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.
49,492 skills from 2,391 repositories · updated 17 hours ago
48,451 skills
- 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↓ —
- 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↓ —
- 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↓ —
- 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↓ —
- 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↓ —
- aaai-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when designing or auditing AAAI experiments for the broad-AI program committee, including baselines, ablations, statistical significance, robustness, human evaluation, AI-for-Social-Impact and alignment/safety evidence, compute and cost reporting, and reproducibility-checklist alignment for Phase-1 survival.OtherNo warnings★ 1.4K↓ —
- vis-related-workbrycewang-stanford/Awesome-Journal-SkillsUse when positioning an IEEE VIS submission against the visualization literature across TVCG, the six VIS areas, EuroVis/CGF, PacificVis, and adjacent HCI/graphics venues, writing delta-first contrast rather than a citation catalog, keeping self-citations double-blind when opted in, and handling concurrent, preprint, and prior-version overlap for a TVCG journal article.WritingNo warnings★ 1.4K↓ —
- uai-related-workbrycewang-stanford/Awesome-Journal-SkillsUse when positioning a UAI submission within the probabilistic reasoning, graphical-model, causality, and Bayesian ML literature, covering PMLR archival status of recent UAI volumes, double-blind self-citation discipline, concurrent arXiv and workshop versions, and the cross-community citation coverage UAI reviewers check first.ScienceNo warnings★ 1.4K↓ —
- 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↓ —
- sidebar-generatorkostja94/marketing-skillsDeprecated compatibility entry for Sidebar construction. This component is now maintained in Bricks; install and use component-builder to build a new Sidebar.OtherNo warnings★ 1.1K↓ —
- atc-writing-stylebrycewang-stanford/Awesome-Journal-SkillsUse when drafting or revising an ATC (ACM SIGOPS Annual Technical Conference, formerly USENIX ATC) systems paper — writing a self-standing two-page extended abstract for the round-one gate, structuring the implementation-and-measurement narrative, reporting costs beside gains, and holding the two-column 12-page budget.WritingNo warnings★ 1.4K↓ —
- acmmm-workflowbrycewang-stanford/Awesome-Journal-SkillsUse when planning the end-to-end ACM MM (ACM Multimedia) campaign calendar — from thematic-area scoping and track choice, through the April OpenReview abstract/paper/supplement chain, the June anonymous rebuttal, the July decision, the August camera-ready, and the November presentation in Rio, with the right skill invoked at each stage.ProductivityNo warnings★ 1.4K↓ —
- ase-supplementarybrycewang-stanford/Awesome-Journal-SkillsUse when deciding what belongs in the 10-page ASE (IEEE/ACM Automated Software Engineering) paper body versus the artifact and supplementary material, splitting content by decision-criticality so nothing that decides acceptance lives outside the reviewed pages under the 10+2 budget.ScienceNo warnings★ 1.4K↓ —
- acl-supplementarybrycewang-stanford/Awesome-Journal-SkillsUse when organizing appendices and supplementary material for an ACL paper under ACL Rolling Review, covering the mandatory Limitations and optional ethics sections, appendices after references, anonymized software and data archives, the no-cloud-links rule, and deciding what must stay in the 8-page or 4-page body.ScienceNo warnings★ 1.4K↓ —
- acl-writing-stylebrycewang-stanford/Awesome-Journal-SkillsUse when revising an ACL paper for computational-linguistics house style, covering task-first framing, linguistic examples tied to quantitative error analysis, scoping language claims to tested languages, LLM-era claim discipline, anonymous self-reference, Limitations prose, and compressing into the 8-page or 4-page ACL format.WritingNo warnings★ 1.4K↓ —
- ase-writing-stylebrycewang-stanford/Awesome-Journal-SkillsUse when shaping the prose and structure of an ASE (IEEE/ACM Automated Software Engineering) research paper, covering the automation-first first-page arc, stating the automated task precisely, keeping the tool runnable and the model-swap test in mind, threats-as-argument, and the 10+2 page discipline on the ACM acmart template.WritingNo warnings★ 1.4K↓ —
- colm-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when designing or auditing the empirical core of a COLM paper — contamination analysis for evaluation data, fair baselines under matched prompting and compute, pinned model versions and decoding parameters, uncertainty over runs and samples, scaling coverage, and honest reporting of API-model comparisons.ScienceNo warnings★ 1.4K↓ —
- chi-writing-stylebrycewang-stanford/Awesome-Journal-SkillsUse when drafting or revising the prose of an ACM CHI paper — contribution statements, structure for mixed reviewer audiences, participant voice, calibrated claims, accessible and bias-free writing, and length discipline in a venue that reviews words against contribution instead of pages.WritingNo warnings★ 1.4K↓ —
- colt-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when deciding whether a COLT (Conference on Learning Theory) paper needs numerical content at all — COLT has no experiments requirement — and, when numerics genuinely help, designing small illustrative simulations that visualize a proved bound, a separation, or a phase transition without diluting the theory.MediaNo warnings★ 1.4K↓ —
- cikm-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when designing or auditing the empirical program of a CIKM paper — matching evidence to the claim's lanes across retrieval, mining, and knowledge-management evaluation cultures, choosing datasets and baselines that survive a blended panel, isolating the boundary mechanism, and meeting applied-track deployment-evidence bars.DevOpsNo warnings★ 1.4K↓ —
- cav-writing-stylebrycewang-stanford/Awesome-Journal-SkillsUse when revising a CAV (Computer Aided Verification) paper for a precise verification contribution on the first page, an explicit soundness/completeness statement, theorem-and-proof discipline in the LNCS page budget, fair benchmark claims, honest scope and limits, and double-blind wording for the anonymized categories.WritingNo warnings★ 1.4K↓ —
- conversion-optimizationkostja94/marketing-skillsWhen the user wants to improve conversion rates, run A/B tests, optimize funnels, or reduce friction. Also use when the user mentions "CRO," "conversion rate optimization," "A/B test," "split test," "funnel optimization," "checkout optimization," "form optimization," or "conversion funnel." For pricing psychology, use pricing-strategy.MarketingNo warnings★ 1.1K↓ —
- cold-start-strategykostja94/marketing-skillsWhen the user wants to plan cold start, get first users, or launch a new product with zero traction. Also use when the user mentions "cold start," "cold start problem," "first users," "seed users," "finding users," "finding early users," "Fiverr Upwork," "comment outreach," "Twitter search users," "product launch strategy," "0 to 1 growth," "early-stage acquisition," "launch channels," "get first customers," "Product Hunt launch," "AppSumo," "LTD," "indie hacker," "bootstrapping," or "solo founder." For directory listing copy and submissions, use directory-submission. For Product Hunt day-of execution, use product-hunt-launch. For GTM motion design, use gtm-strategy.DesignNo warnings★ 1.1K↓ —
- openspec-apply-changeMemeMeow-Studio/MemeMeowImplement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.ProductivityNo warnings★ 1.3K↓ —Also in 1 other repo
huggingface-community-evals
huggingface/skills
OfficialOtherUpdated 6 days ago
From the author
Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .eval_results publication, or community-evals automation.
Install
npx skills add huggingface/skills --skill huggingface-community-evals -a claude-code
Installs to .claude/skills/huggingface-community-evals/ · 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
Runs bundled scriptsNo network use seenLicence: APACHE-2.0
Safety checks on SKILL.md
- Ships scripts we have not reviewedLow
Why 88
Security85
Provenance100
Maintenance100
Licence100
Adoption63
Files (6)
- SKILL.md
- examples/.env.example
- examples/USAGE_EXAMPLES.md
- scripts/inspect_eval_uv.py
- scripts/inspect_vllm_uv.py
- scripts/lighteval_vllm_uv.py