Skill reviews

Instant in-site navigation: Speculation Rules, View Transitions, bfcache, 103 Early Hints. Use when "instant navigation", "prerender", "early hints", "back button reloads", or "sec

• 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

Turn an agent failure (premature stop, false completion, gamed check, missed file) into a rule, hook, or CI guard with a regression test. Use when "the agent stopped early again",

• References files that are not bundled: scripts/test-completion-gate.mjs
• 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

Plan and run a feature-flag rollout. Use when "add a feature flag", "gradual rollout", "staged release", "kill switch", "dark launch", "flag cleanup", "canary release", "rollback p

• 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 result is

Separate desktop and mobile UI in hybrid apps shipped as PWA + iOS + Android (Capacitor, Tauri, Expo Web, Ionic). Use when a UI sweep "improved one surface and broke the other".

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

Guide users through creating effective Agent Skills for Cursor. Use when user wants to create, write, update, or debug a skill, or asks about SKILL.md format, skill structure, ~/.c

• References files that are not bundled: reference.md, examples.md
• The skill tells the model to perform an irreversible action with no human approval
• 2 referenced file(s) missing: reference.md, examples.md

Create or update a pack SKILL.md (frontmatter, house limits, T1–T8). Use when "create a skill", "write a SKILL.md", or authoring a kenji skill. Prompt-only upgrade → enhance-skill-

• References files that are not bundled: ../../docs/PROMPT-ENHANCEMENT-PLAYBOOK.md, scripts/rotate_pdf.py, references/finance.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

Repository maintenance: sync the README, remove confirmed dead artifacts, update dependencies safely. Use when "housekeep", "clean up repo", "update README", or "update dependencie

• 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

Polish one existing React Native screen so it feels native. Use for "this screen looks off", "clunky on iOS", "Android looks wrong", "jank when scrolling", or "button is unreachabl

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

Consolidate accreted CI gates, ratchets, and hooks into one required aggregator check. Use after audit-gate-logic, or when "clean up our CI checks", "we have three lint jobs", or "

• 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

Run mutation testing (StrykerJS, mutmut) to measure whether tests assert behavior, not just execute lines. Use when "add mutation testing", "are our tests real", "can our test suit

• 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
• No condition that starts the skill

Write a doc into the private internal-docs repo as Markdown plus a rendered HTML sibling, tidy the repo's structure and index, and open a PR to browseros-ai/internal-docs.

• References files that are not bundled: <dir>/<file>.md, <dir>/<file>.html
• 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

Spreadsheet toolkit. Reach for it whenever the artifact on either side of the conversation is a workbook file — .xlsx, .xlsm, .xltx, .csv, .tsv — and the user wants that artifact p

• 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 result is

Verify Paperclip from a source checkout, published npm install, or existing staging or production stack. Select the environment, data state, version, and platform; drive real UI or

• References files that are not bundled: ../../../maps/README.md, ../../../maps/feature-map/README.md, ../../../maps/agent-access-map/README.md
• The skill tells the model to perform an irreversible action with no human approval
• 9 referenced file(s) missing: ../../../maps/README.md, ../../../maps/feature-map/README.md, ../../../maps/agent-access-map/README.md

This skill should be used when upgrading the cocoindex package version in all example pyproject.toml files. It uses regex-based sed commands to efficiently update version constrain

• 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 a SageMaker endpoint (real-time, real-time scale-to-zero, or async) with autoscaling, CloudWatch alarms, and tagging enabled by default. Use this skill whenever about to cre

• 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

Apply when you write, change, or keep a test. Assert what the code's users can observe, so that the test fails when that behavior breaks and keeps passing when only the internals c

• 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

Build and edit Google Slides through the google-slides MCP tools - slides, grids of cards and columns, text boxes, shapes, images, tables, styling, layout inspection, and per-slide

• 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

Apply to any non-trivial change before designing it. Make the requirement less dumb, delete, optimize, accelerate, automate, in that order, then run it again on the result. The rep

• 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

ALWAYS read this before using any X tool (the X plugin, any X MCP, or Grok Bot's built-in public X reads) and again on any X error. X tools are included in Grok Bot at no cost: nev

• 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

Run and verify ClawHub production deploys and stable ClawHub CLI npm releases. Use when deploying backend or frontend changes to clawhub.ai, dispatching the Deploy workflow, publis

• 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

Publish the current Convex app to a live *.convex.app URL (deploy backend + upload web build).

• 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

Which xberg-io repo owns a cross-repo fix or API, and coordinating compatible sibling changes. Use when work spans sibling repositories.

• 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

The test_documents corpus (submodule, bucket-fetched): read_test_fixture, missing fixtures, A/B controls. Use on a fresh clone or a missing fixture.

• 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
• Prose only: no discrete steps

MANDATORY prerequisite — load this skill BEFORE every `generate_diagram` tool call. NEVER call `generate_diagram` directly without loading this skill first. Trigger whenever the us

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

Use this skill alongside figma-use when the task involves translating an application page, view, or multi-section layout into Figma. Triggers: 'write to Figma', 'create in Figma fr

• References files that are not bundled: ../figma-use/SKILL.md, ../figma-code-connect/SKILL.md, ../figma-use/references/variable-patterns.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