The catalog
608,119 rows, by stacks then stars
baserproject/baser-skills/.agents/skills/markdown-to-html Skill
0★ repoConvert Markdown text or .md files into HTML fragments or full HTML documents. Use when the user asks to transform Markdown into HTML, preserve headings/lists/links/code blocks, or generate browser-ready HTML from Markdown. 日本語で「マークダウンをHTMLに変換して」と頼まれたときにも使う。
pealco/regatta-scheduler Skill
0★Build and revise compact rowing regatta heat sheets from RegattaCentral boats and boat-athletes exports. Use when asked to create, import, deconflict, retime, validate, or review a rowing regatta schedule or Google Sheet using RegattaCentral exports, boat entries, athlete rosters, lane limits, lunch breaks, flight grouping, duplicate-boat checks, athlete conflict windows, age/category grouping, or before/after schedule reports.
WIHATN/vault-crystallize Skill
no license0★Use when working in an agent-managed knowledge vault and the user says "结晶", "结晶一下", "crystallize", "蒸馏", or "distill"; also use for explicit checkpointing of vault recovery state or source-to-evidence extraction. Do not use for generic cleanup, deep audit, doc sync, memory sync, or polished-summary requests unless those trigger words or explicit evidence intent appear.
vikram-rajput/contextforge/skills/contextforge Skill
no license0★ repoUse this skill when creating, organizing, validating, or publishing reusable AI context packs, skills, rules, domains, and agent instructions for AI IDEs.
The same file is in 1 other repository
kevinastuhuaman/ai-kevinastuhuaman/public/.well-known/agent-skills/site-navigation Skill
no license0★ repoNavigate Kevin Astuhuaman's recruiting portfolio and retrieve public-safe profile, resume, project, proof, and contact information.
Suraj787/motif Skill
no license0★Use when an AI coding agent must design, build, improve, audit, or migrate any web interface and needs to choose the least-complex interface and interaction that achieves a real user outcome, governed by evidence rather than aesthetic impulse.
oradotai/agent-ready Skill
0★Build software that AI agents can see, use, and pay. Use this skill when building or extending a product, API, web app, SaaS, or service an agent might use on a user's behalf - designing API endpoints, auth flows, public docs, an MCP server, MCP Apps / interactive agent UI, llms.txt, structured data, or checkout. It bakes agent-readiness in at build time around three questions — can agents SEE you (discovery + identity), USE you (auth, integration, in-agent UX and human handoff), and PAY you (agentic commerce) - across the five layers of the Ora agent-readiness standard. Trigger phrases include make this agent-ready, build an API agents can use, add an MCP server, render UI in Claude or ChatGPT, MCP Apps, write an llms.txt, agent checkout, agentic payments, expose this to AI agents. Not for general SEO, human-only UX, or internal infra with no external agent surface.
reverie2129/hive-optimization-skill-en/skills/hive-optimization-skill Skill
0★ repoReviews and optimizes Hive on MapReduce jobs (table design, HQL, JOINs, data skew, MR tuning). Contains 26 citable rules. Use when optimizing HQL, diagnosing slow Hive jobs, handling skew, or designing partitioned/bucketed tables. Always check rules/ before advising and cite rule names.
noodlebindev/workflow-triage Skill
0★Manual-invoke orchestration gate. Use ONLY when the user explicitly asks how a task should be executed — e.g. "triage this", "should this be a workflow?", "inline or subagents?", "how should I run this?". Returns a structured verdict (inline / few-subagents / dynamic-workflow / loop / hybrid / do-not-automate) plus execution shape — never a script, never a launch. Does NOT scan proactively or run on a loop.
Ninadnj/mcp-skills-kit/skills/doc_qa Skill
no license0★ repoAnswer questions grounded in a set of documents (RAG), with citations.
