Context & AI engineering
25,815 rows, by stacks then stars
1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid
tinh2/skills-hub-registry/productivity/dynamic-skill-loader Skill
no license23★ repoAuto-detects the current project's technology stack and hot-loads context-appropriate skills at session start using Claude Code's SessionStart hook with reloadSkills: true. Detects Node.js/TypeScript, Next.js, Python, Rust, Go, Ruby, and monorepo layouts. Emits a .claude/dynamic-context.md with the detected stack and recommended skill list, then signals Claude Code to reload skills before the first agent turn.
tinh2/skills-hub-registry/productivity/gpt-5-5-agentic-setup Skill
no license23★ repoMigrates your agentic coding pipeline to GPT-5.5 — audits the current model config, switches the API endpoint, validates tool-call compatibility (including parallel-call race conditions), runs Terminal-Bench-style smoke tests, and rewrites system prompts for GPT-5.5's agentic strengths. Safe to run on existing projects.
tinh2/skills-hub-registry/productivity/gpt-5-6-tier-routing Skill
no license23★ repoAutonomously selects the right GPT-5.6 tier (Sol / Terra / Luna) for each coding task based on scope, file count, and planning complexity — then applies explicit cache breakpoints for SKILL.md files and system prompts. Reduces monthly AI coding costs by 50–80% without sacrificing output quality on complex tasks.
tinh2/skills-hub-registry/productivity/session-handoff Skill
no license23★ repoCompress the current working session into a handoff document that a fresh session (or another person) can resume from without re-discovery. Inventories the session (task, decisions made and why, files touched with one-line diff summaries, commands that worked, dead ends to avoid, current blockers), writes it to .claude/handoff/<date>-<topic>.md with a paste-ready RESUME PROMPT section at the top, runs a stranger-test completeness check (no unexplained jargon, absolute file paths, next three actions explicit), and lists stale handoffs older than 30 days for pruning. Use when you say "hand off this session", "write a handoff", "save context before I close this", "I'm out of context, summarize for the next session", "pick this up tomorrow", "create a resume doc", or before compaction on a long task.
tinh2/skills-hub-registry/productivity/session-memory Skill
no license23★ repoPersist, summarize, and reload agent context between sessions — writes a structured session log to CLAUDE.md / AGENTS.md / .hermes.md, snapshots decisions before destructive ops, and resumes long-running goals without re-briefing. Works with any coding agent.
tinh2/skills-hub-registry/productivity/windsurf-spaces Skill
no license23★ repoSets up and manages Windsurf Spaces for multi-agent workflows — discovers project context, creates properly-scoped Space configs, seeds shared context for agent sessions, and generates structured Devin handoff specs so cloud execution starts with complete, unambiguous requirements.
tinh2/skills-hub-registry/qa/browser-agent-verify Skill
no license23★ repoVerifies front-end changes by driving a real browser — spins up the local dev server, navigates to the changed route, executes the affected interaction flow, captures console output and screenshots, then reports pass/fail with structured findings. Works with Claude Code, Cursor, and Codex CLI via Playwright; mirrors the GitHub Copilot browser tools GA workflow announced July 1 2026.
tinh2/skills-hub-registry/security/agent-authorization Skill
no license23★ repoAudits and implements authorization controls for production AI agent systems — policy definition, tool-call enforcement, immutable audit trails, least-privilege scoping, and MCP-layer governance. Use when shipping agents that touch production data or act on behalf of real users.
tinh2/skills-hub-registry/security/cursor-agent-safety Skill
no license23★ repoAudits and hardens Cursor agent run mode settings for Cursor 3.6+. Reviews the current run mode, writes project-appropriate classifier instructions (agent-policy.md), builds a terminal allowlist from the project's actual command usage, and tests the configuration against common prompt-injection and scope-creep patterns. Use when setting up a new Cursor project, after adding MCP servers or new tools, or when agents are producing too many approval interrupts.
tinh2/skills-hub-registry/ux/design-claude Skill
no license23★ repoHTML-first hi-fi design skill: interactive prototypes, slide decks, animation demos, design variant exploration, visual direction advising, and expert critique. Triggers: make a prototype, design demo, interactive prototype, HTML presentation, animation demo, design variants, hi-fi design, UI mockup, prototype, design exploration, make an HTML page, make a visualization, app prototype, iOS prototype, mobile app mockup, export MP4, export GIF, 60fps video, design style, design direction, design philosophy, color scheme, visual style, recommend style, pick a style, make it look good, review, does this look good, review this design. Core capabilities: Junior Designer workflow (show assumptions+reasoning+placeholders first, then iterate), anti-AI-slop checklist, React+Babel best practices, Tweaks variant switching, Speaker Notes presentation, Starter Components (slide shell/variant canvas/animation engine/device frames), App prototype rules (default real images from Wikimedia/Met/Unsplash, AppPhone state manager for interactivity, Playwright click test before delivery), HTML animation→MP4/GIF export (25fps base + 60fps interpolation + palette-optimized GIF + 6 scene BGM tracks + auto-fade). Vague requests fallback: Design Direction Advisor — recommend 3 differentiated directions from 5 schools × 20 design philosophies (Pentagram information architecture / Field.io motion poetics / Kenya Hara eastern minimalism / Sagmeister experimental avant-garde), show 24 pre-made showcases (8 scenes × 3 styles), generate 3 visual demos for user to choose. Optional post-delivery: expert 5-dimension critique (philosophy consistency / visual hierarchy / detail execution / functionality / innovation 0–10 each + fix list).
gtrabanco/agentic-workflow/skills/bump-skill Skill
23★ repoInternal agentic-workflow maintenance: after SKILL.md edits, bump semver, lint authoring rules, and synchronize changelogs, READMEs, routing metadata, and migrations. Triggers: "bump the skill", "update the changelog", "version bump".
gtrabanco/agentic-workflow/skills/design-feature Skill
23★ repoTurn a raw idea or existing feature into a designed product SPEC by completing entity, integration, role, and expectation closure. Upserts never destroy recorded decisions. Triggers: "design-feature", "design this feature", "define product scope".
gtrabanco/agentic-workflow/skills/execute-phase Skill
23★ repoStack-agnostic agentic-programming workflow skills + documentation scaffold
gtrabanco/agentic-workflow/skills/generate-docs Skill
23★ repoGenerate incremental, diff-driven developer guides through the project's detected docs adapter. Never regenerate the whole site, scaffold it, or edit source. Triggers: "generate-docs", "generate the docs", "document this unit".
gtrabanco/agentic-workflow/skills/init-workspace Skill
23★ repoAdapt the workflow scaffold to a new repository or add only missing substrate blocks to an existing install. Every install, hook, and overwrite needs explicit consent. Triggers: "init-workspace", "set up agentic workflow", "upgrade workflow scaffold".
gtrabanco/agentic-workflow/skills/log-session Skill
23★ repoAppend a structured entry to the project's session log (`docs/LOGS.md`): what was done this session, files touched, decisions taken, and the next step — so the next session (or another person) can pick up the thread without re-reading git history. Run it before `/clear`, before closing Claude Code, or at any natural stopping point. On Claude Code and want hand-tuned per-skill model/effort tiers? Install the `#claude` branch instead (`npx skills add gtrabanco/agentic-workflow#claude`) — see the README. This branch is model-agnostic: the skill inherits whatever model and effort your agent session is already using. Triggers: "log this session", "log-session", "write a session log", "journal what we did", "record this session before I clear", "save the session summary".
gtrabanco/agentic-workflow/skills/orchestration-envelope Skill
23★ repoInternal machine-result contract for headless agentic-workflow drivers. The executable source is @gtrabanco/agentic-workflow-schema: strict Envelope v2 for workflow-status, compact SkillOutcome v1 for driven work, compatibility parsing, and deterministic document snapshots. Not a menu entry.
gtrabanco/agentic-workflow/skills/plan-feature Skill
23★ repoRoute designed features or issues into engineering planning and roadmap registration; undesigned work stops at design-feature. Supports `--next`, `--from-issue`, and `--scaffold`. Triggers: "plan-feature", "plan a feature", "plan the next roadmap feature", "create SPEC and TASKS".
