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.
t-code4change/nextjs-claude-skills
Skill Claude Code needs its repo
Flagship SEO + Performance skill for Next.js App Router. Use when implementing or auditing SEO (metadata, Open Graph, JSON-LD, sitemap, robots, canonical, hreflang), optimizing Core Web Vitals (LCP/INP/CLS), optimizing images/fonts/ scripts/bundles, setting up Web Vitals monitoring, or diagnosing Google indexing…
Skill Claude CodeCodex
Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.
2023Anita/clinical-ai-agent-skills
Skill Claude CodeCodex
Use when a task touches clinical research, health claims, trial interpretation, medical AI safety, or content that could be mistaken for medical advice.
zaowanqaq/systematic-understanding-framework
Skill Claude CodeCodex
A structured method for understanding complex subjects by breaking them into parts, finding patterns, asking challenging questions, and testing conclusions. It includes tools such as first-principles thinking, analogies, root-cause analysis, and the Feynman technique.
Skill Codex
Use when Codex should coordinate software project work through a virtual high-standard product and engineering team, including PM, product manager, UI designer, art director, architect, frontend engineer, backend engineer, algorithm engineer, QA engineer, and DevOps engineer. Applies to new projects, existing codebase…
Skill Claude CodeCodex
Enforce Separation of Duties (SoD) in AI-generated code security reviews. Triggers on: code review requests, security scans, vulnerability checks, SoD queries, provenance audits, CI/CD security integration, or when comparing generator/reviewer models. Also triggers on keywords: 'review code', 'security scan'…
Skill Claude CodeCodex
Comprehensive Flow Nexus platform management - authentication, sandboxes, app deployment, payments, and challenges.
Skill Claude CodeCodex
A connectivity-checking workflow for Kuaishou internal services, including single sign-on, configuration services, caches, and bastion hosts. A bastion host is a controlled server used to reach protected systems.
Skill Claude CodeCodex
Designs decentralized apps from brief to production — user + trust-boundary mapping, contract architecture, client layer, indexing strategy, off-chain components, deployment pipeline, and ops. Use when starting a new dApp and needing a coherent plan before code, auditing an existing dApp for architectural gaps, or…
Skill Claude Code
A drop-in walkthrough layer for static HTML demos: it adds a button, step-by-step cards, highlighted page areas, and explanatory text, including across multiple pages. It creates a separate copy of the demo so the original stays unchanged.
specklesystems/speckle-docs-NEW
Skill Claude Code
Make Speckle docs PR CI-ready (CI mechanics only). Use when fixing Docs PR checks failures (Prettier, markdownlint, mint validate, broken links, a11y), before opening or updating a docs PR, or when the user asks to make docs CI green / check:changed / format-ready. For content and tone, use docs-page-review.
Xclaw-bot/benchmark-task-authoring
Skill Claude Code
Design, red-team, ship and debug hard Terminal-Bench 2 / Harbor benchmark tasks: the measured laws for what makes agents actually fail, the kill-list of dead task shapes, and how to clear all 17 review stages in one push instead of three. Use for benchmark task slots, TB2/Harbor tasks, task.toml, instruction.md, task…
Le0Dove/experiment-report-skill
Skill Claude CodeCodex
A skill for generating Chinese undergraduate laboratory reports, with choices for five subject areas, four levels of detail, and six user situations.
Skill Claude CodeCodex
A structured review process used when closing an episode of work. It covers decisions about feedback, routing, promotion of findings into lasting records, and the final status.
Skill Claude CodeCodex
Use this skill when a request asks to refactor code while preserving behavior, especially across stack-specific toolchains.
Skill Claude CodeCodex
Airtable REST API via curl. Records CRUD, filters, upserts.
Skill Claude CodeCodex
A Chinese-language, multi-role workflow for turning product requirements into a packaged delivery. It covers research, a PRD (product requirements document), design checks, design, test cases, and final consistency reviews.
Skill Claude CodeCodex
Find a curated AI prompt template for any task — writing, image generation, video, or code. Use this skill when the user wants a ready-made prompt template (not a one-shot request). The skill queries a configurable prompt library backend via a documented /api/skill/ HTTP contract and returns the best match with…
Skill Claude CodeCodex
A loop for continuously reviewing the Copilot comments on a pull request until all comments are resolved by implementation or explanation.
exchanet/method_enterprise_builder_planning
Skill Cursor
Orchestrate the full enterprise software planning methodology. Activates the 8-phase planning cycle for mission-critical, high-availability, and enterprise-grade systems. Integrates Method Modular Design (Core + Packs) with PDCA-T quality cycle.
CelineWang-bestever/business-analysis-skill
Skill Claude CodeCodex
A business-analysis assistant that helps turn proposed product changes into clear requirements and plans. It uses visual requirement analysis and supports Chinese-language requests.
omneity-labs/ziryab-lyrics-skill
Skill Codex
Use this skill when Codex needs to call Omneity/Sawalni Ziryab rhyme and lyrics APIs for Sawtone-backed rhyme scoring, rhyme search, lyric word replacement suggestions, or lyric/stanza rhyme-structure analysis. Trigger for tasks mentioning Ziryab, Sawtone rhyme APIs, rhyme score, rhyme search, lyric replacements…
Skill Claude CodeCodex
Pages tools for Dataspheres AI.
Skill Codex
Review recent vibe coding or AI-assisted work history across Codex, Claude Code, WorkBuddy, Cursor, GitHub, local repositories, notes, or other available tools to identify repeated manual workflows worth packaging into reusable prompts, skills, slash commands, custom agents, playbooks, or automations, and infer the…
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: