create-template
Skill395k starsChanged todayMITView on GitHub
Turn this agent into a shareable Template for a person to review.
15 other projects use a version of this, 3 of them edited; 5 new projects in the last 4 weeks, against 0 the 4 before.
Adopted by
Surging: 5 new projects took it in the last 4 weeks, none the 4 weeks before.thin data
Most recently taken up by
- bighamx/openclaw-android-node-apkword for word, first seen Nov 9, 2026
- steipete/warelayword for word, first seen Nov 2, 2026
- moltbot/clawdbotword for word, first seen Nov 1, 2026
- lecegues/hitapply-plugintheir own version, first seen Nov 1, 2026
- moltbot/moltbotedited, first seen Nov 1, 2026
- clawdbot/clawdbotedited, first seen Nov 1, 2026
Who's talking about molt-bot/clawdbot
- deepwiki.com“Bootstrap Files | molt-bot/clawdbot | DeepWiki”the web · Mar 7, 2026
- medium.com“My First Three Days with Clawdbot (now Moltbot)”the web · Feb 20, 2026
- linkedin.com“Clawdbot Review: Powerful but Security Concerns”the web · Feb 20, 2026
- sidsaladi.substack.com“OpenClaw/Moltbot/ClawdBot 101: The Complete Guide”the web · Feb 11, 2026
- resecurity.com“Clawdbot / Moltbot: The Autonomous AI Butler That Could ...”the web · Feb 6, 2026
The biggest 5 of 18 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 18
Talked about on the web (18 times).
On the web · 18
- Mar 7, 2026Bootstrap Files | molt-bot/clawdbot | DeepWiki — deepwiki.com
- Feb 20, 2026My First Three Days with Clawdbot (now Moltbot) — medium.com
- Feb 20, 2026Clawdbot Review: Powerful but Security Concerns — linkedin.com
- Feb 11, 2026OpenClaw/Moltbot/ClawdBot 101: The Complete Guide — sidsaladi.substack.com
- Feb 6, 2026Clawdbot / Moltbot: The Autonomous AI Butler That Could ... — resecurity.com
13 more on the web
- Feb 5, 2026Is OpenClaw Worth the Hype? I Spent 10 Days Finding Out — aimaker.substack.com
- Feb 4, 2026Can someone explain OpenClaw AI (formerly Clawdbot ... — beginrescueend.com
- Feb 2, 2026Full Setup Guide Clawdbot Moltbot OpenClaw — dev.to
- Feb 1, 2026Tales from the jar side: Clawdbot née Moltbot née OpenClaw, Moltbook and emergent behavior, The Boss still rules, and the usual Social Media silliness — kenkousen.substack.com
- Feb 1, 2026One Week Later with OpenClaw (prev. ClawdBot, prev. MoltBot): A Product Designer's Honest Take — nervegna.substack.com
- Jan 31, 2026In-Depth Moltbot Analysis for AI Developers — blog.promptlayer.com
- Jan 31, 2026I Used Clawdbot (OpenClaw) for 6 Hours so You Don't Have to Buy a Mac Mini - #108 — theagilevc.substack.com
- Jan 29, 2026Moltbot Hands-On Review: A Magical AI Assistant with Serious Red Flags | by Erik.C — medium.com
- Jan 29, 2026Moltbot (formerly Clawdbot): I Put an AI Agent on My Linux Server and Gave It My WhatsApp. Here's What Happened — mvidmar.substack.com
- Jan 29, 2026Falling in and out of love with Moltbot — platformer.news
- Jan 27, 2026Build Your Own AI Assistant with Molt Bot (Clawdbot) and ... — builder.aws.com
- Jan 27, 2026I Tried OpenClaw (Moltbot/ClawdBot) for Data Engineering and Here’s the Honest Truth | by Reliable Data Engineering — medium.com
- Jan 26, 2026MoltBot (ClawdBot) Review & Setup Guide — uxwritinghub.com
Other versions15 projects use a version of this.
Word for word · 4
- steipete/warelay★ 395k100% same
- moltbot/clawdbot★ 395k100% same
- openclaw/openclaw★ 395k100% same
- bighamx/openclaw-android-node-apk★ 57100% same
Edited · 3
- steipete/clawdis★ 394k62% same
- moltbot/moltbot★ 394k62% same
- clawdbot/clawdbot★ 394k62% same
Wrote their own version · 8
- ComplianceAsCode/content★ 2.8ksame name
- harness/harness-skills★ 134same name
- brwse/earl★ 113same name
- mathematic-inc/earl★ 113same name
- GhostManager/ghostwriter-skills★ 7same name
- DemchaAV/graphcompose-ai-flow★ 4same name
- microsoft/coreai-design-system★ 2same name
- lecegues/hitapply-plugin★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository113 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- extensions/AGENTS.mdAGENTS.md
- scripts/AGENTS.mdAGENTS.md
- test/AGENTS.mdAGENTS.md
- ui/AGENTS.mdAGENTS.md
- agent-transcriptSkill
- auto-qaSkill
- autoreviewSkill
- channel-message-flowsSkill
- clawdtributorSkill
- claw-scoreSkill
- clawsweeperSkill
- control-ui-e2eSkill
- crabboxSkill
- discord-clawdSkill
- discord-e2eSkill
- discord-user-postSkill
- discrawlSkill
- gitcrawlSkill
- graincrawlSkill
- ios-e2eSkill
- labs-graduationSkill
- notcrawlSkill
- openclaw-changelog-updateSkill
- openclaw-ci-limitsSkill
- openclaw-debuggingSkill
- openclaw-docker-e2e-authoringSkill
- openclaw-ghsa-maintainerSkill
- openclaw-live-updaterSkill
- openclaw-parallels-smokeSkill
- openclaw-performanceSkill
- openclaw-pr-maintainerSkill
- openclaw-qa-testingSkill
- openclaw-refactor-docsSkill
- openclaw-release-validationSkill
- openclaw-repair-sweepSkill
- openclaw-secret-scanning-maintainerSkill
- openclaw-test-heap-leaksSkill
- openclaw-testingSkill
- openclaw-test-performanceSkill
- openclaw-updateSkill
- parallels-discord-roundtripSkill
- plugin-sdk-impactSkill
- proof-videoSkill
- prototype-openclaw-tuiSkill
- pr-simplifySkill
- release-openclaw-announcementSkill
- release-openclaw-ciSkill
- release-openclaw-macSkill
- release-openclaw-maintainerSkill
- release-openclaw-plugin-testingSkill
- security-triageSkill
- slack-e2eSkill
- slacrawlSkill
- solidSkill
- tag-duplicate-prs-issuesSkill
- technical-documentationSkill
- telegram-e2e-userbotSkill
- test-auditSkill
- The first 60 shown.
The file
Files
Create a Template
Use this skill when the person asks to create a Template from this agent, including ordinary chat requests such as “create a new template from this agent.” No sidebar action or special command is required. Stay in this conversation and use this agent's current workspace and durable instructions as source material. Prepare only a private proposal; the existing Control UI owns exact-archive review, package assembly, and explicit human publication. A request to create a Template is not permission to publish it.
Locate this SKILL.md and invoke its scripts/cli.mjs with an absolute path so commands use the running OpenClaw installation. If this turn has a request-specific workContext.detail.draftId from the optional Control UI entry, reuse it. Otherwise run node <absolute-skill-directory>/scripts/cli.mjs templates draft <absolute-current-agent-workspace> --json once and capture the returned draftId and path. Read and edit only that request's .openclaw/template-drafts/<draftId>.json. Never search for a latest draft, use a shared pointer, select a different agent, or start another conversation. Independent requests each get a new draft. If initialization has an uncertain result, inspect its recorded output before creating another draft. Keep internal paths and IDs out of your reply.
- Capture the reusable agent. Read the current draft JSON. Use this conversation and the agent's durable instructions to identify its coherent reusable role, input, job, output, and authority. Preserve useful behavior and settings; leave out personal context. If the responsibilities do not form one coherent Template, ask which responsibility to share before writing. Complete when the four scope fields describe an agent a new person can use.
- Inventory only relevant material. Select portable workspace instructions and files that implement that role. Locate this
SKILL.mdand use itsscripts/cli.mjsfor inventory so the CLI matches the running OpenClaw installation; invoke it with an absolute path when outside the skill directory. Runnode scripts/cli.mjs skills list --agent <this agent's id> --jsonandnode scripts/cli.mjs plugins list --enabled --json. Compare the results with tools actually available in this session and capabilities used in the role. Inspect a candidate withnode scripts/cli.mjs plugins inspect <id> --jsonfor its source and exact version. Declare a skill or plugin only when the role requires it. Use an exact ClawHubrefandversionwhen grounded in a current release, or apathentry for a newly authored portable skill or plugin folder included in this proposal. A bundled skill needs a rootSKILL.mdand every required supporting file; include those files under that declared folder. Do not copy an installed skill or plugin tree, dependencies, or private source material. Plugin availability alone is not a requirement. Put these dependency declarations in the top-levelskillsandpluginslists, supported native settings underagent, MCP requirements inmcpServers, and useful schedules inautomations. Referenced releases remain dependencies; declared bundled folders and their eligible supporting files go into the archive automatically. Never invent ClawHub references, versions, or verification for bundled content. Complete when every included file and declaration has a reason tied to the reusable role. - Author the proposal. Follow the draft format. Rewrite instructions for a new owner. Include input, job, output, and authority in the draft
scope, and describe the portable behavior inCLAW.md. Place only newly authored portable text infiles, mapping included workspace files bysourcein the manifest. Exclude raw conversations, memories,USER.md, credentials, secret values, private URLs, local paths, and personal facts. Never copy the source workspace tree. Complete when the JSON at this turn's draft path is valid and contains no private source material. - Hand off for review. After saving the completed proposal, call
screen(action="template_review", draftId="<this request’s draftId>"). Do not pass another session or agent: review is bound to this conversation and this agent. The native read-only review appears inline in this conversation and shows the exact built archive; the person can inspect its files and dependencies and explicitly publish there. To change the name, description, files, or dependencies, revise this request’s private proposal and call screen again for a fresh review; the preview itself does not edit or remove items. On successful handoff, end the turn with the native card alone: its description and contents provide the explanation. Do not add a heading, “Template ready for review,” a repeated summary, or a follow-up confirmation. Do not print internal paths or IDs, invent a review link, upload, invoke publication, or claim that returning the review descriptor proves the review rendered. If screen/review is unavailable (for example outside an active administrator Control UI or with Templates Lab disabled), retain the private draft and report that precise review blocker without publishing or redirecting to a different conversation. Complete when review is available to the person, or clearly report the review-delivery blocker.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

