New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Openclaw Debugger

by mergisi in mergisi/awesome-openclaw-agents

Trigger when an OpenClaw agent is broken, silent, crashing, stuck, not responding, returning empty output, or the user says "my agent is down", "agent not working", "/openclaw-debugger".

MITAuto-check passed

Install Openclaw Debugger

skills CLI
$ npx skills add mergisi/awesome-openclaw-agents --skill openclaw-debugger -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mergisi/awesome-openclaw-agents openclaw-debugger --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mergisi/awesome-openclaw-agents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/claude/openclaw-debugger .claude/skills/openclaw-debugger && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
openclaw-debugger
GitHub stars
4k
Token cost
~959 tokens
SKILL.md length
395 words
Files
1
Skills in repo
16
Repo updated
First seen
Licence
MIT

At a glance

Trigger when an OpenClaw agent is broken, silent, crashing, stuck, not responding, returning empty output, or the user says "my agent is down", "agent not working", "/openclaw-debugger".

  • Works in 6 steps: Gateway health → Tail recent logs → Heartbeat status → …
  • An OpenClaw agent is broken
  • SKILL.md covers When to use, Instructions, Output format and Example invocations
  • Calls python3 and curl; needs ANTHROPIC_API_KEY

What it does

Openclaw Debugger is an agent skill from mergisi/awesome-openclaw-agents. Trigger when an OpenClaw agent is broken, silent, crashing, stuck, not responding, returning empty output, or the user says "my agent is down", "agent not working", "/openclaw-debugger". Walks through the standard OpenClaw 2026.4 diagnosis checklist and prints a report.

Its SKILL.md is about 960 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: 162 production-ready AI agent templates for OpenClaw. SOUL.md configs across 19 categories. Submit yours! The licence is MIT.

When your agent uses it

  • An OpenClaw agent is broken
  • Returning empty output
  • The user says my agent is down
  • Agent not working

Example prompts

  • “my agent is down”
  • “agent not working”
  • “/openclaw-debugger”
  • “/openclaw-debugger”

Requirements

  • Python 3
  • A credential in ANTHROPIC_API_KEY

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Gateway health
  2. Tail recent logs
  3. Heartbeat status
  4. Session file integrity
  5. Model provider reachability
  6. SOUL.md validity

What it can do on your machine

Read from SKILL.md and the folder at commit 05820c5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python3
    • curl

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • ANTHROPIC_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Openclaw Debugger loads about 959 tokens when it runs. Until then it costs about 72 tokens; SKILL.md has 395 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~72
When it runs · the whole SKILL.md, loaded when a task matches
~959

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from mergisi/awesome-openclaw-agents at commit 05820c5, republished under its MIT licence (© mergisi). 395 words, ~959 tokens.

Download SKILL.mdSave it as .claude/skills/openclaw-debugger/SKILL.md (or your agent's skills folder).
name
openclaw-debugger
description
Trigger when an OpenClaw agent is broken, silent, crashing, stuck, not responding, returning empty output, or the user says "my agent is down", "agent not working", "/openclaw-debugger". Walks through the standard OpenClaw 2026.4 diagnosis checklist and prints a report.

OpenClaw Debugger

Diagnose a broken OpenClaw agent (Orion, Echo, Radar, or any custom agent from awesome-openclaw-agents). Produces a structured diagnosis report identifying the most likely root cause.

Compatible with OpenClaw 2026.4.11 and later. For deeper reference see TROUBLESHOOTING.md in this repo.

When to use

  • Agent returns empty output or times out
  • openclaw agent --agent <name> --message "..." hangs
  • Heartbeat dashboard shows the agent as stale
  • Model provider errors (429, 401, connection refused)
  • User says "openclaw is broken" / "agent is down" / "why is Orion not replying"

Instructions

Work through the checklist in order. Stop at the first failing step and report it — no need to run later steps until that's fixed.

1. Gateway health
bash
openclaw agent --status
  • If the gateway is down, tell the user to run openclaw gateway restart.
  • If it reports "port 18789 in use by another process", find and kill the stale process (lsof -i :18789).
2. Tail recent logs
bash
tail -n 200 ~/.openclaw/logs/gateway.log
tail -n 200 ~/.openclaw/agents/<name>/logs/agent.log

Grep for ERROR, PANIC, 401, 429, timeout. The first error in the tail is usually the real cause — everything after is fallout.

3. Heartbeat status
bash
cat ~/.openclaw/agents/<name>/heartbeat.json
  • Check last_seen timestamp. More than 5 minutes old = worker crashed.
  • If status is starting for more than 60s, the agent is stuck in init (usually a bad SOUL.md or missing env var).
4. Session file integrity
bash
ls -la ~/.openclaw/agents/<name>/sessions/sessions.json
  • If the file is >5 MB, sessions may be corrupt. Back it up and delete:
    bash
    mv ~/.openclaw/agents/<name>/sessions/sessions.json{,.bak}
  • If the JSON is invalid (python3 -m json.tool < sessions.json), same fix.
Show full SKILL.md (160 more words)Show less
5. Model provider reachability

Read ~/.openclaw/agents/<name>/SOUL.md frontmatter to find the configured model and provider. Then:

  • Anthropic (Opus 4.6, Sonnet 4.6): echo $ANTHROPIC_API_KEY | head -c 10 — confirm key exists.
  • GLM-5.1 / Minimax M2.7: check ~/.openclaw/providers.json for the base URL and hit /v1/models with curl.
  • Gemma 4 local: confirm Ollama or the local runtime is up (curl localhost:11434/api/tags).

A 401 means bad key. A 429 means you're rate limited — retry with exponential backoff or switch model. Connection refused on localhost means the local runtime crashed.

6. SOUL.md validity

Read the agent's SOUL.md and check:

  • YAML frontmatter parses (must have name, model, system_prompt fields)
  • model string matches one in ~/.openclaw/providers.json
  • No lingering Turkish prompts if the agent is supposed to respond in English (per repo rules)

Output format

Print a diagnosis report like this:

OpenClaw Debugger — <agent-name>

[OK]     Gateway up (port 18789)
[OK]     Logs clean
[FAIL]   Heartbeat stale (last_seen 14 min ago)
[SKIP]   Session file
[SKIP]   Model provider
[SKIP]   SOUL.md

Root cause: worker process crashed ~14 min ago. Last log line:
  ERROR 2026-04-13T08:41:02 panic: model provider returned 401

Fix:
  1. Export a fresh ANTHROPIC_API_KEY
  2. openclaw gateway restart
  3. openclaw agent --agent <name> --message "ping"

Keep it terse. The user wants a fix, not an essay.

Example invocations

  • /openclaw-debugger orion
  • "My Echo agent is stuck — debug it"
  • "Why is openclaw agent --agent radar timing out?"

© mergisi, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/claude/openclaw-debugger of mergisi/awesome-openclaw-agents.

Open the folder on GitHubat commit 05820c5

Compare with similar skills

Openclaw Debugger next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Openclaw Debugger compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Openclaw Debugger this skillmergisi/awesome-openclaw-agents4k—~959Automated safety check: PassMIT
Debuggerdavila7/claude-code-templates32k7 repos~334Automated safety check: PassMIT
Broken Imagesthedaviddias/Front-End-Checklist74k—~728Automated safety check: PassMIT
Broken Linksthedaviddias/Front-End-Checklist74k—~412Automated safety check: PassMIT
Broken External Linksthedaviddias/Front-End-Checklist74k—~401Automated safety check: PassMIT
Broken HTMLthedaviddias/Front-End-Checklist74k—~423Automated safety check: PassMIT

Similar skills

  • Debugger

    davila7/claude-code-templates

    Debugging specialist for errors, test failures, and unexpected behavior.

    32k GitHub starsUsed in 7 repos~334 tokens
    DevelopmentAuto-check passed

  • Broken Images

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing image assets, markup, and CDN or build transforms related to Fix broken images.

    74k GitHub stars~728 tokensUpdated yesterday
    Frontend & DesignAuto-check passed

  • Broken Links

    thedaviddias/Front-End-Checklist

    A skill your agent uses when auditing metadata, crawlability, structured data, or indexability related to Resolve internal broken links.

    74k GitHub stars~412 tokensUpdated yesterday
    Marketing & SEOAuto-check passed

  • Broken External Links

    thedaviddias/Front-End-Checklist

    A skill your agent uses when auditing metadata, crawlability, structured data, or indexability related to Fix or remove broken external links.

    74k GitHub stars~401 tokensUpdated yesterday
    Marketing & SEOAuto-check passed

  • Broken HTML

    thedaviddias/Front-End-Checklist

    A skill your agent uses when auditing metadata, crawlability, structured data, or indexability related to Fix malformed HTML structure.