Curtisflo/karyon/skills/antibody-qc Skill
no license0★ repoDeterministic developability/liability gate for GENERATED antibody Fv sequences (e.g. an AlphaFold-Multimer / RFdiffusion+ProteinMPNN designed binder, or an antibody language model) with karyon. Use AFTER designing an antibody/binder and BEFORE expressing or advancing it — answers "is this Fv developable, or does it carry a liability that makes it undruggable?" with a pass/fail verdict and legible per-reason explanations (an unpaired cysteine, an N-glycosylation sequon in a CDR, an extreme CDR-H3 length or isoelectric point — and, disclosed, the deamidation/isomerization/oxidation hotspots, fragmentation sites, and hydrophobicity/charge proxies even approved antibodies carry). Pure stdlib — no GPU, no network, no numpy. Input is the VH (+VL) amino-acid sequence; single-domain VHH/nanobodies are supported.
lanluyu/research-reports/skills/policy-sources Skill
0★ repo美国政策 / 制裁 / 监管 / 地缘类查询的权威信息源(中文)。当用户询问美国政府政策、OFAC 制裁、Treasury / BIS / State Department / DOJ / White House 公告、国会法案、CRS 报告、智库分析(CSIS、Atlantic Council、CNAS、FDD 等)或相关地缘政治话题时调用此 skill。包含域名白名单(GOV / THINK / MEDIA 三类)、官方 API 端点(Federal Register、Congress.gov、OFAC SDN)、付费墙处理策略和默认查询参数。
Arianassskm/VOC-FACT-Structuring/plugins/voc-fact-structuring/skills/voc-fact-structuring Skill
0★ repoExtract Fact, Action, Context, and Trigger from each VOC item. FACT 结构化:逐条拆解用户原话中的事实、行为、场景、触发点与机会识别。 Use when the user asks in Chinese or English for VOC analysis, customer feedback analysis, 用户反馈, 客户之声, 产品机会, 需求洞察, or this pipeline step: FACT 结构化 / VOC FACT Structuring.
The same file is in 1 other repository
Subho4531/solana-agent-commerce-skill/skill Skill
0★ repoSolana-first agent commerce and x402 skill for building paid APIs, paid MCP servers, and buyer agents that use Solana USDC/SPL/Token2022 payments. Use when implementing x402 on Solana, monetizing API endpoints or MCP tools, adding agent spend policies, pricing paid agent workflows, testing Solana devnet x402 payments, reconciling payment receipts, or hardening x402 payment flows against replay, stale quotes, route confusion, concurrency, and overspending.
faber-craft/faber-resume/skills/faber-ats Skill
0★ repoChecks resume content and structure against ATS (Applicant Tracking System) parsing requirements and a target job description. Returns a structured report with keyword match percentage, missing-keyword gap table, section header validation, date consistency check, metric density score, and concrete formatting recommendations. TRIGGER when: user asks if their resume will pass ATS, wants a keyword match analysis, asks about resume compatibility, pastes a job posting alongside their resume for comparison, or asks "will this get through the filters?" Also triggers when user mentions ATS, applicant tracking, keyword optimization, resume scanning, or job match percentage. DO NOT TRIGGER when: user wants to write or rewrite resume content (use faber or faber-bullet), wants a cover letter, or wants general career advice.
MrBridgeHQ/short-study-claude/skills/short-study Skill
0★ repoUse when turning a simple question into a one-pager data study - a clearly reframed question, a light analysis of a dataset (comparison, correlation, or distribution), and an easy-to-read answer grounded in real, computed figures - plus its promotion assets: anchor links to the study page and social posts for X, Bluesky, and LinkedIn. Triggers on "make a short study", "one-pager study", "is X rated higher than Y", "are A and B correlated", "data study", "study plus social posts", "anchors and posts for a study", EN or FR. Every figure is computed by a script, never estimated.
Learner-Geek-Perfectionist/ai-call-flow-navigator/skills/ai-call-flow-navigator Skill
0★ repo由用户通过 `$ai-call-flow-navigator` 加主题参数(Codex)或 `/ai-call-flow-navigator` 加主题参数(Claude Code)显式调用;在当前本地源码项目中定位主题对应的唯一入口,并向 Android Studio 的 AI Call Flow Navigator 插件投递静态与实时联合分析请求。仅在用户明确输入该 Skill 命令时使用,不要隐式触发。
kyt19970215/codex-skill-evolution-framework/skills/codex-capability-router Skill
0★ repoRoute Codex work to the best installed skills, plugins, apps, MCP tools, or safe candidate plugins, and enforce native use of selected capabilities. Use when the user names an installed capability, a task's dominant artifact or specialist workflow directly matches one, or the task needs plugin discovery, Product Design, creative production, business/data work, documents/slides/sheets/PDFs, GitHub, browser/computer use, or role-specific plugins.
Content localization orchestrator
satishTheLegend/content-localization-orchestrator Skill
0★Orchestrates end-to-end localization of CONTENT (marketing, docs, UX copy, growth assets) — not just code strings — across many locales the right way: per-locale strategy, a persisted glossary + translation memory, culture-aware transcreation instead of literal translation, a cultural-sensitivity and regulated-content QA gate, RTL and text-expansion layout adaptation, and a source-sync map that re-localizes only what changed. Plugs around an existing TMS (Crowdin/Lokalise/Phrase) or runs from files; keeps all locales consistent as the source evolves. Use whenever the user wants to localize, translate, or "go global" with their website, docs, app copy, or marketing into other languages — even if they don't explicitly ask for orchestration; wants to expand into a market or add locales; says their translations sound robotic, literal, inconsistent, or off-brand; wants to transcreate or culturally adapt copy; wants a glossary or translation memory; mentions RTL, Arabic, Hebrew, Japanese, or CJK adaptation; needs cultural or compliance review of translated content; or wants to keep translations in sync after editing the source. Trigger even without the word "localize" — e.g. "make this work for Germany" or "why do our French pages read so badly".
PalmCoast/higgsfield-ai-plugin/skills/higgsfield-generate Skill
no license0★ repoGenerate images/videos via Higgsfield AI. Default: GPT Image 2 for images/design/text, Seedance 2.0 for video, Nano Banana 2/Pro for character/reference image work, Marketing Studio for ads with avatars/products/hooks, settings, plus Soul V2/Cinema/Cast/Location and Kling 3.0. Use when: "generate an image", "make a video", "animate this photo", "image-to-video", "edit/stylize/remix this image", "produce a clip", "create an ad", "make a UGC video", "product demo", "unboxing", "brand video", "presenter video", "import product from URL", "create avatar for ad", or "analyze video virality". Supports image-to-image, image-to-video, references, job/upload IDs, and Marketing Studio. Chain with higgsfield-soul-id for face/identity consistency. Virality Predictor (`brain_activity`) analyzes video virality: hook strength, attention, retention, distraction risk, and creative score. NOT for: Soul Character training (use higgsfield-soul-id), product photoshoots, marketplace listing cards, text/chat/TTS tasks.
The same file is in 15 other repositories
plelevier/gcyphrq/skills/gcyphrq Skill
0★ repoUse for querying graph data with Cypher — service dependencies, infrastructure topology, blast radius analysis, path tracing, graph mutations. Runs against JSON graph files with an in-memory Cypher engine.
Gmail secondary inbox cleaner skill
federicodeponte/gmail-secondary-inbox-cleaner-skill Skill
0★Install, configure, share, or adapt a reusable Floom worker that cleans and classifies a non-primary Gmail inbox. Use when the user wants a secondary Gmail inbox cleaner, an inbox triage worker template, a Floom worker share package, or a skills.sh/Floom Skills package for Gmail cleanup automation.
Zions-store/project-ledger/project-docs Skill
0★ repoInitialize or safely update the three-document project knowledge system (AGENTS.md + PROJECT_STATE.md + DEVLOG.md). Use when the user says "init docs", "建立文档体系", "project-docs", "更新项目状态", or when a project needs a living documentation framework.
brlin-tw/developing-bash-scripts Skill
no license0★Provide guidelines on how to develop bash shell scripts that are compliant with project standards. Should be used when generating, modifying, or reviewing bash scripts.
xenonbyte/xsk/skills/archive-req Skill
0★ repoArchive the active requirement document into .xsk/requirements/archive/ and leave zero active docs.
codeeater/where-to-plai-plugin/plugins/where-to-plai/skills/advisory-board Skill
no license0★ repoThis skill should be used to convene the experimental Where-to-Play advisory board — a panel of named advisor agents that review the current Worksheet 2 and/or Worksheet 3 and surface diverse perspectives, disagreements and assumptions to test. Triggers include "convene the advisory board", "advisory board review", "what would the board think", "get diverse perspectives on our worksheets", "review our where to play with the advisors", "panel review", "get a second opinion on our map". The board provokes — it never scores or picks a market.
satishTheLegend/monetization-architect Skill
0★Turns any pricing or packaging question into a complete, stateful, evidence-driven monetization SYSTEM — not a one-shot Good-Better-Best table. Carries the work across eight phase-gated stages: intake, value-metric discovery (scored, not guessed), segmentation and a valid willingness-to-pay study (Van Westendorp + Gabor-Granger with sample sizing), tier and fence architecture, revenue/elasticity modeling against margin floors, and — the part everyone fears and no skill covers — a SAFE live price-migration plan with grandfathering, cohort rollout, comms templates, churn guardrails, and an explicit, pre-frozen ROLLBACK trigger, then instrumentation and a post-change reconciliation of actuals vs. model. Ships runnable Python (VW, Gabor-Granger, scenario modeler, migration planner) and a file-backed ledger so gates are deterministic. Use whenever the user mentions pricing, packaging, tiers, "how should I price", price increase, repricing, repackage, value metric, willingness to pay, freemium, free trial, usage- or seat-based pricing, monetization, ARPA, or expansion revenue — even if they only ask for a quick tier table or "what should I charge", and even if they don't say "system" or "plan". ALWAYS engage for any live price change so a rollback and guardrails exist before it ships.
satishTheLegend/talk-and-keynote-architect Skill
0★Turns a fuzzy talk idea into a tight, rehearsed, time-boxed talk — and owns the spoken-narrative + rehearsal layer that slide tools skip. Captures the brief (audience, venue, EXACT time budget, single takeaway, desired action); locks ONE through-line and a NAMED structure before any slides exist; sequences tension→resolution beats to the clock with minutes per beat; writes a spoken-language script with [pause]/[0:00] markers, callbacks and a signature line; designs the cold open and closing call-to-action; produces a per-beat SLIDE BRIEF (message titles + what each visual must do, no bullet dumps) and hands the actual deck to universal-designer; war-games hostile and gotcha Q&A with bridges and graceful "I don't know" answers; runs a rehearse-and-tighten loop where a timing engine measures the real script and FORCES specific cuts; and ships a day-of cue-card kit. Use whenever the user mentions a talk, keynote, conference or lightning talk, demo day, investor-pitch narrative, all-hands, webinar, or speech; wants to structure, script, time, rehearse, or trim a presentation; wants Q&A prep; or mentions stage fright or public-speaking help — even a one-liner like "I have to give a talk next week", and even if they only ask for slides (route slides out, do the talk first).
satishTheLegend/staff-eng-planning Skill
0★Compresses the staff/principal-engineer planning function — turning a fuzzy initiative into a written RFC/design doc, Architecture Decision Records (ADRs), three-point effort estimates, a weighted trade-off matrix, a likelihood×impact risk register, and a phased rollout/backout plan, plus a stakeholder-ready one-pager — BEFORE any code is written. Runs a gate-sequenced lifecycle (triage → framing → options → trade-off → ADRs → estimation → risk → rollout) where deterministic scripts block advancing past gaps. Use whenever the user is starting, scoping, planning, architecting, or estimating a new project, feature, migration, refactor, or initiative — even if they don't explicitly ask for a "plan" or "RFC"; especially when they say "how should I approach X", "should I use A or B", "how long will X take", or "what could go wrong with X". Also use when they want a design doc, ADR, effort estimate, trade-off analysis, risk register, rollout plan, or an exec one-pager. Right-sizes the artifact set (micro/standard/heavy) so small work isn't buried in paperwork. Hands off: ship verification → production-readiness-gate; standing risk → risk-register-csf; existing-design critique → principal-architect-review; adversarial security → threat-model-studio; post-incident → sre-slo-postmortem.
satishTheLegend/ingestion-pipeline-architect Skill
0★Designs and hardens resilient data ingestion / ETL / ELT pipelines end-to-end — source-to-warehouse — and ENFORCES reliability as deterministic phase gates (not advice): source profiling, extraction strategy (batch/incremental/CDC/ stream), schema contracts + drift policy, idempotency + load semantics, blocking data-quality gates with quarantine/dead-letter, dependency-ordered orchestration DAG, safe idempotent backfills, freshness/lineage/anomaly observability, late/out-of-order handling, and a final SLA + failure-mode audit. Emits durable artifacts (source profile, contracts, DQ suite, DAG spec, backfill plan, monitoring config, runbook, audit matrix) recorded in an append-only ledger so each gate is provably PASS/FAIL. Composes with transform generators (dbt, etl) rather than re-emitting SQL. Use whenever the user designs, builds, reviews, or fixes any pipeline moving data from APIs/DBs/files/events into a warehouse or lakehouse, even if they only say "ingest X into Y", "my pipeline broke / has duplicate rows / schema drift / stale data", "set up data-quality / lineage / freshness alerting", "handle CDC / incremental loads / backfills safely", or "make my Airflow/dbt/Spark pipeline reliable" — and even if they don't explicitly ask for governance, planning, or an audit.
OpenSealAI/agent-skills/skills/socialseal-asset-planning Skill
no license0★ repoUse this skill when planning what footage to capture or gather so a SocialSeal blueprint's shot panels can be filled in the Asset Studio clip library. Maps blueprint shots to required clips, identifies coverage gaps, batches capture, and prepares clips for upload and clip-to-shot mapping.
LevyBytes/AI-SKILL-turso-db Skill
0★Use when working with Turso Database, Turso Cloud, libSQL, AgentFS, Turso CLI, Turso Platform API, SDKs, SQL reference, sync, migrations, auth tokens, groups, organizations, vector search, embedded replicas, local development, SQLite compatible databases, or Turso connection code.
bonanyan/circuit-diagram Skill
0★Generate reasonably laid-out circuit diagrams from natural language descriptions or SPICE netlist texts using the SchemDraw Python library. Use when the user asks to draw, render, or generate circuit schematics, electrical diagrams, logic circuits, timing diagrams, flowcharts, or when given SPICE netlists to visualize. Outputs SVG, PNG, or other formats.
latchkey-dev/CI-Doctor Skill
0★Diagnose and fix failing CI/CD pipelines. Use this whenever a build or CI job is red, a pipeline log is pasted in, or the user asks why a build failed, why a job is flaky, or how to fix a CI error on GitHub Actions, GitLab CI, CircleCI, Jenkins, Azure Pipelines, or Bitbucket. Covers npm/yarn/pnpm, pip/poetry, Docker, Maven/Gradle, Go, Cargo, kubectl/Helm, Terraform, git, and test-runner failures, plus exit codes (137/143), OOM kills, "no space left on device", registry timeouts, rate limits (429/toomanyrequests), ERESOLVE, and image-pull errors. Reach for it even when the user just pastes a red log without asking a question, or says "my build broke", "the pipeline keeps failing", "is this flaky?", or "why won't CI pass". Anything that smells like a CI/CD failure qualifies. Built from the Latchkey Learn knowledge base (https://latchkey.dev/learn).
RachidChabane/agentsync/examples/demo-bundle/skills/greet Skill
0★ repoThis skill should be used when the user asks to "greet someone", "say hello", or wants a friendly demo of the plugpack pipeline.
htlin222/skill-with-secret/skill Skill
0★ repoUse when the user wants to read or write their private key/value "stash" — a personal store hosted on their own Cloudflare Worker. Verbs are put/get/ls/rm. The credential is baked into this skill's .env (minted per-user at download), so never ask for or print a key.
LevyBytes/AI-SKILL-pyvisa Skill
0★Use when working with PyVISA - the Python library for controlling measurement instruments over VISA (GPIB, USB, serial/RS-232, TCPIP/Ethernet): ResourceManager, listing/opening resources, read/write/query, VISA attributes and constants, termination characters, timeouts, event handling, the visa shell, backends (pyvisa-py, NI-VISA), and the high-level/low-level API. import pyvisa. Not for the Python stdlib or other instrument-control libraries.
paccodes/covfefe/skills/covfefe Skill
0★ repoSpeak like Donald J. Trump — tremendous, superlative-laden, totally confident — for every turn of the conversation, regardless of subject. Auto-invoke at the first turn of any session and persist thereafter.
maxtechera/hushdrop-skill Skill
no license0★Publish/share an artifact (HTML, Markdown, PDF, file, or whole site) as a private, branded, password-protected link on your own domain. Use when the user says 'publish this', 'share this', 'drop this', 'send them a link', or whenever you've generated an HTML artifact they'll want to open in a browser. Zero-knowledge AES-256, ~1s. Zero-setup via --managed; self-host on your own domain.
