Showing 23281–23310 of 77205 skills
Audits queries, transactions, consistency and persistence resource lifetimes; read-only.
levnikolaevich/claude-code-skills
Reviews skill instructions, trigger boundaries and distribution contracts; not product code.
levnikolaevich/claude-code-skills
Use on the first conversation after someone imports the emerging-keyword monitor template: onboard them one question at a time.
Pluviobyte/saas-growth-agents
Use when setting up or running daily emerging-keyword / meme monitoring: sources, gates, prescan→broadcast schedule, Trends cost controls, and report format.
Pluviobyte/saas-growth-agents
Creates and maintains Figma Code Connect files (`*.figma.tsx`) that map Figma components to code via the parser-based `figma.connect()` API. Use when the user mentions Code Connect, Figma component mapping, design-to-code translation, or asks to create/update .figma.tsx files.
LedgerHQ/lumen
Use when creating, naming, or placing a file or folder in libs/*, or when modifying or adding a file to an existing component (even when the barrel isn't touched) — component vs utility naming, the one-responsibility-per-file layout, when a folder needs an `index.ts` barrel (public API only), and the required set of files a component needs per lib. Load this before scaffolding or restructuring a component so the layout matches the codebase.
LedgerHQ/lumen
Use when designing or changing a component's public API, its composition, or its state model in libs/ui-react or libs/ui-rnative — layering (core vs internal vs primitives), BaseProps/Props splits, converting a component to compound / changing its composition with createSafeContext, controlled/uncontrolled state, prop-naming conventions, and cross-platform API parity. Load this before shaping a new component, changing its props, or refactoring its composition.
LedgerHQ/lumen
Use when writing or editing Storybook MDX docs (*.mdx) — the two-tab Overview/Implementation structure, story-backed `<Source>` examples, and doc table guidelines.
LedgerHQ/lumen
Use when creating or editing Storybook stories (*.stories.tsx, React or React Native) — story layout, controls, and export naming conventions.
LedgerHQ/lumen
Use when writing or editing component tests in libs/ui-react or libs/ui-rnative — shared structure and coverage conventions, plus the per-platform runner: Vitest + React Testing Library on web, Jest + React Native Testing Library on RN. Load this before writing tests.
LedgerHQ/lumen
Use when asked to test a Lumen change against consumer repos before releasing it: a breaking or architectural change, a lint-plugin upgrade, peer/prod dependency moves, build or packaging changes, or to check how consumers use a component, prop or variant. Runs the change (or a usage scan) across the production consumers in the adoption registry and outputs a shareable HTML report.
LedgerHQ/lumen
Use when asked how other design systems handle a component, prop, token or pattern; to name a component, prop or token; to research best practices (composition, when to split, a11y, responsiveness, motion) before building; or for a design-system discovery or benchmark report. Compares Coinbase CDS, Adobe Spectrum, Astryx, Material, Primer, MetaMask DS and Base UI, anchors the recommendation in Lumen's code, and outputs a shareable HTML report.
LedgerHQ/lumen
Use when implementing or updating a component from a Figma link — how to turn the Figma design variables into code tokens, on both platforms: Tailwind classnames for libs/ui-react and themeJS (`t.*`) paths for libs/ui-rnative. For the full token catalogues and styling mechanics, see component-styling.
LedgerHQ/lumen
Sync processed CSS design tokens with JavaScript theme objects for React Native. Use when aligning tokens after Figma sync, checking token consistency, or updating JS theme files manually.
LedgerHQ/lumen
Use when asked to check Lumen version adoption across consumer repos, generate the Lumen adoption report, or find which repos are behind on a Lumen package version, or who owns those repos.
LedgerHQ/lumen
Upgrade a consumer repo to the latest Lumen: audit the gap, bump every `@ledgerhq/lumen-*` package, apply each migration crossed, verify, and open the PR. Run from the consumer repo's root, only when asked to upgrade or audit Lumen there.
LedgerHQ/lumen
Open a PR from the current branch to `main`: find the DLS ticket in the current sprint, ensure an Nx version plan exists, commit, push, and create the PR from the repo's PR template. Run only when the user explicitly asks to open/create a PR.
