Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
Use when designing Tauri 2 app architecture, choosing between IPC approaches, or planning application structure. Prevents using commands for streaming data, events for request/response, and putting business logic in the frontend. Covers commands vs events vs channels, state architecture, frontend-backend split…
Folds two surface names for the same backend system into one canonical entity, keeping every original mention individually retrievable, and refuses to merge pairs that only share spelling.
Use this skill for ANY task involving iOS/macOS localization: translating strings, adding or removing languages, checking coverage, finding missing or stale translations, validating format specifiers, managing plural forms, migrating from legacy .strings format, exporting/importing XLIFF for external translators…
Build a new feature using strict test-driven development — UNDERSTAND → DESIGN → RED → VERIFY RED → GREEN → VERIFY GREEN → REFACTOR → VALIDATE → REPEAT. Use when building a new feature with TDD, when the user says "TDD this", "tests first", "red green refactor", or asks for feature work that needs to be verifiable…
Set up the current repository for the orchestrator-worker workflow - project CLAUDE.md, path-scoped rules, continuity directories, and permission settings - by reading the codebase first and proposing a plan before writing anything.
Turn an idea or under-planned project into a buildable blueprint through a focused interview, decision-gap audit and verified open-source component research. Use for PRDs, project scoping, unresolved or conflicting requirements, and finding reusable components. Read existing decisions before asking questions. Works…
Re-assert the working agreement mid-session, or strip AI writing tells from text. Use when the user invokes /stop-the-charade, when they say Claude is drifting back into persona, parenting, or filler, or when they ask to humanize, de-AI, or clean up a piece of text, a file, or a previous response.
Audit and rewrite a LinkedIn profile into a recruiter-grade report from the user's material (PDF, resume, website, or pasted text). Use when the user asks to optimize, improve, review, or audit their LinkedIn profile, headline, About section, or experience, or wants help with personal branding, LinkedIn for job…
Review available recent code-agent history and tool calls, then update the current repository's durable agent guidance with repeatedly needed facts and user-corrected conventions. Run only when the user explicitly invokes /reinit, $reinit, or names the reinit skill; never invoke automatically.
The project's read-only 'where am I / what's next' oracle - scans the artifact chain, INTEGRITY-CHECKS the spine, counts the governance blockers 06-release gates on, DERIVES live state, and routes the NEXT COMMAND. READ-ONLY with respect to truth: never edits the spine or realizations; the only writes are two…
Use this skill when the user describes a consumer, platform, billing, travel, subscription, service, or support dispute and wants complaint, refund, cancellation, replacement, escalation, or customer-service scripts. It turns messy facts into evidence-based messages, escalation ladders, risk-aware variants, and…
Use when verifying implementation work and the failure mode is superficial approval, code-reading in place of execution, or over-trusting a passing test suite without trying to break the change.
Deploy static websites to ShipStatic. Use when the user wants to deploy a site, publish a website, upload to hosting, go live, set up a custom domain, manage deployments, or share a site URL. Free, no account needed. CLI (ship) and Node.js/browser SDK.
Dispatch coding tasks to other AI agents via oneagent (oa). Use when you want to delegate file edits, code generation, reviews, or other scoped tasks to a different model or backend — for example, sending a targeted edit to Codex while continuing your own work.
Convert an academic PDF paper into a single-page scrollytelling website (index.html + style.css + script.js + extracted figures + optional AI cover) using a fixed dark/light scroll-snap chassis. Use when the user provides a PDF and asks for a "storyboard", "scrollytelling page", "paper-to-web", "narrative website", or…
Use when scoping allow/ask rules for a command family (kubectl, oc, terraform, aws, gcloud, docker, etc.) to one repository so routine invocations stop prompting only inside that repo. Triggers include "allow kubectl in this repo", "stop asking about X commands", "add longline rules for this project", "allowlist…
Experto en accesibilidad digital basado en los estándares oficiales W3C WAI (https://www.w3.org/WAI/). Úsalo SIEMPRE que el usuario mencione: accesibilidad, WCAG, A11y, contraste de color, lectores de pantalla, ARIA, roles semánticos, navegación por teclado, focus, skip links, alt text, captions, subtítulos…
Universal prose audit. Scores writing on TWO axes — AI-Slop (does this read like AI wrote it?) and Comprehension (can a fresh reader follow this?). Use PROACTIVELY as a mandatory final QA pass on ANY prose generated for humans to read — every email (internal or external), proposal, report, status update, blog post…
Tracks betting line movements across sportsbooks for NBA, MLB, and Soccer in real-time, comparing odds from multiple bookmakers with sharp money detection and live game correlation. Triggers: betting odds, line movement, odds tracker, sports betting, spread changes, moneyline, over under, odds comparison, sharp money…
★not rated 5 7mo agoA78 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: