Skill reviews

Procedure to fix an existing opendataloader-pdf GitHub issue and open a pull request. It analyzes the issue and makes sub-issues for extra problems. It reproduces the failure and,

• References files that are not bundled: ../odl-review/scripts/fetch_attachment.sh, ../../../.github/ISSUE_TEMPLATE/bug_report.md, scripts/build-python.sh
• 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

Package findings from a completed spike into a durable, project-local skill that auto-loads on future similar work. Reads the most recent `.gsd/workflows/spikes/` directory, interv

• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (20 tags): a typed call is more reliable
• No condition that starts the skill

Kimi Browser Extension（Kimi 浏览器扩展，原 Kimi WebBridge）lets AI control the user's real browser — navigate, click, type, read, screenshot, and interact with any website using the user's

• 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

Use when generating changesets in the kimi-code repository — deciding whether to write one, which package to list, the bump level, the wording, and the confirmation workflow.

• 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

Trigger: reviewer transport, advisory transport, review adapter, lens prompt/schema, OpenCode reviewer plugin, Codex reviewer, ReviewProviderContract. Enforce the shared Go advisor

• 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

Renders every state of a component you choose on a throwaway page, with mock data and a switcher, so you can work on each state.

• 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

Builds multiple variants of a component you're working on and helps you iterate and pick one.

• 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

Track competitor pricing and packaging as a diffable time series. Use when monitoring tiers, gates, limits, and price moves on a monthly or quarterly cadence.

• References files that are not bundled: ../autonomous-investigation/SKILL.md, ../intelligence-collection-disciplines/SKILL.md, ../finance-based-pricing-advisor/SKILL.md
• 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

How to build or extend a multi-app Agent-Native workspace — the monorepo shape, the Dispatch control plane, the shell app that fronts every other app, and the shared package. Use w

• 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
• The response is described with custom markup (8 tags): a typed call is more reliable

Open or create a repo-native visual documentation workspace backed by local Plan MDX files. Use when the user asks to visualize a repository, create durable visual docs for APIs/co

• 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 Design for UI/UX exploration, side-by-side design directions, interactive prototype previews, user selection, iteration, and design-to-code handoff through the hosted Design MC

• 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

Generate slide images locally by default; use Assets over A2A only for a user-requested brand-library generation or an Assets-exclusive capability.

• 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

Which Plan command and creation action fits a request — document-first, UI-first, prototype-first, design-first, recap, or visual intake — plus how to raise an existing plan to des

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the process needs to start
• 16 mutating operations with no state check

Find, save, copy, and adapt Design templates. Use when the user references a template, a prior design, or wants a reusable starting point.

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• 11 mutating operations with no state check

How to create and structure forms. Use when creating a new form, adding fields, modifying form structure, or understanding field types and their JSON schema.

• 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

How screen and camera recording works in Clips — MediaRecorder lifecycle, chunked upload, permission handling, pause/resume, camera bubble overlay, error recovery, and screenshots

• 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

Declare, evaluate, manage, and remove framework feature flags. Use when shipping a capability gradually, targeting users or organizations, or replacing a compile-time rollout switc

• 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

Inspect and manage the live agent context window with Context X-Ray. Use when context is getting large, the user asks what is in context, or stale tool results/files should be pinn

• 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

| Production-tested setup for Tailwind CSS v4 with shadcn/ui, Vite, and React. Use when: initializing React projects with Tailwind v4, setting up shadcn/ui, implementing dark mode,

• 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
• Does not say what the result is

Guide for upgrading Stripe API versions, webhook endpoints, server-side SDKs, Stripe.js, and mobile SDKs

• 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

Guidelines for upgrading Expo SDK versions and fixing dependency issues

• 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
• Does not say what the result is

Draws hand-authored SVG spot illustrations in a bold pop-geometric style for design and coding scenes. Identifying traits: a thick navy outline on every shape, solid navy extrusion

• 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

Draws original hand-written SVG spot illustrations in the One-line style, joyful action figures doing design and coding work. One continuous uniform black line (2.3 px at 480 wide)

• References files that are not bundled: examples/hackathon-sprint.svg, examples/flow-state.svg, examples/juggling-tasks.svg
• 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

Add cursor-following fluid WebGPU distortion over an existing image with the Shaders library's ImageTexture and CursorRipples components. Use when a hero, gallery, or media panel n

• References files that are not bundled: assets/react/cursor-ripple-media.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

Oversee the other Claude threads (sessions) working on the same project. Check what each is doing, confirm finished work is merged to main, has its changelog entry with screenshots

• References files that are not bundled: references/<project>.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