LedgerHQ/lumen
Review a PR or the current branch for a Lumen design-system change — routes each changed file to React (web/Tailwind) or React Native (useStyleSheet) guidelines, checks the Nx version plan, and reports a flat, severity-scored finding list. Use when the user asks to review a PR, review code changes, check a branch, do a local code review, or provides a GitHub PR URL.
LedgerHQ/lumen
Use when generating or editing an Nx version plan in .nx/version-plans/ — the bump type must always be `patch`, one package per file, and the message one `type(Scope): summary` line.
LedgerHQ/lumen
Writes the migration file (in `libs/migrations/src/`) and the Nx version plans for the current branch's changes to Lumen's public API. Use when a branch removes, renames or changes an export, prop, prop value, token, icon or peer dependency, changes behavior or rendering consumers rely on, when `check:breaking-changes` or the migrations `validate` fails, or when asked to write a migration or prepare a breaking change for review.
LedgerHQ/lumen
Implement, refactor, and migrate production Rust with repository-grounded ownership, type-driven invariants, explicit errors, safe concurrency, minimal unsafe code, and verified Cargo workflows. Use for Rust features, crates, CLIs, services, libraries, async code, FFI, performance work, migrations, or substantial .rs and Cargo.toml changes, including requests such as 'rust-coder', 'write Rust', or 'implement this Rust feature with Codex'.
sno-ai/sno-station-skills
Pinvou/pinvou-agent
Pinvou/pinvou-agent
Finds loops where the user keeps acting as a manual step for agents (retrying, judging output, approving, carrying context, starting the same task by hand, doing the agent's work) and proposes how to lift the user out: delete a stale rule, change a skill / AGENTS.md / playbook, add a script or metric, add a skill or scheduled task, or advise the user. Keeps a private loop ledger and promotes Claude Code auto-memory into artifacts. With a task already in the session, reflects on that session; in an empty session, scans recent local Claude Code, MiniMax Code, omp, pi and Codex sessions, a claude.ai export and an Obsidian vault. Triggers: /lifting-loops, retro, post-task reflection, "find repeated work", 反思一下, 复盘这次会话, 总结最近的会话, 找找重复劳动, 哪些事可以不用我; the weekly scheduled run; settling a proposal ("accept P-003", 采纳 P-003, 拒绝 P-003).
MiniMax-AI/mcode-stack
Write multiple-choice questions that check whether a PR's author understands their change. Use only when the MCode Review pipeline asks for an author quiz.
MiniMax-AI/mcode-stack
Review a pull request or the current branch with the MCode Review rules (severity, evidence ladder, lens checklists, review principles) and the repository's own .mcode-review.json and .mcode-review.md. Works with GitHub pull requests and GitLab merge requests. Use when the MCode Review CI pipeline starts a review pass, or when a developer asks to review their PR or branch before asking a person to review it.
MiniMax-AI/mcode-stack
Connects a GitHub or GitLab repository to the MCode Review CI and keeps the setup current. Use when someone adds MCode Review to a repository on GitHub Actions or GitLab CI, upgrades or rolls back the pinned plugin commit, changes the repository's rule pack, language, models, shadow or enforce phase, author quiz or Feishu card, checks the security setup, or troubleshoots a review run that failed.
MiniMax-AI/mcode-stack
Inventory everything an agent injects into each request besides the user's message, such as system prompt, environment info, skill list, tool definitions, per-turn context blocks and reminders, and check necessity, frequency, precision, position and prompt-cache impact. Use when reviewing an agent's prompt assembly, chasing low cache hit rates, or trimming per-turn overhead.
MiniMax-AI/mcode-stack
Review an agent's finished work by reading the evidence before its summary, naming what each check proves and what it misses, pulling out the decisions it made silently, and trying to falsify the result before accepting it. Use when a MiniMax Code session, subagent or cloud agent reports a task done, before merging its PR or acting on its analysis.
MiniMax-AI/mcode-stack
Run a harness change as a controlled experiment, with a small end-to-end eval, one change at a time, repeated runs, and looking at flipped tasks, request count, tokens and cache hits, not just the average score. Use before and after changing prompts, tools, skills, subagent layout, compaction or other agent scaffolding, or when asked whether a change helped.
MiniMax-AI/mcode-stack