openclaw-node-harness 2.0.0

package/skills/self-improving-agent/SKILL.md

@@ -0,0 +1,130 @@
+---
+name: self-improvement
+description: "Captures learnings, errors, and corrections to enable continuous improvement. Use when a command fails, user corrects the agent, a capability is missing, or a better approach is discovered. Also reviews learnings before major tasks."
+triggers:
+  - "log this as a learning"
+  - "save this error"
+  - "that's wrong, actually"
+  - "remember this for next time"
+  - "check learnings before starting"
+negative_triggers:
+  - "improve the UI"
+  - "optimize performance"
+  - "refactor this code"
+---
+
+# 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.
+
+## 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+| Knowledge was outdated | Log to `.learnings/LEARNINGS.md` with category `knowledge_gap` |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` |
+| Similar to existing entry | Link with `**See Also**`, consider priority bump |
+| Broadly applicable learning | Promote to `CLAUDE.md`, `AGENTS.md`, and/or `.github/copilot-instructions.md` |
+| 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
+```
+
+### 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/self-improvement
+
+# Enable it
+openclaw hooks enable self-improvement
+```
+
+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.
+
+## Templates, Formats & Extended Reference
+
+See [references/templates.md](references/templates.md) for templates and detailed examples.
+
+Covers: logging format (learning/error/feature entries), ID generation, resolving entries, promoting to project memory, recurring pattern detection, periodic review, detection triggers, priority guidelines, area tags, best practices, gitignore options, hook integration, automatic skill extraction, and multi-agent support.

package/skills/self-improving-agent/assets/LEARNINGS.md

@@ -0,0 +1,45 @@
+# Learnings
+
+Corrections, insights, and knowledge gaps captured during development.
+
+**Categories**: correction | insight | knowledge_gap | best_practice
+**Areas**: frontend | backend | infra | tests | docs | config
+**Statuses**: pending | in_progress | resolved | wont_fix | promoted | promoted_to_skill
+
+## Status Definitions
+
+| Status | Meaning |
+|--------|---------|
+| `pending` | Not yet addressed |
+| `in_progress` | Actively being worked on |
+| `resolved` | Issue fixed or knowledge integrated |
+| `wont_fix` | Decided not to address (reason in Resolution) |
+| `promoted` | Elevated to CLAUDE.md, AGENTS.md, or copilot-instructions.md |
+| `promoted_to_skill` | Extracted as a reusable skill |
+
+## Skill Extraction Fields
+
+When a learning is promoted to a skill, add these fields:
+
+```markdown
+**Status**: promoted_to_skill
+**Skill-Path**: skills/skill-name
+```
+
+Example:
+```markdown
+## [LRN-20250115-001] best_practice
+
+**Logged**: 2025-01-15T10:00:00Z
+**Priority**: high
+**Status**: promoted_to_skill
+**Skill-Path**: skills/docker-m1-fixes
+**Area**: infra
+
+### Summary
+Docker build fails on Apple Silicon due to platform mismatch
+...
+```
+
+---
+

package/skills/self-improving-agent/assets/SKILL-TEMPLATE.md

@@ -0,0 +1,177 @@
+# Skill Template
+
+Template for creating skills extracted from learnings. Copy and customize.
+
+---
+
+## SKILL.md Template
+
+```markdown
+---
+name: skill-name-here
+description: "Concise description of when and why to use this skill. Include trigger conditions."
+---
+
+# Skill Name
+
+Brief introduction explaining the problem this skill solves and its origin.
+
+## Quick Reference
+
+| Situation | Action |
+|-----------|--------|
+| [Trigger 1] | [Action 1] |
+| [Trigger 2] | [Action 2] |
+
+## Background
+
+Why this knowledge matters. What problems it prevents. Context from the original learning.
+
+## Solution
+
+### Step-by-Step
+
+1. First step with code or command
+2. Second step
+3. Verification step
+
+### Code Example
+
+\`\`\`language
+// Example code demonstrating the solution
+\`\`\`
+
+## Common Variations
+
+- **Variation A**: Description and how to handle
+- **Variation B**: Description and how to handle
+
+## Gotchas
+
+- Warning or common mistake #1
+- Warning or common mistake #2
+
+## Related
+
+- Link to related documentation
+- Link to related skill
+
+## Source
+
+Extracted from learning entry.
+- **Learning ID**: LRN-YYYYMMDD-XXX
+- **Original Category**: correction | insight | knowledge_gap | best_practice
+- **Extraction Date**: YYYY-MM-DD
+```
+
+---
+
+## Minimal Template
+
+For simple skills that don't need all sections:
+
+```markdown
+---
+name: skill-name-here
+description: "What this skill does and when to use it."
+---
+
+# Skill Name
+
+[Problem statement in one sentence]
+
+## Solution
+
+[Direct solution with code/commands]
+
+## Source
+
+- Learning ID: LRN-YYYYMMDD-XXX
+```
+
+---
+
+## Template with Scripts
+
+For skills that include executable helpers:
+
+```markdown
+---
+name: skill-name-here
+description: "What this skill does and when to use it."
+---
+
+# Skill Name
+
+[Introduction]
+
+## Quick Reference
+
+| Command | Purpose |
+|---------|---------|
+| `./scripts/helper.sh` | [What it does] |
+| `./scripts/validate.sh` | [What it does] |
+
+## Usage
+
+### Automated (Recommended)
+
+\`\`\`bash
+./skills/skill-name/scripts/helper.sh [args]
+\`\`\`
+
+### Manual Steps
+
+1. Step one
+2. Step two
+
+## Scripts
+
+| Script | Description |
+|--------|-------------|
+| `scripts/helper.sh` | Main utility |
+| `scripts/validate.sh` | Validation checker |
+
+## Source
+
+- Learning ID: LRN-YYYYMMDD-XXX
+```
+
+---
+
+## Naming Conventions
+
+- **Skill name**: lowercase, hyphens for spaces
+  - Good: `docker-m1-fixes`, `api-timeout-patterns`
+  - Bad: `Docker_M1_Fixes`, `APITimeoutPatterns`
+
+- **Description**: Start with action verb, mention trigger
+  - Good: "Handles Docker build failures on Apple Silicon. Use when builds fail with platform mismatch."
+  - Bad: "Docker stuff"
+
+- **Files**:
+  - `SKILL.md` - Required, main documentation
+  - `scripts/` - Optional, executable code
+  - `references/` - Optional, detailed docs
+  - `assets/` - Optional, templates
+
+---
+
+## Extraction Checklist
+
+Before creating a skill from a learning:
+
+- [ ] Learning is verified (status: resolved)
+- [ ] Solution is broadly applicable (not one-off)
+- [ ] Content is complete (has all needed context)
+- [ ] Name follows conventions
+- [ ] Description is concise but informative
+- [ ] Quick Reference table is actionable
+- [ ] Code examples are tested
+- [ ] Source learning ID is recorded
+
+After creating:
+
+- [ ] Update original learning with `promoted_to_skill` status
+- [ ] Add `Skill-Path: skills/skill-name` to learning metadata
+- [ ] Test skill by reading it in a fresh session

package/skills/self-improving-agent/hooks/openclaw/HOOK.md

@@ -0,0 +1,23 @@
+---
+name: self-improvement
+description: "Injects self-improvement reminder during agent bootstrap"
+metadata: {"openclaw":{"emoji":"🧠","events":["agent:bootstrap"]}}
+---
+
+# Self-Improvement Hook
+
+Injects a reminder to evaluate learnings during agent bootstrap.
+
+## What It Does
+
+- Fires on `agent:bootstrap` (before workspace files are injected)
+- Adds a reminder block to check `.learnings/` for relevant entries
+- Prompts the agent to log corrections, errors, and discoveries
+
+## Configuration
+
+No configuration needed. Enable with:
+
+```bash
+openclaw hooks enable self-improvement
+```

package/skills/self-improving-agent/hooks/openclaw/handler.js

@@ -0,0 +1,56 @@
+/**
+ * Self-Improvement Hook for OpenClaw
+ * 
+ * Injects a reminder to evaluate learnings during agent bootstrap.
+ * Fires on agent:bootstrap event before workspace files are injected.
+ */
+
+const REMINDER_CONTENT = `
+## Self-Improvement Reminder
+
+After completing tasks, evaluate if any learnings should be captured:
+
+**Log when:**
+- User corrects you → \`.learnings/LEARNINGS.md\`
+- Command/operation fails → \`.learnings/ERRORS.md\`
+- User wants missing capability → \`.learnings/FEATURE_REQUESTS.md\`
+- You discover your knowledge was wrong → \`.learnings/LEARNINGS.md\`
+- You find a better approach → \`.learnings/LEARNINGS.md\`
+
+**Promote when pattern is proven:**
+- Behavioral patterns → \`SOUL.md\`
+- Workflow improvements → \`AGENTS.md\`
+- Tool gotchas → \`TOOLS.md\`
+
+Keep entries simple: date, title, what happened, what to do differently.
+`.trim();
+
+const handler = async (event) => {
+  // Safety checks for event structure
+  if (!event || typeof event !== 'object') {
+    return;
+  }
+
+  // Only handle agent:bootstrap events
+  if (event.type !== 'agent' || event.action !== 'bootstrap') {
+    return;
+  }
+
+  // Safety check for context
+  if (!event.context || typeof event.context !== 'object') {
+    return;
+  }
+
+  // Inject the reminder as a virtual bootstrap file
+  // Check that bootstrapFiles is an array before pushing
+  if (Array.isArray(event.context.bootstrapFiles)) {
+    event.context.bootstrapFiles.push({
+      path: 'SELF_IMPROVEMENT_REMINDER.md',
+      content: REMINDER_CONTENT,
+      virtual: true,
+    });
+  }
+};
+
+module.exports = handler;
+module.exports.default = handler;

package/skills/self-improving-agent/hooks/openclaw/handler.ts

@@ -0,0 +1,62 @@
+/**
+ * Self-Improvement Hook for OpenClaw
+ * 
+ * Injects a reminder to evaluate learnings during agent bootstrap.
+ * Fires on agent:bootstrap event before workspace files are injected.
+ */
+
+import type { HookHandler } from 'openclaw/hooks';
+
+const REMINDER_CONTENT = `## Self-Improvement Reminder
+
+After completing tasks, evaluate if any learnings should be captured:
+
+**Log when:**
+- User corrects you → \`.learnings/LEARNINGS.md\`
+- Command/operation fails → \`.learnings/ERRORS.md\`
+- User wants missing capability → \`.learnings/FEATURE_REQUESTS.md\`
+- You discover your knowledge was wrong → \`.learnings/LEARNINGS.md\`
+- You find a better approach → \`.learnings/LEARNINGS.md\`
+
+**Promote when pattern is proven:**
+- Behavioral patterns → \`SOUL.md\`
+- Workflow improvements → \`AGENTS.md\`
+- Tool gotchas → \`TOOLS.md\`
+
+Keep entries simple: date, title, what happened, what to do differently.`;
+
+const handler: HookHandler = async (event) => {
+  // Safety checks for event structure
+  if (!event || typeof event !== 'object') {
+    return;
+  }
+
+  // Only handle agent:bootstrap events
+  if (event.type !== 'agent' || event.action !== 'bootstrap') {
+    return;
+  }
+
+  // Safety check for context
+  if (!event.context || typeof event.context !== 'object') {
+    return;
+  }
+
+  // Skip sub-agent sessions to avoid bootstrap issues
+  // Sub-agents have sessionKey patterns like "agent:main:subagent:..."
+  const sessionKey = event.sessionKey || '';
+  if (sessionKey.includes(':subagent:')) {
+    return;
+  }
+
+  // Inject the reminder as a virtual bootstrap file
+  // Check that bootstrapFiles is an array before pushing
+  if (Array.isArray(event.context.bootstrapFiles)) {
+    event.context.bootstrapFiles.push({
+      path: 'SELF_IMPROVEMENT_REMINDER.md',
+      content: REMINDER_CONTENT,
+      virtual: true,
+    });
+  }
+};
+
+export default handler;