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.
49.409 skill-uri din 2.375 de depozite · actualizat acum 10 ore
49.409 skill-uri
- aws-ami-builderhashicorp/agent-skillsBuild Amazon Machine Images (AMIs) with Packer using the amazon-ebs builder. Use when creating custom AMIs for EC2 instances.OficialDevOpsFără avertismente★ 911↓ —
- colt-camera-readybrycewang-stanford/Awesome-Journal-SkillsUse when converting an accepted COLT (Conference on Learning Theory) paper into its PMLR proceedings version, covering de-anonymization, acknowledgements and funding restoration, appendix consolidation into the archival PDF, PMLR volume metadata and BibTeX hygiene, rebuttal-promised edits, and presentation logistics.DocumenteFără avertismente★ 1,4 K↓ —
- conext-workflowbrycewang-stanford/Awesome-Journal-SkillsUse when planning an ACM CoNEXT campaign backward from a deadline, covering the choice between the December and June submission cycles, the mandatory registration step, the one-shot major-revision window, the reproducibility badge opt-in due at submission, PACMNET camera-ready, and presentation — all on CoNEXT's distinctive two-cycles-per-year calendar.ProductivitateFără avertismente★ 1,4 K↓ —
- regression-alerthoangsonww/Claude-Code-Agent-MonitorCompare this period's reliability against the prior period using Agent Monitor data — error rate (APIError/total) and tool-failure rate (PreToolUse→PostToolUse gap) — flag any regression where reliability got worse, and optionally wire a persistent alert rule so the dashboard catches the next regression automatically. Use when checking whether reliability degraded.AlteleFără avertismente★ 1,1 K↓ —
- usability-testingrampstackco/claude-skillsPlan and run usability tests on existing or prototype designs including test design, task scripts, moderation, observation, and findings synthesis. Use this skill whenever the user wants to test usability, run a moderated test, run an unmoderated test, validate a design, find usability issues, or improve task completion. Triggers on usability test, usability testing, moderated test, unmoderated test, task script, think aloud, prototype testing, user testing, design validation, task completion. Also triggers when the user has built something and wants to know if real users can use it before shipping.TestareFără avertismente★ 1 K↓ —
- archivehashgraph-online/awesome-codex-pluginsUse at ship time to merge the spec into the living documentation, delete the staging spec and plan, and ask how to finish.PlanificareFără avertismente★ 1,5 K↓ —
- colm-camera-readybrycewang-stanford/Awesome-Journal-SkillsUse when converting a COLM acceptance into the final paper — the August 7 camera-ready deadline in 2026, de-anonymization and the one-page acknowledgments allowance, folding rebuttal commitments into the text, publishing on OpenReview, releasing artifacts publicly, and planning the October conference in San Francisco.ȘtiințăFără avertismente★ 1,4 K↓ —
- colm-related-workbrycewang-stanford/Awesome-Journal-SkillsUse when positioning a COLM paper inside the fastest-moving literature in ML — triaging arXiv-heavy citations, handling concurrent work fairly, citing model and dataset artifacts correctly, distinguishing COLM's three-edition archive from adjacent venues' archives, and keeping self-citation double-blind safe.ȘtiințăFără avertismente★ 1,4 K↓ —
- edbt-submissionbrycewang-stanford/Awesome-Journal-SkillsUse when auditing an EDBT research-track submission for Microsoft CMT readiness, covering the cycle choice, the paper shape (Regular / Experiments-&-Analysis / Vision), the OpenProceedings/host LaTeX template and per-shape page budget, the 12-month resubmission ban, reproducibility items, and desk-reject triage before the cycle deadline.ȘtiințăFără avertismente★ 1,4 K↓ —
- 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★ 1,4 K↓ —
- team-builder-packagingagentlas-ai/Agentlas-OSUse when generating or auditing a multi-role agent team package with orchestrator, PM Soul, Memory Curator, Policy Gate, workers, eval, QA, handoffs, and runtime adapters.TestareFără avertismente★ 1,6 K↓ —Apare și în 4 alte depozite
- product-hunt-launchkostja94/marketing-skillsWhen the user wants to launch on Product Hunt, prepare a PH submission, or plan launch day (hunter, first comment, timing, upvotes). Also use when the user mentions "Product Hunt," "launch on Product Hunt," "PH launch," "Product Hunt submission," "hunter," "Product of the Day," "upvotes," or "Product Hunt first comment." For multi-platform directory listings and paste-ready copy beyond PH, use directory-submission.PlanificareFără avertismente★ 1,1 K↓ —
- performance-profileralirezarezvani/claude-skillsUse for a slow endpoint, memory leak, CPU spike, large bundle or performance budget in Node.js, Python or Go, before optimizing. Measures before and after with performance_profiler.py, flamegraphs and k6 load tests.TestareFără avertismente★ 29,2 K↓ —
- releasehyhmrright/brooks-lintCut a brooks-lint release: set the version in package.json, propagate it across all four plugin manifests and every version-bearing text file (README badges, docs site metadata), write the CHANGELOG entry, validate, then commit, push, tag, and publish the GitHub release. Triggers when the maintainer asks to "release", "cut a release", "ship a new version", or "bump and publish" brooks-lint. Do NOT trigger for: propagating an already-decided version without releasing (use `npm run bump` directly), CHANGELOG edits alone, or questions about the release process that don't ask to perform it.RedactareFără avertismente★ 1,6 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★ 1,4 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★ 1,4 K↓ —
- flowchartmohitagw15856/pm-claude-skillsTurn a process, workflow, or decision logic into a clean flowchart. Use when asked to diagram a process, map a workflow, visualize steps/branches, or show 'how this works' as a chart. Produces a ready-to-render Mermaid flowchart (renders live in the playground, exportable as PNG/SVG) plus a short legend and the assumptions made.MediaFără avertismente★ 1,5 K↓ —
- programmatic-seokostja94/marketing-skillsWhen the user wants to create SEO pages at scale using templates and data—including AI-assisted, grounded copy for per-URL differentiation (vs rigid mail-merge templates). Also use when the user mentions "programmatic SEO," "programmatic SEO pages," "template pages," "scale content," "location pages," "city pages," "comparison pages at scale," "X vs Y pages," "integration pages," "pages from data," "automated landing pages," or "programmatic landing pages." Uses a playbook matrix aligned to skills under skills/pages. For user-facing template galleries or marketplaces (browse → use), use template-page-generator.MarketingFără avertismente★ 1,1 K↓ —
- run-qafcakyon/claude-codex-settingsThis skill should be used when user asks to "run QA", "verify real playback", "test provider connections", or "check website, extension or Android flows" with tracked journeys.TestareFără avertismente★ 1,2 K↓ —
- focs-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when deciding whether and how computation appears in a FOCS (IEEE Symposium on Foundations of Computer Science) paper — a venue that accepts on theorems with no evaluation section expected — covering machine-verified case analyses, computer-discovered constructions, and honest illustrative plots.MediaFără avertismente★ 1,4 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★ 1,4 K↓ —
- fleet-runshoangsonww/Claude-Code-Agent-MonitorSummarize Workflow-tool fleet runs from the Agent Monitor — these fleets emit no hooks and are ingested from on-disk run journals. List recent runs with status and agents-per-run, then drill into a single run's per-agent detail. Reconciles against the live run-state endpoints. Use when reviewing Workflow() fleets rather than hook-instrumented interactive sessions.ProductivitateFără avertismente★ 1,1 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★ 1,4 K↓ —
- year-in-reviewmohitagw15856/pm-claude-skillsRun an honest personal year-in-review and set next year's direction — wins, misses, an energy audit, and one theme, not a resolution list that dies in February. Use when asked for a personal year in review, a yearly reflection, to reflect on the past year, or plan next year. Produces the structured retrospective (what worked, what didn't, what you learned), an energy audit of what gave vs. drained you, the honest misses, and a single theme with a few concrete commitments. Personal, not corporate.InginerieFără avertismente★ 1,5 K↓ —
finetuning
evo-hq/evo
DesignActualizat 5 oct. 2026
De la autor
This skill should be used when picking or diagnosing a training move (SFT, LoRA, DPO/KTO/ORPO, RFT, GRPO/PPO/RLOO, RLHF), or when the user mentions fine-tuning, post-training, training recipe, reward design, or weight updates. Decision tree by reward shape, smoke-run gate, three failure diagnostics, five false-progress patterns. Provider recipes and I/O contract in references/.
Instalare
npx skills add evo-hq/evo --skill finetuning -a claude-code
Se instalează în .claude/skills/finetuning/ · 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: APACHE-2.0
Verificări de siguranță pe SKILL.md
Niciun avertisment.
De ce 88
Securitate100
Proveniență78
Întreținere100
Licență100
Adopție51
Fișiere (9)
- SKILL.md
- references/diagnostics.md
- references/false-progress.md
- references/glue.md
- references/observability.md
- references/rl/art.md
- references/serving/vllm.md
- references/sft/tinker.md
- references/trace-schema.md