Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

OpenClaw Documentation Expert · jdrhyne | DecimalAI

jdrhyne/clawddocs

SkillScore95Maintained

OpenClaw documentation expert with decision tree navigation, search scripts, doc fetching, version tracking, and config snippets for all OpenClaw features

Documentationby jdrhyne

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Doc Ops pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/jdrhyne-clawddocs/SKILL.md

decimalai skills pull jdrhyne-clawddocs --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/jdrhyne-clawddocs/SKILL.md https://app.decimal.ai/s/jdrhyne-clawddocs/SKILL.md

Raw file: /s/jdrhyne-clawddocs/SKILL.md ↗ · machine-readable summary at /s/jdrhyne-clawddocs.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 34d ago

—+26% tokens0% turns95% of whole cases pass with skill (21/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	82%	0%
case-03	✗→✓	▲ Improved	27%	0%
case-06	✗→✓	▲ Improved	31%	0%
case-07	✗→✓	▲ Improved	47%	0%
case-08	✗→✓	▲ Improved	25%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

jdrhyne / agent-skills

clawdbot/clawddocs/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1Bundled 7 files · scripts

Skill contents

scripts/

SKILL.md

OpenClaw Documentation Expert

Capability Summary: OpenClaw documentation expert skill with decision tree navigation, search scripts (sitemap, keyword, full-text index via qmd), doc fetching, version tracking, and config snippets for all OpenClaw features (providers, gateway, automation, platforms, tools).

You are an expert on OpenClaw documentation. Use this skill to help users navigate, understand, and configure OpenClaw.

Quick Start

"When a user asks about OpenClaw, first identify what they need:"

🎯 Decision Tree

"How do I set up X?" → Check providers/ or start/
Discord, Telegram, WhatsApp, etc. → providers/<name>
First time? → start/getting-started, start/setup

"Why isn't X working?" → Check troubleshooting
General issues → debugging, gateway/troubleshooting
Provider-specific → providers/troubleshooting
Browser tool → tools/browser-linux-troubleshooting

"How do I configure X?" → Check gateway/ or concepts/
Main config → gateway/configuration, gateway/configuration-examples
Specific features → relevant concepts/ page

"What is X?" → Check concepts/
Architecture, sessions, queues, models, etc.

"How do I automate X?" → Check automation/
Scheduled tasks → automation/cron-jobs
Webhooks → automation/webhook
Gmail → automation/gmail-pubsub

"How do I install/deploy?" → Check install/ or platforms/
Docker → install/docker
Linux server → platforms/linux
macOS app → platforms/macos

Available Scripts

All scripts are in ./scripts/:

Core

bash
./scripts/sitemap.sh # Show all docs by category
./scripts/cache.sh status # Check cache status
./scripts/cache.sh refresh # Force refresh sitemap

Search & Discovery

bash
./scripts/search.sh discord # Find docs by keyword
./scripts/recent.sh 7 # Docs updated in last N days
./scripts/fetch-doc.sh gateway/configuration # Get specific doc

Full-Text Index (requires qmd)

bash
./scripts/build-index.sh fetch # Download all docs
./scripts/build-index.sh build # Build search index
./scripts/build-index.sh search "webhook retry" # Semantic search

Version Tracking

bash
./scripts/track-changes.sh snapshot # Save current state
./scripts/track-changes.sh list # Show snapshots
./scripts/track-changes.sh since 2026-01-01 # Show changes

Documentation Categories

🚀 Getting Started (`/start/`)

First-time setup, onboarding, FAQ, wizard

🔧 Gateway & Operations (`/gateway/`)

Configuration, security, health, logging, tailscale, troubleshooting

💬 Providers (`/providers/`)

Discord, Telegram, WhatsApp, Slack, Signal, iMessage, MS Teams

🧠 Core Concepts (`/concepts/`)

Agent, sessions, messages, models, queues, streaming, system-prompt

🛠️ Tools (`/tools/`)

Bash, browser, skills, reactions, subagents, thinking

⚡ Automation (`/automation/`)

Cron jobs, webhooks, polling, Gmail pub/sub

💻 CLI (`/cli/`)

Gateway, message, sandbox, update commands

📱 Platforms (`/platforms/`)

macOS, Linux, Windows, iOS, Android, Hetzner

📡 Nodes (`/nodes/`)

