Skill reviews

Only use when the user explicitly invokes this skill by name.

• 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

Migrate a single oRPC procedure from classic async handler to Effect-backed implementation. Use when converting procedures one at a time to maintain incremental, reviewable changes

• 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
• Does not say what the result is

PCBWay PCB fabrication and assembly — turnkey/consigned assembly, design rules, ordering workflow. Alternative to JLCPCB for manufacturing. Use with KiCad. Use this skill when the

• 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

Create new skills, edit existing skills, and iterate wording. Use when writing SKILL.md from scratch, improving existing skills, turning repeated workflows into reusable skills, or

• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (6 tags): a typed call is more reliable
• No condition that starts the skill

Creates a new graphics format spec (custom canvas dimensions + content rules) and publishes it to the Gooseworks library so any agent can render against it. Use when the existing c

• 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

Portable visual skill pack for the Agent Skills ecosystem (Claude Code, Claude Desktop, Claude Cowork, Claude Design, Goose, Cursor, Codex). Discovers community-published styles +

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 18 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

Write the step-by-step runbook a computer-use or browser agent follows to finish a real online task, such as cancelling a subscription or changing an energy supplier: what to look

• 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

Prepare, before you need it, the runbook for stopping a proactive agent that is misbehaving: how to pause it in seconds, which connections to revoke in what order, how to check wha

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

Deploys and hardens Vaultwarden, a lightweight self-hosted server that is compatible with the official Bitwarden apps and browser extensions, so a person, family or small team can

• 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

Discord is a chat platform whose bot API lets programs read events, answer slash commands and post messages in servers. Use this skill to create a Discord application and bot, choo

• 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

Diagnose and recover users stuck on a blank page or endless splash screen because a CDN or browser has pinned a 404 for a boot chunk. Covers confirming the diagnosis, the origin-si

• 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

Dispatches the comment-sicko subagent to hunt gratuitous comments in a PR/diff, triages its raw findings, and posts a polite, professional writeup. Use when reviewing a PR/diff, ch

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

Bug fix workflow that proves test validity with a red-then-green CI sequence. Commits a failing test first (CI red), then the minimal fix (CI green). Use when fixing a bug, writing

• 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

What publication checks, which private values never go into published files, and how to act on each rejection.

• 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

Do a write build's requested task once as a live act session, confirm it, then compose and publish its script without running it again.

• References files that are not bundled: references/write-readback.ts, references/write-session.ts
• 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

[omh] Production is down or an incident is open: command an incident that is still open -- severity as declared live state, commander and roles, an append-only timeline, a recorded

• 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

[omh] Support ticket your team must answer or escalate: turn a support case into a clear customer reply, severity path, and owned next step. Use when the user says: support escalat

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

[omh] Data pipeline work -- an ETL or streaming job, a backfill or replay, duplicate events, a schema change downstream, a lineage question, a data-quality regression: make every r

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

[omh] Spending money on the user's behalf -- a card checkout, an HTTP 402 or pay-per-request call, a wallet transfer, a booking, a paid data endpoint: show a pre-spend card (payee,

• 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

[omh] Explaining OMH itself: current-source-first documentation for OMH itself: product identity, public capability catalog, model routing, local state, and long-term memory. Use w

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

Run reputation programs: reviews, sentiment, brand safety. Crisis → crisis-response; one review → review-response. "get more Google reviews"

• 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 process needs to start

Read the GSC AI Performance report by script: AI Overviews and AI Mode impressions. "read the new GSC AI report"

• References files that are not bundled: scripts/gsc-ai-performance.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

Draft content in brand voice through a gated pipeline: blogs, ads, emails. Brief only → content-brief. "write a blog post about X"

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

Use when structuring Roblox game code: where scripts go (ServerScriptService, ReplicatedStorage, StarterPlayerScripts), Script vs LocalScript and RunContext, a module loader or fra

• References files that are not bundled: scripts/agentkit/architecture/Loader.luau, scripts/agentkit/architecture/Binder.luau, scripts/agentkit/architecture/
• 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

Use when animating Roblox characters, NPCs or creatures: animation not playing, wrong animation wins, animation priority or weight, blending, animation events and markers, hit timi

• References files that are not bundled: scripts/agentkit/animation/
• 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