Verified Capability Evolver

“通过验证、回滚和升级门控来扩展 Capability Evolver。当代理记录学习、提出自我改进或希望将学习提升为永久记忆时使用。在升级之前，定义确定性规范，通过 SettlementWitness 验证实际输出，然后通过 → 使用收据 ID 进行提升，失败 → 回滚并记录反证据，不确定 → 保留以供审查。”验证是通过外部 SettlementWitness 服务执行的。该技能定义了验证要求和工作流程，但不嵌入 API 客户端或凭证；集成由运行时或连接的验证层处理。

## 概述（中文）

“通过验证、回滚和升级门控来扩展 Capability Evolver。当代理记录学习、提出自我改进或希望将学习提升为永久记忆时使用。在升级之前，定义确定性规范，通过 SettlementWitness 验证实际输出，然后通过 → 使用收据 ID 进行提升，失败 → 回滚并记录反证据，不确定 → 保留以供审查。”验证是通过外部 SettlementWitness 服务执行的。该技能定义了验证要求和工作流程，但不嵌入 API 客户端或凭证；集成由运行时或连接的验证层处理。

## 原文

# Verified Capability Evolver — powered by SettlementWitness

This verified version ensures every promoted learning is externally validated by SettlementWitness, preventing incorrect patterns from becoming permanent agent behavior.
Log learnings and errors for continuous improvement, but do not allow permanent self-modification unless the improvement is verified. This skill adds a verification gate before promotion to project memory, attaches SettlementWitness receipts to promoted learnings, and requires rollback when a promoted learning later fails verification.


## Core Principle

An agent should not just improve — it should **prove that it improved**.

The highest-stakes moment in self-improvement is promotion to permanent memory. A temporary fix becomes permanent behavior only after it passes verification.

## Agent Identity (Required)

All SettlementWitness verification calls must use a stable agent_id:

```text
{wallet_address}:capability-evolver
```

Use the format {wallet_address}:capability-evolver so TrustScore history compounds correctly across sessions.


## 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| Knowledge was outdated | Log to `.learnings/LEARNINGS.md` with category `knowledge_gap` |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` |
| Learning is marked `resolved` | Define verification spec before promotion |
| Promotion to permanent memory is being considered | Call SettlementWitness first |
| SettlementWitness returns PASS | Promote and attach `receipt_id` |
| SettlementWitness returns FAIL | Roll back and log counter-evidence |
| SettlementWitness returns INDETERMINATE | Hold for review, do not promote |
| 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 |
| Workflow improvements | Promote to `AGENTS.md` (OpenClaw workspace) after PASS |
| Tool gotchas | Promote to `TOOLS.md` (OpenClaw workspace) after PASS |
| Behavioral patterns | Promote to `SOUL.md` (OpenClaw workspace) after PASS |

## 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 verified-capability-evolver
```

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

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 these files into every session:

```
~/.openclaw/workspace/
├── AGENTS.md          # Multi-agent workflows, delegation patterns
├── SOUL.md            # Behavioral guidelines, personality, principles
├── TOOLS.md           # Tool capabilities, integration gotchas
├── MEMORY.md          # Long-term memory (main session only)
├── memory/            # Daily memory files
│   └── YYYY-MM-DD.md
└── .learnings/        # This skill's log files
    ├── LEARNINGS.md
    ├── ERRORS.md
    └── FEATURE_REQUESTS.md
```

### Create Learning Files

```bash
mkdir -p ~/.openclaw/workspace/.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

### Optional: Enable Hook

For automatic reminders at session start:

```bash
# Copy hook to OpenClaw hooks directory
cp -r hooks/openclaw ~/.openclaw/hooks/verified-capability-evolver

# Enable it
openclaw hooks enable verified-capability-evolver
```

See `references/openclaw-integration.md` for complete details.

---

## Generic Setup (Other Agents)

For Claude Code, Codex, Copilot, or other agents, create `.learnings/` in your project:

```bash
mkdir -p .learnings
```

Copy templates from `assets/` or create files with headers.

### Add reference to agent files AGENTS.md, CLAUDE.md, or .github/copilot-instructions.md to remind yourself to log learnings. (this is an alternative to hook-based reminders)

#### Self-Improvement Workflow

When errors or corrections occur:
1. Log to `.learnings/ERRORS.md`, `LEARNINGS.md`, or `FEATURE_REQUESTS.md`
2. Review and promote broadly applicable learnings to:
   - `CLAUDE.md` - project facts and conventions
   - `AGENTS.md` - workflows and automation
   - `.github/copilot-instructions.md` - Copilot context

## 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

### 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: