Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
49,459 skills from 2,407 repositories · updated 21 minutes ago
48,360 skills
- ppopp-workflowbrycewang-stanford/Awesome-Journal-SkillsUse when planning a PPoPP submission campaign end to end, sequencing the summer paper deadline, the author-response rebuttal window, notification, the post-acceptance CGO-shared artifact-evaluation round, the camera-ready, and the presentation inside the co-located HPCA/CGO/PPoPP/CC week.ProductivityNo warnings★ 1.4K↓ —
- pldi-submissionbrycewang-stanford/Awesome-Journal-SkillsUse when auditing a PLDI submission for HotCRP readiness — the single annual November deadline, the 20-pages-of-text-excluding-bibliography cap in single-column acmsmall format, double-blind hygiene across tool names and repositories, dual-submission rules, and summary-rejection triggers before the cutoff.ProductivityNo warnings★ 1.4K↓ —
- sci-workflowbrycewang-stanford/Awesome-Journal-SkillsUse when deciding which sci-* sub-skill to invoke next, or when sequencing a manuscript from significance test through reviewer rebuttal for Science (AAAS). Routes — it does not replace — the specialized skills.ProductivityNo warnings★ 1.4K↓ —
- soda-submissionbrycewang-stanford/Awesome-Journal-SkillsUse when preparing or auditing a SODA (ACM-SIAM Symposium on Discrete Algorithms) submission — the no-page-limit full-version norm, the title-page abstract, 11-point single-column letter format, lightweight double-blind rules, HotCRP entry, and the July AoE deadline with its summary-rejection triggers.ProductivityNo warnings★ 1.4K↓ —
- socc-submissionbrycewang-stanford/Awesome-Journal-SkillsUse when auditing an ACM SoCC (Symposium on Cloud Computing) research-paper submission for HotCRP readiness, covering the two-round abstract+paper deadlines, the acmart/sigconf 12-page (full) or 6-page (short) budget with unlimited references, dual-anonymous review, the systems-and-data reproducibility posture, and desk-reject triage before the AoE cutoff.ScienceNo warnings★ 1.4K↓ —
- tacas-workflowbrycewang-stanford/Awesome-Journal-SkillsUse when planning a TACAS (ETAPS) project timeline from category choice and venue fit through the EasyChair paper deadline, the mandatory tool-paper artifact deadline, the rebuttal window, notification, the voluntary post-acceptance artifact round, LNCS camera-ready, and presentation, with backward-planning offsets that account for TACAS's single annual round and its parallel paper+artifact review.ProductivityNo warnings★ 1.4K↓ —
- secrets-manageritsmostafa/aws-agent-skillsAWS Secrets Manager for secure secret storage and rotation. Use when storing credentials, configuring automatic rotation, managing secret versions, retrieving secrets in applications, or integrating with RDS.DevOpsNo warnings★ 1.2K↓ —
- cloudwatchitsmostafa/aws-agent-skillsAWS CloudWatch monitoring for logs, metrics, alarms, and dashboards. Use when setting up monitoring, creating alarms, querying logs with Insights, configuring metric filters, building dashboards, or troubleshooting application issues.DevOpsNo warnings★ 1.2K↓ —
- cognitoitsmostafa/aws-agent-skillsAWS Cognito user authentication and authorization service. Use when setting up user pools, configuring identity pools, implementing OAuth flows, managing user attributes, or integrating with social identity providers.DevOpsNo warnings★ 1.2K↓ —
- bedrockitsmostafa/aws-agent-skillsAWS Bedrock foundation models for generative AI. Use when invoking foundation models, building AI applications, creating embeddings, configuring model access, or implementing RAG patterns.DevOpsNo warnings★ 1.2K↓ —
- lambdaitsmostafa/aws-agent-skillsAWS Lambda serverless functions for event-driven compute. Use when creating functions, configuring triggers, debugging invocations, optimizing cold starts, setting up event source mappings, or managing layers.DevOpsNo warnings★ 1.2K↓ —
- claude-authenticityagentscope-ai/OpenJudgeDetect whether an API endpoint is backed by genuine Claude (not a wrapper, proxy, or impersonator) using 9 weighted rule-based checks that mirror the claude-verify project. Also extracts injected system prompts from providers that override Claude's identity. Fully self-contained — copy the code below and run, no extra packages beyond httpx. Use when the user wants to verify a Claude API key or endpoint, check if a third-party Claude service is authentic, audit API providers for Claude authenticity, test multiple models in parallel, or discover what system prompt a provider has injected.TestingNo warnings★ 1.1K↓ —
- stoc-submissionbrycewang-stanford/Awesome-Journal-SkillsUse when auditing a STOC (ACM Symposium on Theory of Computing) submission for HotCRP readiness — the abstract + table-of-contents + first-12-pages reading rule, single-column 11-point format, double-blind hygiene, the SIGACT prior/simultaneous-publication policy, and deadline-week sequencing before the November cutoff.OtherNo warnings★ 1.4K↓ —
- hf-cloud-sagemaker-production-defaultshuggingface/skillsCreate a SageMaker endpoint (real-time, real-time scale-to-zero, or async) with autoscaling, CloudWatch alarms, and tagging enabled by default. Use this skill whenever about to create a SageMaker endpoint, write deployment code that calls `create_endpoint`, or finalize a deployment after the image URI and IAM role are known. Provides deploy.py for real-time endpoints, deploy_ic.py for real-time endpoints that scale to zero instances via inference components, and deploy_async.py for async endpoints (also scale-to-zero). This is the last step in the SageMaker deployment workflow. Never generate a bare `create_endpoint` call without these defaults — endpoints without autoscaling or alarms are demos, not deployments.OfficialDevOpsNo warnings★ 11.3K↓ —
- red-green-proofalirezarezvani/claude-skillsTurns a suspected bug into a proven one. Verify the cause against reality before claiming it, write a test that FAILS on the current code, apply the fix, watch it pass — then revert the fix and confirm the test goes red again, because a test that passes both ways proves nothing. Invoked bare after a debugging conversation, it takes the target from context rather than asking. Use when fixing a bug, investigating an incident, hardening a flaky area, or when asked to "add tests that reveal the bug". Triggers on "/red-green-proof", "prove the bug", "red-green", "make the test fail first", "is that test load-bearing", "reveal the bug with a test".TestingNo warnings★ 29.3K↓ —
- trip-plannano-muse/nanoMusePlan a trip end to end (itinerary by day, a packing list to tick off, a budget, and the calendar checked for conflicts) as pages in the workspace. Use when the user is going somewhere for more than a day and wants a plan, an itinerary or a packing list.PlanningNo warnings★ 3.2K↓ —
- vldb-submissionbrycewang-stanford/Awesome-Journal-SkillsUse when auditing a PVLDB submission before a monthly deadline, covering the mandatory abstract on the 25th, the CMT window, the 1st-of-month 5:00 PM Pacific cutoff, category and page-budget choice, single-blind cover-page requirements, the per-month and per-year author caps, and desk-reject hazards specific to VLDB.PlanningNo warnings★ 1.4K↓ —
- hf-cloud-serving-image-selectionhuggingface/skillsPick the right serving container for a SageMaker model deployment and find its current image URI. Use this skill whenever about to deploy a model to a SageMaker endpoint and an image URI needs to be chosen — including when the user says "deploy this LLM", "host this HuggingFace model", "serve this fine-tuned model", "deploy this embedding model", "host a reranker", "serve a sentence-transformers model", or when about to hardcode any container URI in deployment code. HuggingFace-curated Deep Learning Containers are ALWAYS preferred: HuggingFace vLLM (LLMs and generative rerankers), HuggingFace vLLM-Omni (multimodal), TEI (embeddings/cross-encoder rerankers), HF Inference Toolkit (other transformers). Generic images (AWS vLLM, DJL-LMI, SGLang) are used only when no HuggingFace image is compatible — never merely because they carry a newer version. Never hardcode a container URI from memory and never default to TGI. Prevents stale-image failures and wrong-region URIs.OfficialMediaNo warnings★ 11.3K↓ —
- uist-submissionbrycewang-stanford/Awesome-Journal-SkillsUse when performing the final pre-upload audit of a UIST paper in PCS — the abstract-then-paper deadline pair, 10-page/5-page two-column limits with desk-reject enforcement, anonymous acmart options, video-figure and supplementary uploads, the prior-work overlap rule, and deadline-week sequencing.MediaNo warnings★ 1.4K↓ —
- sigir-workflowbrycewang-stanford/Awesome-Journal-SkillsUse when planning a SIGIR project calendar — backward-planning from the January-pattern abstract/paper deadlines to the July conference, sequencing evidence freeze, significance testing, and anonymization, coordinating multi-track decisions, and wiring the SIGIR/ECIR/CIKM/WSDM/SIGIR-AP fallback calendar into one pipeline.ProductivityNo warnings★ 1.4K↓ —
- gtm-strategykostja94/marketing-skillsWhen the user wants to plan go-to-market strategy, GTM framework, or market entry. Also use when the user mentions "GTM," "go-to-market," "market entry," "new market," "repositioning," "PLG," "sales-led," "product-led," "marketing-led," "ICP," "buyer persona," "GTM motion," or "market expansion." For launch checklist, use product-launch.MarketingNo warnings★ 1.1K↓ —
- heading-structurekostja94/marketing-skillsWhen the user wants to write or optimize H1-H6, fix heading hierarchy, improve content structure, rewrite an H1, or align headings with page intent. This skill owns actual heading changes; page-metadata may only check and report metadata-to-heading alignment.WritingNo warnings★ 1.1K↓ —
- wacv-submissionbrycewang-stanford/Awesome-Journal-SkillsUse when auditing a WACV submission before an OpenReview round deadline, covering the Round 1 vs Round 2 choice, the Applications vs Algorithms track field, the 8-page-including-figures limit, double-blind anonymity and OpenReview-profile requirements, the anonymized supplement, dual submission, and desk-reject triage.PlanningNo warnings★ 1.4K↓ —
- planning-with-filesOthmanAdi/planning-with-filesPersistent file-based planning for multi-step AI-agent work. Keeps task_plan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected project planning context. Automatic recovery reads project planning files only. Explicit session-catchup.py --metadata reads same-project local agent session records and emits aggregate counts only; --replay may emit bounded nonce-framed excerpts. Optional gated mode can request continuation only when the host supports it and never runs commands declared in Markdown. The skill has no network upload path. Use for research or work needing 5+ tool calls.PlanningNo warnings★ 27.9K↓ —
stripe-docs
fcakyon/claude-codex-settings
EngineeringUpdated 4 hours ago
From the author
Use when the user or agent needs to read, search, or look up Stripe documentation or API reference. Prefer this over curl or WebFetch for any docs.stripe.com content. Use to fetch gated documentation.
Install
npx skills add fcakyon/claude-codex-settings --skill stripe-docs -a claude-code
Installs to .claude/skills/stripe-docs/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Download .zip
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Instructions onlyUses the networkLicence: MIT
Safety checks on SKILL.md
No warnings.
Why 88
Security100
Provenance77
Maintenance100
Licence100
Adoption50
Files (1)
- SKILL.md