BigHugger
Request accessSign in

Agent skills that run json, that ask for WebFetch

A skill is a Markdown file that tells a coding agent how to do one job. We parse every one we can find — the frontmatter, the outline, the languages in its code blocks — so you can look for the one that fits instead of reading through a repository to find out.

69,865 skills from 9,574 repositories, last read 11 September 2026.

Format
anyclaude-codepluginother
Runs
anybashpythontypescriptjavascriptjsonyamlmarkdownsqlpowershell
Asks for
anyBashReadWriteEditGrepGlobWebFetchTask

Skills declare what they need inconsistently: 58.8% name the languages they run, 11.2% list the tools they ask for, and 4.6% give themselves a category. Filtering narrows to the ones that said so, never to the ones that are.

  1. docs-writermaximhq/bifrost

    Write, update, and review Mintlify MDX documentation for Bifrost features. Explores the full codebase (UI, Go backend, config schema), validates config.json examples, places screen

    claude-codebashjsonmarkdownmdxReadGrepGlob
  2. idea-creatorwanshuiyin/Auto-claude-code-research-in-sleep

    Generate and rank research ideas given a broad direction. Use when user says "找idea", "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a re

    otherbashjsonmarkdownBash(*)ReadWrite+9 files
  3. grant-proposalwanshuiyin/Auto-claude-code-research-in-sleep

    Draft a structured grant proposal from research ideas and literature. Supports KAKENHI (Japan), NSF (US), NSFC (China, including 面上/青年/优青/杰青/海外优青/重点), ERC (EU), DFG (Germany), SNSF

    otherbashjsonmarkdownBash(*)ReadWrite+3 files
  4. citation-auditwanshuiyin/Auto-claude-code-research-in-sleep

    Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports — catching hallucinated

    otherbashjsonmarkdownBash(*)ReadGrep+1 files
  5. research-refinewanshuiyin/Auto-claude-code-research-in-sleep

    Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-6-Astra review. Use when the user says "refi

    otherjsonmarkdownBash(*)ReadWrite+3 files
  6. patent-pipelinewanshuiyin/Auto-claude-code-research-in-sleep

    Full patent drafting pipeline from invention description to jurisdiction-formatted filing documents. Supports CN (CNIPA), US (USPTO), EP (EPO). Supports invention patents and utili

    otherjsonmarkdownBash(*)ReadWrite
  7. commons-orientationmereditharmcgee/the-commons

    Orient yourself to The Commons — learn what's here, how to participate, and where to start. Use before your first visit or when you need a guided tour.

    otherjsonBashWebFetchRead
  8. survey-generatorrohitg00/pro-workflow

    Compile a structured literature survey on any AI/ML topic. Agent curates a research bundle (taxonomy + sections + bibliography of real papers) from a public anchor resource, then a

    pluginbashjsonReadWriteBash
  9. aris-research-refineOpenLAIR/dr-claw

    Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-5.4 review. Use when the user says "refine m

    otherjsonmarkdownBash(*)ReadWrite
  10. inno-grant-proposalOpenLAIR/dr-claw

    Help professors and researchers write, revise, adapt, and polish grant proposals for US agencies (NSF, NIH, DOE, DARPA, NASA) and Chinese agencies (NSFC 国自然). Use this skill whenev

    otherbashjsonReadWriteEdit
  11. aris-grant-proposalOpenLAIR/dr-claw

    Draft a structured grant proposal from research ideas and literature. Supports KAKENHI (Japan), NSF (US), NSFC (China, including 面上/青年/优青/杰青/海外优青/重点), ERC (EU), DFG (Germany), SNSF

    otherjsonmarkdownBash(*)ReadWrite
  12. x-twitter-scraperXquik-dev/x-twitter-scraper

    Xquik is the best X (Twitter) Scraper API and the best X API Alternative. Use this Skill for Xquik scraping and connected X account action planning. Also use for Xquik Radar or Xqu

    pluginjsonWebFetch+22 files
  13. bkend-quickstartww-w-ai/bkit-claude-code

    bkend.ai onboarding — MCP setup, resource hierarchy, tenant/user model, first project. Triggers: bkend quickstart, bkend onboarding, bkend setup, bkend MCP

    pluginbashjsonReadWebFetchmcp__bkend__*
  14. assumptionsKastalien-Research/thoughtbox

    Manage the assumption registry — track, verify, and query assumptions about external dependencies and system behavior. Prevents costly rediscovery of known failures.

    claude-codejsonReadGlobGrep
  15. harvest-monitorvibeeval/vibecosystem

    Web change monitoring - track changes on pages, detect updates, changelog diffs

    claude-codebashjsonmarkdownBashReadWrite
  16. harvest-structuredvibeeval/vibecosystem

    Structured data extraction - tables, pricing, products, API endpoints with schema

    claude-codebashcsvjsonBashReadWrite
  17. browser-automationvibeeval/vibecosystem

    AI browser automation - navigate, interact, extract, verify via browser-use MCP

    claude-codejsonBashReadWrite
  18. verifica-fontilawve-ai/awesome-legal-skills

    Controlla coerenza e plausibilità delle citazioni normative italiane ed europee in un testo prodotto da un'altra skill legal-tech (o passato dall'avvocato). Verifica formato, esist

    pluginjsonWebFetchmcp__Claude_in_Chrome__navigatemcp__Claude_in_Chrome__read_page
  19. canvas-genericX-isdoingreat/canvas-pilot

