Chalk Labs
Need help deploying self-heal?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/zhaoxinyi02-self-heal
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
self-heal- Description
- None
- License
- MIT
- Instructions
- 210 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Agent Skills spec issues
- invalid YAML frontmatter: Nested mappings are not allowed in compact mappings at line 2, column 14:
- name: missing
- description: missing
- body: contains an absolute path from the author's machine
Files (9)
- SKILL.md
- evolve.py · scripts/
- fix_config.py · scripts/
- fix_dependency.py · scripts/
- fix_process.py · scripts/
- fix_tool.py · scripts/
- health_check.py · scripts/
- knowledge_base.json · scripts/
- verify_fix.py · scripts/
SKILL.md (first lines)
# Self Heal
## Overview
This skill enables autonomous detection, diagnosis, and recovery from operational issues. It can:
- Detect tool failures, process crashes, and configuration errors
- Automatically attempt fixes for common problems
- Learn from successful recoveries to prevent future failures
## When to Trigger
**Auto-trigger conditions:**
- Any tool call returns an error or fails
- A process is detected as crashed or unresponsive
- Configuration validation fails
- Explicit request for "self-heal", "self-repair", or "self-diagnose"
**Manual triggers:**
- "Check your health"
- "Diagnose what's wrong"
- "Recover from the error"
- "Learn from this experience"
## Workflow
```
detect_issues → analyze_root_cause → attempt_fix → verify_fix → evolve
```
---
## Step 1: Detect Issues
Run the health check script to identify problems:
```bash
python3 /home/node/clawd/skills/self-heal/scripts/health_check.py
```
This detects:
- **Tool failures** - Last N tool calls that errored
- **Process issues** - Crashed or hanging processes
- **Config problems** - Missing or invalid configuration
- **Dependency issues** - Missing packages or modules
**Output format:**
```json
{
"issues": [
{"type": "tool_failure", "tool": "exec", "error": "command not found", "severity": "high"},
{"type": "config_error", "file": "config.yaml", "error": "missing field", "severity": "medium"}
],
"health_score": 75
}
```
---
## Step 2: Analyze Root Cause
For each issue, determine the appropriate fix strategy:
| Issue Type | Fix Strategy |
|------------|--------------|
| `tool_failure` | Retry with fallback, verify tool availability |
| `process_crash` | Restart process, check logs |
| `config_error` | Repair config from backup or default |
| `dependency_missing` | Install/verify dependency |
---
## Step 3: Attempt Fix
Execute the appropriate fix script based on issue type:
### For tool failures:
```bash
python3 /home/node/clawd/skills/self-heal/scripts/fix_tool.py --tool <name> --error <error_msg>
```
### For process crashes:
```bash
python3 /home/node/clawd/skills/self-heal/scripts/fix_process.py --process <name>
```
### For config errors:
```bash
python3 /home/node/clawd/skills/self-heal/scripts/fix_config.py --file <path> --error <error_msg>
```
### For missing dependencies:
```bash
python3 /home/node/clawd/skills/self-heal/scripts/fix_dependency.py --package <name>
```
---
## Step 4: Verify Fix
After applying fixes, verify they worked:
```bash
python3 /home/node/clawd/skills/self-heal/scripts/verify_fix.py --issue-id <id>
```
If verification passes, proceed to evolve. If it fails, try an alternative fix strategy.
---
## Step 5: Evolve
Record successful fixes for future reference:
```bash
python3 /home/node/clawd/skills/self-heal/scripts/evolve.py --issue-type <type> --fix Applied --outcome success
```
This builds a knowledge base of:
- Successful fix patternsFrom zhaoxinyi02/ClawPanel-Plugins, MIT.
More from zhaoxinyi02/ClawPanel-Plugins
- 0.478score
agent-reach
zhaoxinyi02
Give your AI agent eyes to see the entire internet.
SkillDFreshness: D★ 9Claude Code +9 - 0.478score
finance-data
zhaoxinyi02
Query A/HK stock prices, financial indicators, market news, and China macroeconomic data (GDP, CPI, PMI, etc.).
SkillDFreshness: D★ 9Claude Code +9 - 0.471score
qoderwork-ppt
zhaoxinyi02
Generate QoderWork-style presentations.
SkillDFreshness: D★ 9Claude Code +9 - 0.470score
feishu-doc
zhaoxinyi02
Fetch content from Feishu (Lark) Wiki, Docs, Sheets, and Bitable.
SkillDFreshness: D★ 9Claude Code +9 - 0.453score
agent-browser
zhaoxinyi02
Browser automation CLI for AI agents.
SkillDFreshness: D★ 9Claude Code +9 - 0.449score
skill-creator
zhaoxinyi02
Create or update AgentSkills.
SkillDFreshness: D★ 9Claude Code +9 - 0.448score
find-skills
zhaoxinyi02
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express…
SkillDFreshness: D★ 9Claude Code +9 - 0.448score
pdf
zhaoxinyi02
Use this skill whenever the user wants to do anything with PDF files.
SkillDFreshness: D★ 9Claude Code +9 - 0.253score
34ai-api-suite
zhaoxinyi02
No description from the publisher yet.
SkillDFreshness: D★ 9Claude Code +9 - 0.250score
feishu-common
zhaoxinyi02
No description from the publisher yet.
SkillDFreshness: D★ 9Claude Code +9 - 0.250score
_template
zhaoxinyi02
No description from the publisher yet.
SkillDFreshness: D★ 9Claude Code +9
Signals
- Stars
- 9
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Mar 14, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/zhaoxinyi02/ClawPanel-Plugins
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from zhaoxinyi02
- 0.478score
agent-reach
zhaoxinyi02
Give your AI agent eyes to see the entire internet.
SkillDFreshness: D★ 9Claude Code +9 - 0.478score
finance-data
zhaoxinyi02
Query A/HK stock prices, financial indicators, market news, and China macroeconomic data (GDP, CPI, PMI, etc.).
SkillDFreshness: D★ 9Claude Code +9 - 0.471score
qoderwork-ppt
zhaoxinyi02
Generate QoderWork-style presentations.
SkillDFreshness: D★ 9Claude Code +9 - 0.470score
feishu-doc
zhaoxinyi02
Fetch content from Feishu (Lark) Wiki, Docs, Sheets, and Bitable.
SkillDFreshness: D★ 9Claude Code +9 - 0.453score
agent-browser
zhaoxinyi02
Browser automation CLI for AI agents.
SkillDFreshness: D★ 9Claude Code +9 - 0.449score
skill-creator
zhaoxinyi02
Create or update AgentSkills.
SkillDFreshness: D★ 9Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get self-heal running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
self-heal skill. Agent Mart. https://agentmart.dev/skills/zhaoxinyi02-self-heal (last updated 2026-10-24)