gtrabanco/agentic-workflow/skills/plan-fix Skill
23★ repoDraft and locally commit a tightly scoped, phased fix SPEC from one or more issues, then stop before push/PR and hand off to execute-phase --fix. Triggers: "plan-fix", "plan a fix for issue N", "draft the fix spec".
gtrabanco/agentic-workflow/skills/product-audit Skill
23★ repoAudit the whole product across code, quality, process, docs, roadmap, and tooling. Persist one severity-ranked, F-numbered report with proposals; never fix or file work. Triggers: "product-audit", "audit the product", "full health check", "are we product-ready", "CTO review".
gtrabanco/agentic-workflow/skills/review-change Skill
23★ repoReview a change with only applicable internal axes, classify every finding, persist fix-now work, and return one evidence-backed decision. Findings only; --adversarial N uses isolated reviewers; --synthesize fuses supplied reviewer tables. Triggers: "review-change", "review this change", "adversarial review".
gtrabanco/agentic-workflow/skills/triage-issue Skill
23★ repoVerify an issue, persisted audit finding, or unresolved review finding against current code, classify it, and write only the contracted forge/ledger outcome. Supports independent batches and an immediate-fix review-finding route. Triggers: "triage-issue", "triage issue N", "triage this finding", "is this trigger met".
pinecone-io/gemini-cli-extension/skills/mcp Skill
23★ repoReference for the Pinecone MCP server tools. Documents all available tools - list-indexes, describe-index, describe-index-stats, create-index-for-model, upsert-records, search-records, cascading-search, and rerank-documents. Use when an agent needs to understand what Pinecone MCP tools are available, how to use them, or what parameters they accept.
pinecone-io/gemini-cli-extension/skills/pinecone-docs Skill
23★ repoCurated documentation reference for developers building with Pinecone. Contains links to official docs organized by topic and data format references. Use when writing Pinecone code, looking up API parameters, or needing the correct format for vectors or records.
pinecone-io/gemini-cli-extension/skills/query Skill
23★ repoQuery integrated indexes using text with Pinecone MCP. IMPORTANT - This skill ONLY works with integrated indexes (indexes with built-in Pinecone embedding models like multilingual-e5-large). For standard indexes or advanced vector operations, use the CLI skill instead. Requires PINECONE_API_KEY environment variable and Pinecone MCP server to be configured.
etrebels/claude-code-growth-os/.claude/skills/onboarding-handoff Skill
23★ repoRun the Won→onboarding handoff — the seam most teams drop. Trigger when a deal is marked won/closed-won, when the user says "we won X", "hand this off to onboarding", "kick off the new customer", or "onboarding checklist".
alexclowe/awesome-copilot-cowork-plugins/prompt-engineer/skills/prompt-optimization-loop Skill
23★ repoPrompt-engineering expertise for designing test cases, edge cases, adversarial inputs, and iterating on prompts based on eval results
NintendaDev/unikit-ai/skills/unikit-evolve Skill
22★ repoLearn project rules from accumulated fix patches in .unikit/code/patches/. Analyzes past mistakes, extracts prevention points, classifies each as a coding rule (→ RULES.md) or a per-skill workflow rule (→ skill-context), and proposes them for approval. Use when the user wants to turn past fixes into rules — "evolve", "evolve the rules", "learn from past mistakes", "learn from the fixes", "analyze the patches", "what rules should we add from recent fixes". Best run after several /unikit-fix sessions have left patches behind. This derives rules from accumulated patch history — to add a single rule by hand use /unikit-rules, and to promote mature RULES.md entries into the knowledge base use /unikit-memory migrate-rules.
NintendaDev/unikit-ai/skills/unikit-memory Skill
22★ repoCurate the project's knowledge base and memory in .unikit/memory/ — the indexed reference library of coding standards and framework usage patterns. ALWAYS use this skill whenever the user adds knowledge from a source: a URL, a file, a folder path, a PDF, an article, or a book — any path/link/document is a strong signal for the knowledge base, not a quick rule. Also use it to research or document how the project uses a framework, or to add a researched core/stack knowledge entry. Sub-commands by phrasing: "migrate the rules" or "promote rules" runs migrate-rules; "optimize the knowledge base" or "optimize the rules" runs optimise (extract large sections into references); "validate" re-syncs RULES_INDEX.md; "--module <id>" targets a module. For a quick one-line convention or correction typed as a prompt ("always do X", "never use Y", "remember this") with no source, use /unikit-rules; for architecture decisions use ARCHITECTURE.md.
NintendaDev/unikit-ai/skills/unikit-rules-registry Skill
22★ repoOrchestrate the remote rules registry — the shared registry (often connected as a local folder or git repo) that the project's rules are published to and pulled from. Three modes, picked from the user's wording: create scaffolds a new local rules registry ("create a local rules registry", "init a rules registry"); update migrates/promotes local knowledge-base rules from .unikit/memory/ into the remote registry with automatic semver bumps ("migrate local rules to the remote registry", "promote my rules to the registry", "push local rules", "publish local rules", "update the rules registry"); sync pulls registry updates back into memory ("sync the rules registry", "pull registry updates"). Pass "--module <id>" to scope to one knowledge-base module. This skill ONLY orchestrates the CLI (`unikit-ai rules *`) — it never edits .unikit.json or .unikit/memory/ sources directly.
NintendaDev/unikit-ai/skills/unikit-rules Skill
22★ repoAdd a short, project-specific rule, convention, or override to .unikit/RULES.md — the quick-capture inbox for this project's rules; each invocation appends a rule, automatically loaded by /unikit-implement before execution (later promotable into the knowledge base via /unikit-memory migrate-rules). Works only with a rule typed as a prompt — it does NOT read files, folders, URLs, or PDFs. Cross-checks against the knowledge base (RULES_INDEX.md) to avoid duplicating core/stack entries. Use for fast, one-line conventions and corrections: "add a rule", "remember this", "convention", "always do X", "never use Y", "from now on do Z", or when the user corrects agent behavior and wants it remembered. If the user points to a source (file, folder, URL, PDF, article, book) or wants to research/document framework usage, use /unikit-memory; for architecture decisions use ARCHITECTURE.md.
social-media-skills/skills/skills/hook-writer Skill
22★ repoUse to write the hook — the opening that earns attention — for any social content: a caption's first line, a video's first three seconds, a carousel cover slide, a thread opener, a YouTube title, or an email subject. Run when the user says "write a hook," "hook for this," "opening line," "first three seconds," "cover slide," "make this scroll-stopping," or when good content keeps getting ignored. Reads brand-profile and voice first so hooks sound like the brand, not viral-bait templates. Hooks must be TRUE to the content that follows — this skill extracts the hook from the post's strongest element and never overpromises. For full captions use caption-writer; for full video scripts use the video skills. This writes the opening itself.
social-media-skills/skills/skills/ideogram Skill
22★ repoUse to write great prompts for Ideogram (Ideogram 4.0) to generate design-grade images for social media — the image-prompt-craft mini-skill for typography + layout, sibling to nano-banana under the image-prompt router. Run when the user wants an Ideogram / AI image prompt where TEXT and LAYOUT matter: quote cards, carousel covers, posters, logos/wordmark concepts, signage, ads with headlines, or any image that must say words correctly. Reads brand-profile for style/palette. Ideogram's standouts: best-in-class in-image text rendering, structured JSON prompting (bounding boxes, hex palettes), native 2K, transparency, and Layerize Text. Also covers the Ideogram app-editor workflow (Canvas, Magic Fill, Extend, Style References). Honest: review rendered text, disclose AI images and sign with C2PA, never generate real identifiable people or copyrighted characters/IP/logos. The API/connection and the generate -> upload to WoopSocial Media -> attach flow live in tools/integrations/ideogram.md.
social-media-skills/skills/skills/image-prompt Skill
22★ repoUse as the foundation and router for any image a post needs — turn a social need into a clear image brief, describe it with model-agnostic prompt craft, and route to the right tool. Run when the user says "I need a visual/image for this post," "what image should I use," "make a graphic," "help me prompt an image," or is unsure which image tool/model to use. Reads brand-profile for the visual brand. Teaches the image brief, the universal anatomy of a strong prompt in natural language, and a tool router (typographic -> ideogram/nano-banana; photoreal -> nano-banana/flux; surreal -> Midjourney; editing -> nano-banana/flux; vector -> Recraft; video -> veo-3). Includes a "should this even be AI-generated?" gate (a real photo, screenshot, or chart often beats generic AI), accessibility, and honest scope (disclose AI, never real identifiable people or copyrighted IP, verify text/data). Hands off to the tool-specific mini-skills; WoopSocial publishes via Media and doesn't generate images.
social-media-skills/skills/skills/veo-3 Skill
22★ repoUse to write great prompts for Google Veo (Veo 3.1) to generate or animate video for social media — the video-prompt-craft mini-skill, the video counterpart to nano-banana. Run when the user wants a Veo / AI video prompt, a short video clip for a post (b-roll, product-in-motion, hook visual, spokesperson/UGC clip, ad), to animate a still image into video, or a vertical Reel/TikTok/Short clip. Reads brand-profile for brand style. Veo's standout is native synchronized audio in one pass, plus image-to-video and native 9:16 vertical. Teaches the prompt anatomy, audio prompting, the image-to-video pipeline, and the 8-second constraint + extension/stitching. Honest: iterate cheap then finalize, disclose AI video (SynthID watermark), never generate real identifiable people or copyrighted IP. This is the prompt-craft layer — the API/connection and the generate -> upload to WoopSocial Media -> attach flow live in tools/integrations/veo.md; the consuming pack is reels-script's veo-prompt-pack.
0xhughs/director-skills/skills/cinematic-image-prompting Skill
22★ repoGenerate cinematic image prompts for characters, locations, props, costumes, keyframes, posters, concept art, reference sheets, and scene stills using creative intent plus camera, lighting, texture, and continuity anchors.
0xhughs/director-skills/skills/cinematic-video-prompting Skill
22★ repoGenerate text-to-video and image-to-video prompts with shot timing, subject motion, camera movement, lensing, lighting, audio cues, continuity anchors, and model-aware constraints.
Prompt iteration and diagnostics
0xhughs/director-skills/skills/prompt-iteration-and-diagnostics Skill
22★ repoDiagnose failed AI image or video outputs, identify root causes, revise prompts with single-variable iteration, and produce structured prompt revision reports.
hogan-tech/brand-loom/skills/hook Skill
22★ repoUse when you need scroll-stopping hooks or headlines for a topic. Model-agnostic (OpenAI/Anthropic/Gemini/Ollama). Part of brand-loom; hosted brand-memory version at neoxra.com.
Dqz00116/skill-lib/kimicode-vision-bridge Skill
22★ repoUse when the current Agent LLM cannot process images directly and visual analysis is needed — bridges images through KimiCode CLI print mode to a multimodal Kimi model for text description
Dqz00116/skill-lib/knowledge-base-cache Skill
22★ repoUse when managing large knowledge bases, reducing API costs, or implementing multi-tier caching for frequent queries
Dqz00116/skill-lib/unity-mcp Skill
22★ repoUse when controlling Unity editor via AI, automating scene operations, or programmatically generating Unity assets and scripts
igmarin/rails-agent-skills/io.github.igmarin/rails-agent-skills-mcp MCP server
22★ repoRails development skills, docs, and workflows exposed through MCP stdio.
Fec backend requirements handoff
bovinphang/frontend-craft/localized/zh-CN/skills/fec-backend-requirements-handoff Skill
21★ repo用于前端工作需要向后端团队说明数据、动作、状态、权限、校验或业务规则需求,但不指定端点设计、字段名、数据库形态或实现细节;中文触发词包括 前后端需求交接、后端需求、API 需求澄清、数据需求说明。
Fec backend requirements handoff
bovinphang/frontend-craft/skills/fec-backend-requirements-handoff Skill
21★ repoUse when frontend work needs to communicate data, action, state, permission, validation, or business-rule needs to backend teams without dictating endpoint design, field names, database shape, or implementation details; Chinese triggers include front-end and back-end requirements handover, back-end requirements, API requirements clarification, data requirements description.
agents-inc/skills/src/skills/ai-orchestration-langchain Skill
21★ repoLangChain.js patterns for building LLM applications — chat models, LCEL chains, prompt templates, structured output, agents, tools, RAG, streaming, and LangSmith tracing
agents-inc/skills/src/skills/ai-orchestration-llamaindex Skill
21★ repoLlamaIndex.TS data framework for RAG, indexing, retrieval, query engines, chat engines, and agentic workflows in TypeScript
Ai orchestration vercel ai sdk
agents-inc/skills/src/skills/ai-orchestration-vercel-ai-sdk Skill
21★ repoVercel AI SDK patterns - providers, text generation, streaming, structured output, tool calling, chat UI hooks, embeddings, and RAG
agents-inc/skills/src/skills/ai-patterns-tool-use-patterns Skill
21★ repoProvider-agnostic patterns for LLM function calling, tool loops, and agentic workflows
agents-inc/skills/src/skills/ai-provider-claude-vision Skill
21★ repoImage understanding and document analysis with Claude's multimodal capabilities -- image input formats, PDF processing, multi-image patterns, structured extraction, and token cost estimation
Lambenthan/paper-discipline-skills/paper-verify-before-handoff Skill
21★ repo在把任何成果交付给用户("改完了"、"已完成"、"可以发给导师"、"可以提交")之前, 必须运行一份硬检查清单:术语一致性、引用完整性、数据正确性、图表编号、 内部交叉引用、字数 / 格式合规、未完成 todo 残留、AIGC pattern(涉及文段改写时跑 chinese-de-aigc 五维自评)、 论证一致性(涉及核心声明改动时跑 paper-logical-consistency 复核)、 改动概要——任意一项 fail 都不能宣告完成。 Use when 你即将说「改完了 / 完成了 / 可以提交了 / 可以发给导师了」、 或用户问「是不是可以了」「还有什么要检查的吗」。
cmertdalli/polisci-review/templates/claude-skill Skill
21★ repoRun a public-facing political science pre-submission audit with journal personas, stage gating, and evidence-grounded issue reporting
ur-grue/autopunk-media-skills/skills/image-prompting/art-direction/visual-identity-prompt Skill
21★ repoWrites a comprehensive visual identity prompt for a show, channel, or publication — a master brief that defines the complete visual language and can be used to art-direct any asset in the project's visual system.
ur-grue/autopunk-media-skills/skills/image-prompting/flux/dark-aesthetic-prompt Skill
21★ repoGenerates a Flux prompt for dark, moody, or noir visual aesthetics — producing images with low-key lighting, shadow-dominant composition, and the specific atmospheric quality of noir cinema, gothic illustration, or dark editorial photography.
ur-grue/autopunk-media-skills/skills/image-prompting/flux/editorial-photo-prompt Skill
21★ repoWrites a Flux prompt for editorial-style photography suitable for journalism, documentary, and factual media contexts — images that look authentic, specific, and grounded in the real world rather than idealized or commercial.
ur-grue/autopunk-media-skills/skills/image-prompting/midjourney/character-consistency-prompt Skill
21★ repoWrites a set of Midjourney prompts designed to maintain consistent character appearance — face, build, clothing, and presence — across multiple generated images for use in editorial series, podcast artwork, YouTube thumbnails, or visual narratives.
ur-grue/autopunk-media-skills/skills/image-prompting/midjourney/cinematic-shot-prompt Skill
21★ repoGenerates a film-grammar-aware Midjourney prompt from a scene description — specifying shot type, lens, lighting, color grade, and mood — that produces an image with the visual language of a cinematically composed film still.
ur-grue/autopunk-media-skills/skills/image-prompting/midjourney/style-reference-prompt Skill
21★ repoBuilds a Midjourney prompt that precisely captures a defined visual style or artistic reference — translating a style description, reference image context, or artistic period into the specific prompt language Midjourney responds to.
ur-grue/autopunk-media-skills/skills/magazine-journalism/editing/fact-check-prompt Skill
21★ repoGenerates a systematic fact-checking checklist from a draft article, categorizing every verifiable claim by type and priority, with the specific verification question and recommended source type for each.
ur-grue/autopunk-media-skills/skills/youtube/pre-production/hook-generator Skill
21★ repoWrite three opening hook options — one per style — for a YouTube video, podcast intro, or documentary opening.