Camera, audio, images, location, voice

🌐 Web (`/web/`)

Webchat, dashboard, control UI

📦 Install (`/install/`)

Docker, Ansible, Bun, Nix, updating

📚 Reference (`/reference/`)

Templates, RPC, device models

Config Snippets

See ./snippets/common-configs.md for ready-to-use configuration patterns:

Provider setup (Discord, Telegram, WhatsApp, etc.)
Gateway configuration
Agent defaults
Retry settings
Cron jobs
Skills configuration

Workflow

Identify the need using the decision tree above
Search "if unsure: ./scripts/search.sh <keyword>"
Fetch the doc: ./scripts/fetch-doc.sh <path> or use browser
Reference snippets for config examples
Cite the source URL when answering

Tips

Always use cached sitemap when possible (1-hour TTL)
For complex questions, search the full-text index
Check recent.sh to see what's been updated
Offer specific config snippets from snippets/
Link to docs: https://docs.openclaw.ai/<path>

Example Interactions

User: "How do I make my bot only respond when mentioned in Discord?"

You:

Fetch providers/discord doc
Find the requireMention setting
Provide the config snippet:

json
{
  "discord": {
    "guilds": {
      "*": {
        "requireMention": true
      }
    }
  }
}

Link: https://docs.openclaw.ai/providers/discord

User: "What's new in the docs?"

You:

Run ./scripts/recent.sh 7
Summarize recently updated pages
Offer to dive into any specific updates

Illustrative Want to see what jdrhyne/clawddocs would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Latest benchmark · publisher runVerified

8/24/2026, 15:08 UTC · 22 cases

Measured on 21 comparable cases — below the 22 needed to publish a lift, so this result is shown here but not on the registry card or leaderboard.

Lift

+68%

95% vs 27%

Agent turns

1.0 vs 1.0

Tokens

+26%

2,159.57 vs 1,714

fail → pass · 15pass → pass · 6fail → fail · 1

Per-case results (22)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-01 I am setting up a Telegram bot with OpenClaw and want to ensure it only listens in specific allowed groups. Can you check the documentation for this provider, show me the exact JSON configuration format to restrict access, and cite the source documentation link?	fail→pass	11,163	14,122	+27%	1	1	0%	1,755	3,200	+82%	0	0	—
case-02 I want to see what documentation pages for OpenClaw have been updated over the past week. Please inspect recent modifications, summarize the main updates grouped by category, and list the relevant reference links.	fail→fail	11,020	7,576	-31%	1	1	0%	1,810	1,587	-12%	0	0	—
case-03 My OpenClaw gateway is throwing errors when trying to set up scheduled background tasks. Could you consult the OpenClaw troubleshooting and automation guides to explain why this might fail, provide an example configuration snippet for cron tasks, and give me links to the underlying docs?	fail→pass	14,379	10,631	-26%	1	1	0%	2,383	3,038	+27%	0	0	—
case-04 I just downloaded OpenClaw for the first time and need to know where to begin setting up my environment from scratch. Which path in the documentation structure handles initial onboarding?	pass→pass	8,641	3,378	-61%	1	1	0%	1,340	1,815	+35%	0	0	—
case-05 I want my OpenClaw Discord bot to respond strictly when a user explicitly mentions it in a guild, ignoring general channel chatter. What JSON field controls this behavior?	pass→pass	6,497	3,807	-41%	1	1	0%	909	1,904	+109%	0	0	—
case-06 I am deploying OpenClaw as a containerized service. What is the specific path in the documentation tree for container setup instructions?	fail→pass	8,963	2,605	-71%	1	1	0%	1,300	1,700	+31%	0	0	—
case-07 I need a complete high-level overview of all available OpenClaw documentation pages listed by category. What shell command executes this lookup using local tooling?	fail→pass	9,333	3,823	-59%	1	1	0%	1,375	2,019	+47%	0	0	—
case-08 I want to perform a semantic search across all local OpenClaw documentation for 'webhook retry'. Which script command handles semantic search queries?	fail→pass	9,123	2,751	-70%	1	1	0%	1,385	1,736	+25%	0	0	—
case-09 The OpenClaw browser automation tool is crashing during headless rendering on my Linux host. Which specific troubleshooting documentation path addresses headless browser failures on Linux?	fail→pass	12,234	3,539	-71%	1	1	0%	1,958	1,855	-5%	0	0	—
case-10 I need to review all changes made to OpenClaw documentation pages since January 1st, 2026. What change-tracking script command displays modifications since a given date?	fail→pass	6,893	2,919	-58%	1	1	0%	1,101	1,746	+59%	0	0	—
case-11 I need to set up push notifications from Google email accounts to trigger OpenClaw workflows. What documentation section covers this integration?	fail→pass	8,573	4,406	-49%	1	1	0%	1,251	2,035	+63%	0	0	—
case-12 Where in the OpenClaw documentation hub can I find complete full-file examples for main gateway settings rather than isolated parameters?	fail→pass	8,977	4,105	-54%	1	1	0%	1,203	1,855	+54%	0	0	—
case-13 How can I check whether the locally cached OpenClaw documentation sitemap is current or expired before running search queries?	fail→pass	14,054	3,118	-78%	1	1	0%	2,483	1,749	-30%	0	0	—
case-14 I need to quickly search all OpenClaw documentation titles for references to 'discord' without running a full vector indexing build. Which script handles fast keyword matching?	fail→pass	8,704	2,986	-66%	1	1	0%	1,394	1,760	+26%	0	0	—
case-15 I know the exact doc path I want to read is `gateway/configuration`. Which local helper script retrieves the content of this file directly?	fail→pass	9,460	1,563	-83%	1	1	0%	1,585	1,537	-3%	0	0	—
case-16 What documentation section details platform-specific installation steps for running the OpenClaw desktop app on macOS?	fail→pass	6,891	3,124	-55%	1	1	0%	1,107	1,740	+57%	0	0	—
case-17 I want to configure incoming HTTP webhooks to trigger OpenClaw actions. What documentation route explains incoming webhook routing?	pass→pass	12,405	4,267	-66%	1	1	0%	1,874	1,997	+7%	0	0	—
case-18 Where can I find pre-built, reusable configuration snippet patterns for common OpenClaw tasks like retry settings and provider defaults?	fail→pass	12,801	3,641	-72%	1	1	0%	2,215	1,904	-14%	0	0	—
case-19 What is the standard URL pattern for linking directly to an OpenClaw core concept page like `concepts/architecture`?	fail→pass	8,742	1,991	-77%	1	1	0%	1,375	1,589	+16%	0	0	—
case-20 I am developing a custom C++ native module for the OpenClaw gateway binary to implement a custom compression algorithm. How do I write the memory management logic for this C++ extension?	pass→pass	19,864	18,071	-9%	1	1	0%	3,421	4,411	+29%	0	0	—
case-21 I need to configure my Linux firewall iptables rules directly on my host machine to drop incoming packets on port 8080 before they reach my reverse proxy. What iptables commands should I run?	pass→pass	11,736	5,563	-53%	1	1	0%	2,008	2,264	+13%	0	0	—
case-22 I am designing a brand logo and vector color palette for a new chat bot application. What design principles should I follow for choosing accessible color contrasts?	pass→pass	17,713	14,634	-17%	1	1	0%	2,572	3,497	+36%	0	0	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 21 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +68 percentage points is the difference between those two pass rates over the 21 comparable cases.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 27.3%
Pass rate with the skill: 95.5%
Cases attempted: 22
Cases counted toward lift: 21
Cases that regressed: 0
Skill version measured: v1
Run completed: 8/24/2026, 15:08 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-01

Prompt

I am setting up a Telegram bot with OpenClaw and want to ensure it only listens in specific allowed groups. Can you check the documentation for this provider, show me the exact JSON configuration format to restrict access, and cite the source documentation link?

Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.

Show both answers

SkillScore blends 4 signals1 of 4 complete

BenchmarkPass rate WITH skill on a verified run95

Live evalNeeds ≥10 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

Efficiency · separate axis (at equal correctness)+0% turns+31% tokens

Shown for transparency; not credited unless a verified run shows no correctness regression.

Backed by 1 of 4 signals — each added signal makes the score more robust.

Verified on gemini-3.6-flash · re-tested 34 days ago

Other measured skills in the registry, with their headline benchmark lift.