Skill reviews

Publish HTML to a private, unguessable link your human can open in any browser — no account for the viewer, passcode optional. Built for the pages a personal agent produces: a morn

• 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

Hand a fresh Linux server to an AI and get back a running Kannaka node. Given an IP or hostname and SSH access, the agent checks the box, installs the signed Kannaka release, write

• 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

Accidental ClawHub publish or leaked package files: scope, remove, and verify one affected version.

• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (10 tags): a typed call is more reliable
• Does not say what the result is

Review the quality, reproducibility, legal reasoning, and decision usefulness of an existing freedom-to-operate (FTO), patent-infringement-risk, or event IP risk report. Use for th

• References files that are not bundled: assets/fto_report.css, assets/harness_report.css
• 20 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

Render comparison tables a human reads at a glance instead of parsing — colour and bar length carry the comparison, text only confirms it. Use whenever you are about to present sev

• The skill tells the model to perform an irreversible action with no human approval
• Prose only: no discrete steps
• Does not say what the result is

Knowledge base from 'Agorism in the 21st Century: A Philosophical Journal Vol. 3 — Network States' (2024) ed. Dylan-Ennis & O'Leary. Use when applying logic-of-violence forecasting

• References files that are not bundled: references/chapters/ch00-introduction.md, references/chapters/ch01-promethean-network-state.md, references/chapters/ch02-black-flag-white-paper.md
• The skill tells the model to perform an irreversible action with no human approval
• 10 referenced file(s) missing: references/chapters/ch00-introduction.md, references/chapters/ch01-promethean-network-state.md, references/chapters/ch02-black-flag-white-paper.md

Update SenseNova Skills (the sn-* bundle) inside an OpenClaw or hermes-agent install. ALWAYS use this skill when the user says any of: "update SenseNova skills", "update SN skills"

• 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 (8 tags): a typed call is more reliable

Huawei Cloud CloudDeploy (CodeArts Deploy / 部署) management, execution, and failure analysis using the KooCLI hcloud command-line client. Covers deploy application listing and creat

• 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 (7 tags): a typed call is more reliable

Discover locally running HTTP interfaces, identify their listening ports and processes, and build a browsable launcher dashboard. Use when the user asks what web apps, dashboards,

• 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

Waffo Pancake (waffo.ai). Use this skill for ANY Waffo Pancake request — reading, creating, and updating data. Whenever a task involves Waffo Pancake, use this skill instead of cal

• 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

Set up server side conversion tracking for ad platforms (Google Ads, Meta, ChatGPT, LinkedIn, TikTok and more) without writing tracking code. Use this whenever the user wants to tr

• 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 (9 tags): a typed call is more reliable

Gate Simmer/Polymarket tennis market entries on the live match state (score, who is serving, break-point flag, retirement/walkover/suspension) from the Live Tennis API. Observe-onl

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

Investigate an Alibaba Cloud AccessKey (AK) leakage incident and produce a read-only investigation report. Use when the user reports a leaked / exposed / stolen / compromised Aliba

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

Use when about to claim anything works, is fixed, is complete, or passes - before committing, replying to the user, or moving to the next task. Also use when relaying a subagent's

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Free image hosting with albums, privacy controls, and API access. Upload images by URL or file, organize into albums with folders, set privacy levels, and manage your hosted images

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 12 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

Publishes a validated GTFS Schedule update before the old calendar expires. Use when a service change, calendar rollover, stop rename, or route rename requires a new schedule expor

• 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
• Does not say what the process needs to start

Run a real brainstorm — divergent generation without judgment, then convergent selection with explicit criteria — instead of listing ten obvious ideas and calling it creativity. Us

• The skill tells the model to perform an irreversible action with no human approval
• No condition that starts the skill
• 3 mutating operations with no state check

Keeps this week's podcast episode from breaking distribution. Use when a new episode is published, before directories pull the revised public RSS feed, when a show is not ready, va

• 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
• Does not say what the process needs to start

Run the public-repository gates for Git commits, pushes, and pull requests. Check staged and untracked scope, secrets and personal data, internal material, branches and remotes, PR

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

Install and use GrayMatter as an OpenClaw skill that provides primary durable memory, shared object-graph state, and authenticated access to the live api-docs schema via api-0. Use

• References files that are not bundled: scripts/gm-light-smoke, scripts/gm-invariant-preflight, scripts/gm-activate
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 22 top-level sections: this looks like several domains in one skill

Manage Huawei Cloud APIG (API Gateway, dedicated instances) via hcloud CLI: instance lifecycle (create/list/delete), API groups, API create/update/delete, publish/offline, request

• 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 (5 tags): a typed call is more reliable

Export, import, and restore Alibaba Cloud DDoS Pro manual non-website TCP and UDP port forwarding rules and their portable configuration through Aliyun CLI. Use for non-website por

• 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

Create, validate, draft, schedule, publish, update, cancel, and manage platform-specific social posts across connected post2all accounts. Use when the user wants OpenClaw to publis

• 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
• Does not say what the result is

Force the simplest, shortest solution that works �� YAGNI, stdlib first, no unrequested abstractions

• 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

Structure and format meeting notes following PM best practices. Use when asked to create meeting notes, format discussion notes, capture action items, or document decisions from an

• References files that are not bundled: ../../SKILLSPEC.md, ../../connectors/mcp-pairings.md
• 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