-and-harden`
   - Set `Pattern-Key`, `Recurrence-Count: 1`, and `First-Seen`/`Last-Seen`

### Promotion Rule (System Prompt Feedback)

Promote recurring patterns into agent context/system prompt files when all are true:

- `Recurrence-Count >= 3`
- Seen across at least 2 distinct tasks
- Occurred within a 30-day window

Promotion targets (OpenClaw prima):
- `AGENTS.md`, `SOUL.md`, `TOOLS.md`, `MEMORY.md`
- `.github/copilot-instructions.md` solo se usi Copilot in quel repo

Write promoted rules as short prevention rules (what to do before/while coding),
not long incident write-ups.

## Periodic Review

Review `.learnings/` at natural breakpoints:

### When to Review
- Before starting a new major task
- After completing a feature
- When working in an area with past learnings
- Weekly during active development

### Quick Status Check
```bash
# Count pending items
grep -h "Status\*\*: pending" .learnings/*.md | wc -l

# List pending high-priority items
grep -B5 "Priority\*\*: high" .learnings/*.md | grep "^## \["

# Find learnings for a specific area
grep -l "Area\*\*: backend" .learnings/*.md
```

### Review Actions
- Resolve fixed items
- Promote applicable learnings
- Link related entries
- Escalate recurring issues

## Detection Triggers

Automatically log when you notice:

**Corrections** (→ learning with `correction` category):
- "No, that's not right..."
- "Actually, it should be..."
- "You're wrong about..."
- "That's outdated..."

**Feature Requests** (→ feature request):
- "Can you also..."
- "I wish you could..."
- "Is there a way to..."
- "Why can't you..."

**Knowledge Gaps** (→ learning with `knowledge_gap` category):
- User provides information you didn't know
- Documentation you referenced is outdated
- API behavior differs from your understanding

**Errors** (→ error entry):
- Command returns non-zero exit code
- Exception or stack trace
- Unexpected output or behavior
- Timeout or connection failure

## Priority Guidelines

| Priority | When to Use |
|----------|-------------|
| `critical` | Blocks core functionality, data loss risk, security issue |
| `high` | Significant impact, affects common workflows, recurring issue |
| `medium` | Moderate impact, workaround exists |
| `low` | Minor inconvenience, edge case, nice-to-have |

## Area Tags

Use to filter learnings by codebase region:

| Area | Scope |
|------|-------|
| `frontend` | UI, components, client-side code |
| `backend` | API, services, server-side code |
| `infra` | CI/CD, deployment, Docker, cloud |
| `tests` | Test files, testing utilities, coverage |
| `docs` | Documentation, comments, READMEs |
| `config` | Configuration files, environment, settings |

## Best Practices

1. **Log immediately** - context is freshest right after the issue
2. **Be specific** - future agents need to understand quickly
3. **Include reproduction steps** - especially for errors
4. **Link related files** - makes fixes easier
5. **Suggest concrete fixes** - not just "investigate"
6. **Use consistent categories** - enables filtering
7. **Promote aggressively** - if in doubt, add to `AGENTS.md` or `TOOLS.md` (OpenClaw) o al file di contesto del repo
8. **Review regularly** - stale learnings lose value

## Gitignore Options

**Keep learnings local** (per-developer):
```gitignore
.learnings/
```

This repo uses that default to avoid committing sensitive or noisy local logs by accident.

**Track learnings in repo** (team-wide):
Don't add to .gitignore - learnings become shared knowledge.

**Hybrid** (track templates, ignore entries):
```gitignore
.learnings/*.md
!.learnings/.gitkeep
```

## Hook Integration

**OpenClaw (gateway):** hook gestito in `~/.openclaw/hooks/self-improvement/` (`HOOK.md` + `handler.js`), evento `before_prompt_build`. Richiede `hooks.internal.enabled` e riavvio gateway dopo modifiche. Dettagli: [references/openclaw-integration.md](references/openclaw-integration.md).

**Script in `scripts/` (`activator.sh`, `error-detector.sh`):** opzionali; servono solo se usi un **altro client** che espone hook da shell (es. prompt-submit / post-tool). Su OpenClaw con l’hook gateway **non servono**. Non documentiamo qui JSON di altri editor per evitare confusione con OpenClaw.

## Automatic Skill Extraction

When a learning is valuable enough to become a reusable skill, extract it using the provided helper.

### Skill Extraction Criteria

A learning qualifies for skill extraction when ANY of these apply:

| Criterion | Description |
|-----------|-------------|
| **Recurring** | Has `See Also` links to 2+ similar issues |
| **Verified** | Status is `resolved` with working fix |
| **Non-obvious** | Required actual debugging/investigation to discover |
| **Broadly applicable** | Not project-specific; useful across codebases |
| **User-flagged** | User says "save this as a skill" or similar |

### Extraction Workflow

1. **Identify candidate**: Learning meets extraction criteria
2. **Run helper** (or create manually):
   ```bash
   ./skills/self-improvement/scripts/extract-skill.sh skill-name --dry-run
   ./skills/self-improvement/scripts/extract-skill.sh skill-name
   ```
3. **Customize SKILL.md**: Fill in template with learning content
4. **Update learning**: Set status to `promoted_to_skill`, add `Skill-Path`
5. **Verify**: Read skill in fresh session to ensure it's self-contained

### Manual Extraction

If you prefer manual creation:

1. Create `skills/<skill-name>/SKILL.md`
2. Use template from `assets/SKILL-TEMPLATE.md`
3. Follow [Agent Skills spec](https://agentskills.io/specification):
   - YAML frontmatter with `name` and `description`
   - Name must match folder name
   - No README.md inside skill folder

### Extraction Detection Triggers

Watch for these signals that a learning should become a skill:

**In conversation:**
- "Save this as a skill"
- "I keep running into this"
- "This would be useful for other projects"
- "Remember this pattern"

**In learning entries:**
- Multiple `See Also` links (recurring issue)
- High priority + resolved status
- Category: `best_practice` with broad applicability
- User feedback praising the solution

### Skill Quality Gates

Before extraction, verify:

- [ ] Solution is tested and working
- [ ] Description is clear without original context
- [ ] Code examples are self-contained
- [ ] No project-specific hardcoded values
- [ ] Follows skill naming conventions (lowercase, hyphens)

## Quando applicare (qualsiasi agente)

1. **Discover something non-obvious** — la soluzione non era immediata  
2. **Correct yourself** — l’approccio iniziale era sbagliato  
3. **Learn project conventions** — pattern non documentati  
4. **Hit unexpected errors** — soprattutto se la diagnosi è stata difficile  
5. **Find better approaches** — miglior rispetto alla prima ipotesi  

Su **OpenClaw**: contesto da workspace (`AGENTS.md`, …), hook opzionale, tool tra sessioni come in [Inter-Session Communication](#inter-session-communication).

讨论

基于 GitHub Discussions。登录 GitHub 即可参与讨论、点赞、订阅更新。