Skill reviews

Autonomous job-market watcher for OpenClaw. On a cron schedule it monitors the career pages of companies the user has EXPLICITLY configured, judges each posting against the user's

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (12 tags): a typed call is more reliable

Replicate one agent across N clients without drift — one context source, a generator that refuses unknowns. Use when duplicating an agent deployment. Trigger on "duplicate this age

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 15 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Use when the user runs /wdp-ctx-en to save, load, verify, export, or clear the project's context so it survives session reset and can be resumed by any coding agent. English varian

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 16 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Test system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests, golden values, marker filters, and CI parity.

• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (4 tags): a typed call is more reliable
• Does not say what the result is

Skill for creating new PPTX, PDF, and PNG files with Presenton. Use this skill whenever a user asks for a PowerPoint, presentation, slide deck, pitch deck, report deck, PDF, presen

• References files that are not bundled: <preview_url>, <url>
• The skill tells the model to perform an irreversible action with no human approval
• 2 referenced file(s) missing: <preview_url>, <url>

Use when converting voice recordings, voice memos, or speech transcripts into structured Markdown notes, setting up recording-folder monitoring, or processing pending transcription

• 10 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (5 tags): a typed call is more reliable

Turn any keyword—animal, character, brand, object, or style—into a complete installable Codex pet package. Use when a user says ‘生成 Codex 宠物’, ‘做一个宠物包’, ‘Codex pet’, or provides a

• References files that are not bundled: references/layout-guides/, references/canonical-base.png, references/layout-guides/<state>.png
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 19 top-level sections: this looks like several domains in one skill

Generate multi-size SVG logos from natural-language product briefs, following Simple Icons design rules; runs an iterative generate → visual-check → optimize loop with a vision-cap

• References files that are not bundled: scripts/render_previews.py, scripts/config.json, scripts/validate_svg.py
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval

Cryptographically sign and verify AgentSkill directories using Ed25519 (RFC 8032). Publishers sign skills with a private key; recipients verify with a public key, proving the skill

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 11 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Add word-timed captions to an Open Recut program. Use this skill to map the canonical transcript through timeline.json, review a maintained style on source-backed pixels, render a

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 11 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Uploads and publishes files or static site folders to OkFile, with direct links, preview URLs, and multipart support. Use when the user asks to upload, publish, or share files or f

• References files that are not bundled: assets/app.css
• 11 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Use when comparing live MLB win probabilities with executable prediction-market prices through Simmer.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

The point-of-view content type — articulate, sharpen, and argue a genuinely-held contrarian stance / hot take / opinion / thought-leadership position that builds authority and real

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• No test case covers injection arriving through data

Use this skill when a user needs KOL or influencer research, creator email lookup, similar-creator discovery, outreach-list building, influencer prospecting, or a contact table fro

• References files that are not bundled: ../LICENSE
• The skill tells the model to perform an irreversible action with no human approval
• 1 referenced file(s) missing: ../LICENSE

Route Huoshan and Qifu knowledge requests through the default Feishu Bitable catalog, preserve entry-document and child-document relationships, and return original catalog links. U

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill ranks results itself: that belongs to the system behind the tool, not the model
• The skill tells the model to perform an irreversible action with no human approval

Invoke this skill to capture poor experiences and distill them into high-value requirements (Voice of Developer). Use when user encounters any Huawei Cloud related issues, like use

• 10 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (13 tags): a typed call is more reliable

Autonomously orchestrate the ingestion of 3rd-party data exports (e.g., Spotify, Netflix) from the Fulcra File Store into properly mapped Fulcra Annotations.

• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (4 tags): a typed call is more reliable
• Does not say what the result is

Use when your agent or environment is broken — wrong answers, errors, timeouts, tool failures, or CLI issues. Reads traces and logs to diagnose root causes. Also checks prerequisit

• References files that are not bundled: references/doctor.md, ../agents-build/references/vpc.md, ../agents-harden/references/limits.md
• 21 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Substack for AI agents. Write articles and notes, comment, follow, and message each other and the humans who run the place. Humans vouch for one agent, then watch.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Turn a supplied narration audio file plus an article, notes, screenshots, images, or source videos into a fact-checked faceless vertical teaching video, synchronized captions, cove

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Evaluates, configures, and migrates workloads to AWS Lambda Managed Instances (LMI). Runs Lambda functions on EC2 instances in the user's account while AWS manages provisioning, pa

• References files that are not bundled: references/cost-comparison.md, references/configuration-guide.md, references/thread-safety.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval

Keep an OpenClaw agent running 24/7 — loopback gateway blocks inbound webhooks, OAuth expires silently, strict config. Use when crons stop firing. Trigger on "agent went quiet".

• References files that are not bundled: scripts/secrets.env
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 14 top-level sections: this looks like several domains in one skill

Deliver local reports and artifacts through OpenClaw chat channels. Use when generated HTML/PDF/archive/table files must be sent from local, self-hosted, or WSL OpenClaw setups whe

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• Does not say what the process needs to start

LogSnag (logsnag.com). Use this skill for ANY LogSnag request — reading, creating, and updating data. Whenever a task involves LogSnag, use this skill instead of calling the API di

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Use Coil's CLI and API for agent-operated outbound recipes, durable runs, lead management, automations, provider integrations, feedback, and runtime discovery. Use when an agent ne

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• No condition that starts the skill