    74k GitHub stars~423 tokensUpdated yesterday
    Marketing & SEOAuto-check passed

  • Debug Cuda Crash

    sgl-project/sglang

    Call this skill when you need to debug CUDA crashes in SGLang using kernel API logging

    37k GitHub starsUsed in 2 repos~4.9k tokens
    AI & LLM EngineeringAuto-check passed

More from mergisi/awesome-openclaw-agents

All 16 skills in this repo

  • Claude Code Cost Optimizer

    mergisi/awesome-openclaw-agents

    Audits a project's Claude Code setup for common token-cost leaks and returns a prioritized fix list, using only static inspection of files and settings.

    4k GitHub stars~1.1k tokensUpdated 11 days ago
    Auto-check passed

  • Excalidraw Architecture Diagram

    mergisi/awesome-openclaw-agents

    Generates or updates a whiteboard-style architecture diagram of the current codebase as an Excalidraw JSON file, showing services and data flow.

    4k GitHub stars~1.1k tokensUpdated 11 days ago
    Auto-check passed

  • Git Commit Message Writer

    mergisi/awesome-openclaw-agents

    Drafts a commit message from your staged diff, matching the repo's own style and explaining why the change happened, not just what changed.

    4k GitHub stars~664 tokensUpdated 11 days ago
    Auto-check passed

  • Model Cost Compare

    mergisi/awesome-openclaw-agents

    Trigger when the user asks which model to use, wants to compare model costs, says "what's cheapest for this task", "should I use Opus or Sonnet", "can a smaller model handle this", or…

    4k GitHub stars~1k tokensUpdated 11 days ago
    Auto-check passed

  • Code Explainer

    mergisi/awesome-openclaw-agents

    Explains a pasted code snippet in plain English, returning the detected language, a one-sentence summary, how it works and one practical tip.

    4k GitHub stars~283 tokensUpdated 11 days ago
    Auto-check passed

  • Commit Message

    mergisi/awesome-openclaw-agents

    Generate a clean, conventional commit message from a description of your changes.

    4k GitHub stars~239 tokensUpdated 11 days ago
    Auto-check passed

Questions about Openclaw Debugger

What does Openclaw Debugger do?

Trigger when an OpenClaw agent is broken, silent, crashing, stuck, not responding, returning empty output, or the user says "my agent is down", "agent not working", "/openclaw-debugger". Openclaw Debugger is an agent skill from mergisi/awesome-openclaw-agents. Trigger when an OpenClaw agent is broken, silent, crashing, stuck, not responding, returning empty output, or the user says "my agent is down", "agent not working", "/openclaw-debugger".

When should I use Openclaw Debugger?

Openclaw Debugger fits situations like: an OpenClaw agent is broken; returning empty output; the user says my agent is down; agent not working.

How do I install Openclaw Debugger in Claude Code?

Run `npx skills add mergisi/awesome-openclaw-agents --skill openclaw-debugger -a claude-code`. Or copy the skill folder (skills/claude/openclaw-debugger in mergisi/awesome-openclaw-agents) into .claude/skills/openclaw-debugger in your project. Claude Code loads it when a task matches its description.

How do I install Openclaw Debugger in Codex?

Run `npx skills add mergisi/awesome-openclaw-agents --skill openclaw-debugger -a codex`. Or copy the skill folder (skills/claude/openclaw-debugger in mergisi/awesome-openclaw-agents) into .agents/skills/openclaw-debugger in your project. Codex loads it when a task matches its description.

Can I use Openclaw Debugger in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mergisi/awesome-openclaw-agents --skill openclaw-debugger -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/openclaw-debugger, .gemini/skills/openclaw-debugger, .github/skills/openclaw-debugger and .opencode/skills/openclaw-debugger in your project.

What does Openclaw Debugger need to run?

Going by SKILL.md and its folder, Openclaw Debugger needs the command-line tools its instructions call (python3 and curl) and credentials named ANTHROPIC_API_KEY. Our summary lists: Python 3; A credential in ANTHROPIC_API_KEY.

Does Openclaw Debugger access the network?

SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Openclaw Debugger safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Openclaw Debugger use?

Openclaw Debugger is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Openclaw Debugger use?

About 959 tokens (SKILL.md is roughly 3.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Openclaw Debugger?

Skills that share tags, products or a category with Openclaw Debugger: Debugger (davila7/claude-code-templates, 32k stars), Broken Images (thedaviddias/Front-End-Checklist, 74k stars), Broken Links (thedaviddias/Front-End-Checklist, 74k stars) and Broken External Links (thedaviddias/Front-End-Checklist, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Openclaw Debugger?

mergisi (a GitHub user) maintains it in mergisi/awesome-openclaw-agents, which has 3,995 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on September 26, 2026.

Source: mergisi/awesome-openclaw-agents on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.