satishTheLegend/raise-room-orchestrator Skill
0★Runs a startup fundraise end-to-end as one governed workspace — not just a pitch deck. Assesses raise-readiness and round shape; routes to existing deck skills for the narrative (never rebuilds them); builds and sanity-checks the financial model (burn, runway, cohorts, unit economics); ASSEMBLES a categorized data room and AUDITS a real folder for gaps before investors; runs the investor pipeline as a lightweight CRM with fit scoring and stall detection; prepares an adversarial diligence Q&A war room with every answer grounded in a real data-room artifact (flagging any unsupported claim); compares term sheets and models dilution from the cap table; and stands up a recurring investor-update engine. Keeps deck = model = data room consistent, and refuses to call a data room "investor-ready" while required corporate or financial artifacts are missing. Use whenever the user mentions fundraising, raising a round, pre-seed/seed/ Series A/B, pitching investors, a data room, due diligence, an investor pipeline, a term sheet, dilution, the cap table, runway, an investor update, or "who should I raise from" — even if they only ask for a pitch deck (route it through the deck phase) or never say "plan a raise". Trigger on one-liners like "we're raising a seed round" or "get diligence-ready".
abdalrahman-ahmed/agentflow-template/skills/agentflow Skill
0★ repoDelegate a bounded coding task to a second, background `agy -p` implementer run — on a different model than the one orchestrating — then review its diff and land it yourself. Use whenever the user wants to hand off implementation while staying the reviewer, wants a cheap/fast model for a mechanical task while a stronger model plans or reviews, or explicitly asks to "delegate", "run this on another model", or "spin off a background agy run". Native to Antigravity/agy — no external CLI required. DO NOT USE for tasks small enough to just do inline.
ProdaZhang/aidd/aidd Skill
0★ repoAIDD (AI-assisted Design→Dev) — turn a design discussion into a platform-agnostic handoff package another AI can build from, gated by deterministic checkers. Use for designing any config/rule/UI-heavy system from scratch — game systems, app & SaaS features (plans, quotas, permissions, feature flags, forms, onboarding), tools — or to advance / sync the project spine. One skill: it reads the spine, judges progress, and routes you to the right phase playbook in references/. Domain-neutral; ships with references/.
satishTheLegend/ai-rmf-governor Skill
0★Runs NIST AI RMF (Govern, Map, Measure, Manage) for a solo or small-team builder shipping an LLM/ML feature, turning "it seemed fine in the demo" into a living AI-RMF profile plus a runnable offline eval gate: named failure modes, chosen metrics with acceptable limits AND course-correction triggers, an explicit list of risks deliberately NOT measured and why, and signed-off residual risk. Use whenever the user is building, shipping, reviewing, or changing anything that calls an LLM or ML model — a chatbot, RAG pipeline, agent, classifier, summarizer, extraction step, prompt, or judge — EVEN IF they don't explicitly ask for governance, evals, or risk management. Use proactively when the user says they will "ship", "deploy", "it works", "good enough", or shows a model/prompt with no evals; when they SWAP a model, edit a prompt, or add a use case (re-open Map/Measure); when they mention hallucination, prompt injection, jailbreak, bias, PII/data leakage, over-reliance, cost blowup, or quality regression; or when they ask "is this safe to ship?". Defers generic risk registers to risk-register-csf and generic threat modeling to threat-model-studio, owning the AI-specific harms and eval rigor those do not. Iterative, not one-shot.
clankercode/pirfl Skill
no license0★Runs a fallibilist plan-implement-review-fix loop (PIRFL) for complex tasks, coding, writing, research, document work, and multi-task projects. Use when the user wants robust execution, iterative critique, validation, subagent review, error correction, or review-and-fix loops. Do not use for trivial one-step requests.
yuanyuanyuan430/ganhuo-ai-discoverability Skill
0★Builds the AI-discoverability foundation for a brand, product, project, site, or content cluster by mapping entities, answer intents, crawl access, llms.txt assets, Markdown routes, search indexing, and next-skill routing. Use when the goal is to improve the chance that modern AI systems can discover, understand, recommend, and cite the user's content.
agentic-workflow-kit/technical-design/skills/author-technical-design Skill
0★ repoUse when the user wants to write or update a technical design document from an approved problem frame and system model. Requires approved InputResolution and AgreedSystemModel, proposes DocStructurePlan before durable docs, then produces a DDD-first, technical-solution-compatible design and decisions log.
janole/session-bandit/.claude/skills/doc-sweep Skill
0★ repoReconcile Session Bandit's long-lived docs against recent code changes. Reads each doc's "Last updated:" cursor, diffs git since then, and applies targeted edits to the PRD, architecture decision log, adapter guides, extract design, README files, and the Session Bandit skill. Invoke with /doc-sweep [window], e.g. /doc-sweep 1w. Use when the user asks to "sync docs", "update the docs", "catch the docs up", or after merging a chunk of work.
MrBridgeHQ/ga4-analyst-claude/skills/ga4-analyst Skill
0★ repoUse when retrieving or analyzing Google Analytics 4 (GA4) data - pulling reports via the GA4 Data API, querying the BigQuery events export, choosing dimensions/metrics, building funnels/cohorts/attribution/segment analyses, interpreting sessions/engagement/key-events/channels, or diagnosing GA4 numbers that look wrong. Triggers on "GA4", "Google Analytics 4", "analyticsdata.googleapis.com", "runReport", "GA4 BigQuery export", "events_YYYYMMDD", "engagement rate", "key events", "channel grouping", "(not set)". Claude Code skill.
jpoindexter/design-engineering-canon/skills/dec-accessibility Skill
0★ repoAccessibility foundations for design engineers — WCAG / POUR, semantic-HTML-first then ARIA, keyboard and focus management, inclusive design for permanent/temporary/situational constraints. Use when building or reviewing any interactive UI, adding ARIA, implementing modals/menus/forms, or auditing keyboard operability and focus order.
The same file is in 1 other repository
niuma996/code-hygiene-skills/skills/cleanup-stale-code Skill
0★ repoUse when the user asks to clean up stale, outdated, low-value, or migration-era comments OR expired/deprecated/over-coupled test cases in a codebase. Triggers on phrases like "stale comments", "comment cleanup", "remove migration notes", "test cleanup", "delete test cases", "evaluate tests", "remove dead tests". Skip for adding new doc comments, improving test coverage, or auditing a single file manually.
sanzgiri/pi-skills/repo-findability Skill
0★ repoImproves the discoverability (SEO + GitHub findability) of a GitHub repo and its deployed web app on Vercel, Netlify, Render, or Fly.io. Audits and fixes sitemap.xml, robots.txt, page/site metadata (title, description, canonical, OpenGraph/Twitter cards), a footer attribution signature, GitHub topics, repo description, license, and README, then guides search-engine submission and distribution. Use when the user asks to "improve findability/SEO", "make my repo/site more discoverable", "get indexed by Google", "add a sitemap/robots", "set GitHub topics", "add a signature/credit to my site", or "help people find my project".
Wudi12317/aware-code Skill
0★Use when writing or modifying code. Scans project context and conventions before changes, auto-detects project type (Godot/Rust/Node/Python/etc.), learns from errors with cross-session persistence, reviews quality (correctness, performance, security, tests), syncs docs, and outputs structured summaries. Supports lightweight mode for small changes and rollback for recovery. Do NOT use for purely conversational tasks or quick drafts where review is explicitly skipped.
eidos-agi/eidos-travel-hub/skills/award-booking-playbook Skill
0★ repoStrategy guide for finding award space — when to search, which tools to use, how far out to look, and how to unlock availability that doesn't show online. Pairs with booking-process for execution.
satishTheLegend/llm-app-productionizer Skill
0★Takes a working LLM prototype (chatbot, extractor, classifier, agent, or RAG app) and drives it to a hardened production endpoint through a dependency-ordered, phase-gated lifecycle: profile the prototype, define a versioned golden eval set with numeric pass thresholds, build a reproducible eval harness, harden I/O (schema validation, injection/jailbreak defense, PII redaction, output moderation), add reliability (retries, provider fallback, circuit breaker, timeouts), set cost/latency controls (caching, token budgets, cheap-model routing), instrument OTel-style tracing of prompt/response/tokens/cost/verdict, wire canary + rollback + a CI regression gate, then a severity-ranked readiness audit. Provider-agnostic; composes with existing eval/guardrail tools instead of replacing them; produces artifacts the user keeps. Use when someone wants to ship/productionize/harden an LLM feature, chatbot, AI endpoint, or agent; says it works in the demo but is flaky/expensive/unsafe in prod; wants evals, guardrails, observability, fallbacks, or cost controls; wants to stop hallucinations, PII leaks, or rate-limit breakage; or wants regression testing/CI for prompt or model changes. Trigger even without production: harden my chatbot, my extractor is flaky, this costs too much all qualify.
yusekiya/tikz-figure/skills/tikz-figure Skill
0★ repoCreate publication-quality figures and diagrams as PDF using TikZ/LaTeX, keeping the editable .tex source so the figure can be fine-tuned later. Use this skill whenever the user wants to draw, illustrate, sketch, or generate a figure — a diagram, schematic, geometric construction, vector diagram, flow/graph, or technical illustration — from a text description and/or a reference (e.g. a hand-drawn) image. Trigger for any request to reproduce a sketch as a clean vector PDF, or to produce figures for papers, lecture notes, slides, or exercises across any field (physics, math, CS, engineering, chemistry, biology, economics, …), even if the user never says the word "TikZ" but clearly wants a clean vector diagram in PDF/LaTeX form.
LevyBytes/AI-SKILL-github Skill
0★Use when working with GitHub (the platform on top of git) - creating or managing repositories, branches, and branch protection / rulesets; opening, reviewing, or merging pull requests (merge vs squash vs rebase, CODEOWNERS, required reviews); issues, labels, milestones, issue templates/forms, and Projects; authoring or debugging GitHub Actions workflows (.github/workflows/*.yml - on, jobs, runs-on, uses, with, permissions, matrix, contexts, GITHUB_TOKEN, caching, artifacts, reusable workflows); and the gh CLI (gh pr/issue/run/workflow/release/api); plus keeping your commit email private (GitHub noreply addresses, the block-pushes-that-expose-my-email setting / GH007). Also fires when editing files under .github/ (workflows, CODEOWNERS, ISSUE_TEMPLATE), reading a workflow error, or choosing the right GitHub command/field - even when the user never says "GitHub" by name. Gives faithful, task-routed guidance with worked examples; defers core git mechanics to the git skill.
whatsteamhq/whatsapp-claude-skills/skills/whatsteam-ai-agent Skill
0★ repoBuild a production-grade AI agent that answers your customers on WhatsApp with WhatsTeam — an LLM (OpenAI/Claude) replies to inbound messages inside the 24-hour window, with a hard human handoff for sensitive or low-confidence cases, idempotent webhook handling, opt-out, and a kill switch. Use when the user wants an "AI chatbot / assistant / auto-responder" that handles FAQs, qualifies leads, and covers after-hours on WhatsApp — and wants it safe enough to put in front of real customers, not a naive autonomous bot.
CaptainTimmeow/creator-vault-skill/.agents/skills/creator-vault Skill
0★ repoUse when solo creators, photographers, videographers, YouTubers, or filmmakers need to create or attach a local footage vault, safely ingest SD card or camera media, organize photo/video/audio files by project, generate manifests, or audit a media library. Do not use for editing, color grading, cloud sync, or social media scheduling.
intelligems-io/intelligems-mcp-skills/skills/api-integration-builder Skill
0★ repoUse when a user wants to build scripts, dashboards, alerts, or data pipelines with the Intelligems External API and needs source-backed endpoint guidance.
kazani-351/system-upgrade Skill
0★Run high-leverage system-upgrade meta-prompts on the user's own agent setup and life/work system, not on application code. Use whenever the user wants to audit, optimize, tune, trim, or upgrade their AI harness or agent config (CLAUDE.md, AGENTS.md, hooks, skills, memory, system prompt); reconcile configs that drifted across multiple agents (Claude Code, Codex, etc.); harden against prompt injection or map their deployed attack surface; get strategic clarity on scattered projects or a career; stress-test a big bet before committing months to it; or find what would break if they vanished for a month. Triggers on phrases like "upgrade my system", "tune/audit my harness", "clean up my CLAUDE.md", "run the Fable prompts", or "optimize how you work for me". Goes one prompt at a time, applies reversible changes with diffs, confirms irreversible ones. Not for reviewing application code, a single config-line fix, or creating new skills. Works on any capable agent; benefits from maximum reasoning effort.