Skill reviews

Scans and removes sensitive data (secrets, API keys, private domains/IPs, PII) from GitHub repository history, then verifies and force-pushes safely. Use for 清理敏感数据 / 历史重写 / 泄露, "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 (3 tags): a typed call is more reliable

Designs and audits macOS launchd watchdogs: LaunchAgent/LaunchDaemon setup, plist edits, scheduled self-healing, repeated notifications, apps reopening after quit, crash/repair loo

• References files that are not bundled: ../macos-permissions/references/uv-fda-trap.md, assets/launchagent.template.plist
• 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

Generate a self-contained JavaScript server runtime and registration metadata for an MCP codeful tool. Use when the user asks to create a codeful MCP tool, generate server logic fo

• References files that are not bundled: ../../references/codeful-tool-host-data-api.d.ts, ../../samples/account-summary.tool.js, ../../samples/account-summary.tool.json
• 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 a Power Apps mobile project needs dependency updates or an npm audit review. Checks the mobile-app plugin first, then updates the native host, other Microsoft packages, an

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

Autonomously build a complete Power Automate flow from a description. Use when you need to generate a full flow definition and create it. Always validates first and uses OpenApiCon

• 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

Adds Microsoft Copilot Studio connector to a Power Apps code app. Use when invoking Copilot Studio agents, sending prompts to agents, or integrating agent responses.

• References files that are not bundled: ${PLUGIN_ROOT}/shared/shared-instructions.md, ${PLUGIN_ROOT}/shared/connector-reference.md, ${PLUGIN_ROOT}/shared/connector-reference.md
• The skill tells the model to perform an irreversible action with no human approval
• 3 referenced file(s) missing: ${PLUGIN_ROOT}/shared/shared-instructions.md, ${PLUGIN_ROOT}/shared/connector-reference.md, ${PLUGIN_ROOT}/shared/connector-reference.md

Deploys an existing Power Pages site to a Power Pages environment using PAC CLI. Routes SPA sites to the existing build and upload-code-site workflow, and PAC-downloaded non-SPA (c

• 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

Use when the user asks to "set up authentication", "add login", "add logout", "add sign in", "enable auth", "add role-based access", "add authorization", "protect routes", "configu

• 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

Turn hunches into accepted results: worthiness score, evidence bar, research-to-rules. Use when vetting ideas. Not for QA; use night-market-validation-and-qa.

• 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

Shapes turns action-first: action leads, steps numbered, state restated. Use for ADHD-friendly output. Do not use to trim tokens; use response-compression.

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

Converts a Claude Code session JSONL file into an animated GIF terminal replay. Use when creating demos or visual evidence from past sessions.

• 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

Generates and self-executes a diff-derived test plan for a PR. Use when validating PR changes before merge. Do not use for code review; use sanctum:pr-review.

• 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
• The response is described with custom markup (3 tags): a typed call is more reliable

Convenes a multi-LLM expert panel to pressure-test hard-to-reverse decisions. Use when reversibility score is low and adversarial review is warranted.

• 17 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
• No condition that starts the skill

Run several independent Cotal features concurrently by creating one Git worktree and one spawn-capable mesh manager per feature; each manager staffs a review panel in a dedicated c

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

Prepare and manage durable MEX team handoffs. Use when the user asks to hand work to a person or team, prepare an end-of-session handoff, save what the next engineer needs, create

• 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

Prepare and manage durable MEX team handoffs in git-native project memory. Use when the user asks to hand work to a person or team, prepare an end-of-session handoff, save what the

• 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

Clean up an already-merged local branch after proving containment. Confirm each discard and preserve unique work.

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

Exploratory spike on a throwaway branch — answer a named question with disposable code. Never merges; exits to a findings note or $ca-feature.

• References files that are not bundled: ../../routines/brainstorming/SKILL.md
• 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

Clean up an already-merged local branch after proving containment. Confirm each discard and preserve unique work.

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

Exploratory spike on a throwaway branch — answer a named question with disposable code. Never merges; exits to a findings note or /ca-feature.

• 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
• Does not say what the result is

Frontend: UI design, distinctive visual styles, HTML artifacts, Three.js 3D.

• References files that are not bundled: templates/fonts/archivo-black.css
• 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

Evidence-capture and PoC-redaction discipline for bug-bounty submissions

• 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
• The skill tells the model to perform an irreversible action with no human approval

Shape output for ADHD readers: next action first, numbered steps, restated state, no tangents, time estimates, visible wins. Toggle with /i-have-adhd.

• 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

Codex-only team orchestration: run a named team of cooperating Codex workers with durable, script-managed state. MUST USE when the user asks Codex to create, run, coordinate, inspe

• 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

Remove unused code from this project with ultrawork mode, LSP-verified safety, atomic commits. Triggers: remove dead code, dead code, cleanup, remove unused.

• 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