Skill-uri pentru agenți pe care le poți verifica înainte să le instalezi
Skill-uri SKILL.md publice din depozite GitHub cu peste 50 de stele și de la producători, scanate și evaluate. Instalează oricare dintre ele cu o singură comandă în Claude Code, Cursor, Codex, GitHub Copilot sau Gemini CLI.
47.966 de skill-uri din 2.309 depozite · actualizat acum 16 ore
46.854 de skill-uri
- lancet-writingbrycewang-stanford/Awesome-Journal-SkillsUse to structure and hold the length of a Lancet Article main text — Introduction, Methods, Results, Discussion (~3000–3500 words), the Research in context panel, a limited reference list (~30), and a cautious, globally minded Discussion that does not overstate.RedactareFără avertismente★ 1,3 K↓ —
- icse-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when designing or auditing the evaluation of an ICSE research-track paper, covering subject and benchmark selection, baseline fairness, statistical tests and effect sizes as SE reviewers expect them, qualitative-methods rigor, ablations for AI-based techniques, and threats-driven study design.TestareFără avertismente★ 1,3 K↓ —
- imc-writing-stylebrycewang-stanford/Awesome-Journal-SkillsUse when drafting or revising the prose of an ACM IMC measurement paper, covering the first-page measurement finding, making vantage points and methodology auditable, longitudinal framing for a moving Internet, arguing limitations rather than reciting them, writing the Ethics section early, and acmart page-budget discipline.RedactareFără avertismente★ 1,3 K↓ —
- icdm-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when designing or auditing the empirical evaluation for an ICDM (IEEE International Conference on Data Mining) paper - mining-task definition, strong and fairly-tuned baselines, ablations that isolate the named mechanism, scalability curves that test scale claims, and discovery-validity checks that separate real findings from evaluation artifacts.TestareFără avertismente★ 1,3 K↓ —
- icra-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when designing or auditing the experimental section of an ICRA paper — real-robot versus simulation-only evidence, trial counts and success-rate reporting, task distributions and resets, baseline fairness on shared hardware, sim-to-real transfer claims, failure-mode analysis, and the statistics robotics reviewers actually expect.ȘtiințăFără avertismente★ 1,3 K↓ —
- hpca-experimentsbrycewang-stanford/Awesome-Journal-SkillsJournal-specific Claude Code/Codex skill packs covering mainstream journals — AER, QJE, Nature, Cell, 管理世界, 经济研究 & 200+ more — your fast track to getting published. ｜ 覆盖主流期刊的 Claude Code/Codex 期刊技能包，从选题、识别策略到表格规范与审稿回复全流程，助你快速发论文。PlanificareFără avertismente★ 1,3 K↓ —
- run-paid-campaigns-weekly-readgooseworks-ai/goose-skillsStep of the run-paid-campaigns playbook: reads each platform's last mature results window against the allowable cost, as evidence for the week's moves. Run run-paid-campaigns instead; not for direct use.AlteleFără avertismente★ 1,3 K↓ —
- hri-supplementarybrycewang-stanford/Awesome-Journal-SkillsUse when planning the supplementary materials for an ACM/IEEE HRI full paper — above all the video figure that shows the embodied interaction, plus study instruments, extended results, and appendices — deciding what a reviewer must see to judge the interaction versus what belongs outside the 8-page body, all anonymized for double-blind review.MediaFără avertismente★ 1,3 K↓ —
- fse-supplementarybrycewang-stanford/Awesome-Journal-SkillsUse when deciding what belongs in an ESEC/FSE paper body versus its anonymized artifact and appendices, covering the ACM-template page budget, the rule that decision-critical evidence stays inside the reviewed pages, double-anonymous supplementary material, and how to split an empirical-SE paper between body and package.ȘtiințăFără avertismente★ 1,3 K↓ —
- eas-workflowsexpo/skillsHelps understand and write EAS workflow YAML files for Expo projects. Use this skill when the user asks about CI/CD or workflows in an Expo or EAS context, mentions .eas/workflows/, or wants help with EAS build pipelines or deployment automation.OficialDevOpsFără avertismente★ 3,8 K↓ —
- cvpr-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when designing or auditing the experimental program of a CVPR paper, covering benchmark and baseline selection under matched-compute fairness, the ablation study reviewers treat as mandatory, qualitative and failure-case evidence, efficiency metrics tied to the Compute Reporting Form, and generalization tests beyond a single dataset.TestareFără avertismente★ 1,3 K↓ —
- dac-writing-stylebrycewang-stanford/Awesome-Journal-SkillsUse when drafting or tightening the prose of an ACM/IEEE Design Automation Conference (DAC) Research Manuscript, covering the QoR-forward first-page arc, stating the design-automation contribution as a measured delta, fitting a complete argument into six double-column pages plus a references-only page, building column-width EDA figures, and third-person self-citation for double-blind review.RedactareFără avertismente★ 1,3 K↓ —
- eacl-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when designing or auditing the empirical evidence for an EACL paper, covering tuned and LLM baselines, multilingual breadth matched to the claim, significance and variance floors, human-evaluation agreement, data-contamination controls, ablations, and error taxonomies, so that every stated result is measured rather than asserted.ȘtiințăFără avertismente★ 1,3 K↓ —
- ijcai-workflowbrycewang-stanford/Awesome-Journal-SkillsUse when planning an IJCAI or IJCAI-ECAI project timeline from venue fit through abstract registration, full-paper upload, author information, PPI payment, summary-reject risk, author response, notification, camera-ready, in-person presentation, and artifact release.ProductivitateFără avertismente★ 1,3 K↓ —
- iclr-submissionbrycewang-stanford/Awesome-Journal-SkillsUse when auditing an ICLR main-conference submission for OpenReview readiness, double-blind anonymity, page limits, reciprocal reviewing, LLM-use disclosure, dual-submission policy, supplementary material, and desk-reject risk.AlteleFără avertismente★ 1,3 K↓ —
- icsme-workflowbrycewang-stanford/Awesome-Journal-SkillsUse when planning an IEEE ICSME project timeline from venue and track choice through abstract registration, paper submission, the early-decision cut and author-response rebuttal, notification, IEEE Xplore camera-ready, the ROSE-Festival artifact evaluation, and presentation, with backward-planning offsets for a maintenance/evolution paper and honest handling of the single-annual-round calendar.ProductivitateFără avertismente★ 1,3 K↓ —
- imc-related-workbrycewang-stanford/Awesome-Journal-SkillsUse when writing or auditing the related-work and positioning of an ACM IMC paper, covering the measurement literature lanes, positioning against prior datasets and vantage points, delta-first framing, citing the datasets and tools you build on, distinguishing IMC from SIGCOMM/NSDI/PAM prior art, and keeping self-citations double-blind.ȘtiințăFără avertismente★ 1,3 K↓ —
- icse-submissionbrycewang-stanford/Awesome-Journal-SkillsUse when auditing an ICSE research-track submission for HotCRP readiness, covering the mandatory abstract deadline, the 10-page-plus-2-reference-page IEEE format, double-anonymous rules, the open-science Data Availability section, supplementary uploads, and desk-reject triage before the AoE cutoff.ȘtiințăFără avertismente★ 1,3 K↓ —
- icra-submissionbrycewang-stanford/Awesome-Journal-SkillsUse when auditing an ICRA paper for upload — PaperPlaza account and metadata, the 6-page-plus-2-reference-page limit, IEEE two-column template compliance, the double-anonymous rule introduced in the 2026 cycle, video-attachment specs (180 s, 20 MB), dual-submission conflicts with RA-L, and return-without-review triggers.MediaFără avertismente★ 1,3 K↓ —
- hri-camera-readybrycewang-stanford/Awesome-Journal-SkillsUse when preparing the camera-ready of an accepted ACM/IEEE HRI paper — de-anonymizing systematically, completing ACM+IEEE dual-publication metadata (CCS concepts, ORCID, rights/eRights form), delivering every rebuttal promise within the 8-page budget, finalizing the video and de-anonymized archive, and passing production checks.MediaFără avertismente★ 1,3 K↓ —
- iccv-submissionbrycewang-stanford/Awesome-Journal-SkillsUse when auditing an ICCV submission in the weeks before the early-March deadline, covering OpenReview registration and profile completeness, the single same-day paper-plus-supplement upload, the 8-page inclusive format, the 25-submissions-per-author cap, every-author reviewer enrollment, anonymity and media-embargo rules, and desk-reject triage.ȘtiințăFără avertismente★ 1,3 K↓ —
- asc-aso-auditrorkai/app-store-connect-cli-skillsRun an offline ASO audit on canonical App Store metadata under `./metadata` and surface keyword gaps using Astro MCP. Use after pulling metadata with `asc metadata pull`.AlteleFără avertismente★ 1,1 K↓ —
- icalp-workflowbrycewang-stanford/Awesome-Journal-SkillsUse when planning an ICALP (EATCS) campaign backward from its single annual February deadline, through abstract registration, the anonymous submission, the Track B rebuttal window, the April notification, and the LIPIcs camera-ready and presentation, and when coordinating a full-version (arXiv/ECCC) release alongside the anonymous submission.ProductivitateFără avertismente★ 1,3 K↓ —
- hpca-submissionbrycewang-stanford/Awesome-Journal-SkillsUse when auditing an HPCA submission for the two-step July gate on HotCRP, the 11-page main-body limit, the IEEE template, double-blind anonymity plus the all-authors reference rule, the AI-use disclosure, artifact-link scrubbing, and final-week sequencing before the paper deadline.ȘtiințăFără avertismente★ 1,3 K↓ —
ai-eval-plan
mohitagw15856/pm-claude-skills
PlanificareActualizat 23 oct. 2026
De la autor
Design an evaluation plan for an LLM or AI feature before shipping it. Use when asked how to evaluate a prompt/model/agent, set up an eval harness, define quality metrics for an AI feature, or build a regression gate. Produces an eval plan — task definition, datasets, metrics & rubrics, baselines, automated + human evals, a pass bar, and a regression gate.
Instalare
npx skills add mohitagw15856/pm-claude-skills --skill ai-eval-plan -a claude-code
Se instalează în .claude/skills/ai-eval-plan/ · Fiecare comandă descarcă skill-ul direct de pe GitHub cu utilitarul open source skills.
Descarcă .zip
Identic octet cu octet cu commit-ul scanat, cu licența depozitului și un fișier SOURCE.txt.
La ce are acces
Doar instrucțiuniNu am văzut acces la rețeaLicență: MIT
Verificări de siguranță pe SKILL.md
Niciun avertisment.
De ce 88
Securitate100
Proveniență78
Întreținere100
Licență100
Adopție51
Fișiere (1)
- SKILL.md