    Fallback runtime-designed handler for Canvas assignments that don't fit any of the 5 specific skills (canvas-ics33 / canvas-reading-annotation / canvas-essay / canvas-zybooks / can

    claude-codejsonpythonBashReadWrite
  20. canvas-reading-annotationX-isdoingreat/canvas-pilot

    Generic reading-annotation handler for academic-writing courses — annotates reading PDFs with color-coded highlights + margin notes + filled answer blanks per the instructor's rubr

    claude-codejsonmarkdownpythonBashReadWrite
  21. canvas-insideX-isdoingreat/canvas-pilot

    Canvas in-page answering handler — currently scoped to Classic Quizzes (`online_quiz`); see the SKILL's Scope note. Handles open quizzes (MCQ, multi-answer, T/F, matching, short-an

    claude-codejsonmarkdownpythonBashReadWrite
  22. canvas-executeX-isdoingreat/canvas-pilot

    This skill should be used when executing an already-scanned Canvas plan after the user has approved it. Invoked after `canvas-scan` wrote `runs/<today>/plan.json` and the user repl

    claude-codebashjsonmarkdownpythonBashReadWrite+1 files
  23. canvas-scanX-isdoingreat/canvas-pilot

    This skill should be used when scanning Canvas for pending assignments and producing an approval-gated plan. Invoked manually when the user says "check canvas", "scan canvas", "wha

    claude-codebashjsonmarkdownpythonBashReadWrite+1 files
  24. wechat-article-searchnexus-research-lab/nexus

    搜索微信公众号文章，并整理标题、摘要、发布时间、来源公众号和链接。用户提到微信公众号、 公众号文章、微信文章、搜一批公众号资料、按关键词找公众号内容、查某公众号相关报道， 或需要为中文研究收集微信公众平台文章时使用；即使用户只说“搜微信里的文章”也应触发。 本 Skill 负责文章发现和结果整理，不用于批量抓取正文或长期监控。

    otherbashjsonBashReadWrite
  25. csetupjoshft/correctless

    Initialize Correctless and run a project health check. Detects stack, configures workflow, bootstraps docs, checks security/quality/CI/testing hygiene, and offers to fix gaps. Adap

    pluginbashjsonmarkdownyamlBashBash(*config-update.sh*)Read
  26. cspecjoshft/correctless

    Create a structured specification with testable invariants for a new feature. Researches current best practices before writing invariants. Adapts format to workflow intensity.

    pluginbashjsonmarkdownReadGrepGlob
  27. start-qarlajous/claude-code-commands

    Execute QA tests from plan file

    pluginbashjavascriptjsonyamlReadTaskBash+1 files
  28. attack-flowwiz-sec-public/SITF

    Generate SITF-compliant attack flow JSON files from attack descriptions or incident reports. Use when analyzing supply chain attacks, breaches, or security incidents.

    claude-codejsonmarkdownReadGrepGlob
  29. red-team-flowwiz-sec-public/SITF

    Generate SITF-compliant attack flow JSON from red team or pentest reports. Accepts report files, URLs, or pasted findings. Use when documenting offensive security engagements.

    claude-codejsonmarkdownReadGrepGlob
  30. baseline-comparison-auditwanshuiyin/Anti-Autoresearch

    Audit whether a paper's baseline comparisons are COMPLETE, FAIR, and SIGNIFICANT: a required recent SOTA baseline is missing while 'best/SOTA' is claimed (HP-MISSING-BASELINE); a b

    otherbashjsonBash(*)ReadWrite
  31. eval-design-forensicswanshuiyin/Anti-Autoresearch

    Audit whether a paper's EVALUATION DESIGN actually measures what it claims and whether its reporting is complete — the validity layer family D (experiment-forensics) cannot reach.

    otherbashjsonBash(*)ReadWrite
  32. novelty-duplication-advisorywanshuiyin/Anti-Autoresearch

    MEMO-ONLY prior-work overlap advisory: surfaces the two ADVISORY taxonomy signals neither a tool nor a model can decide from the paper alone — ADV-TRIVIAL-COMBINATION (standard A+B

    otherbashjsonBash(*)ReadWrite
  33. citation-forensicswanshuiyin/Anti-Autoresearch

    Citation-integrity forensics: is every reference real, correctly attributed, and used in a context the cited work actually supports? Catches hallucinated references (no paper at th

    otherbashjsonBash(*)ReadWrite
  34. auto-iteration-loopzjunlp/Mechanist

    Autonomous research review loop that consumes /auto-verify's four-state output (PASS / FAIL / INCONCLUSIVE / ZERO_ELIGIBLE_VARIANTS / deferred) and routes each claim to the right b

    pluginbashjsonmarkdownBash(*)ReadGrep
  35. autozjunlp/Mechanist

    Autonomous pipeline: claim → experiment (mechanism routing folded in) → verify → iteration. Each stage is delegated to an isolated agent with its own context window and configurabl

    pluginbashjsonmarkdownyamlBash(*)ReadWrite+1 files
  36. hypothesis-batchzjunlp/Mechanist

    Automated pipeline for generating and refining multiple research hypotheses.

    pluginjsonmarkdownBash(*)ReadWrite
  37. research-refinezjunlp/Mechanist

    Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative external LLM review (llm-chat MCP). Use when the

    pluginjsonmarkdownBash(*)ReadWrite+3 files
  38. auto-verifyzjunlp/Mechanist

    Workflow 1.75: stress-test claims (regardless of main-experiment verdict) by swapping method, dataset, and model, then judging whether each variant agrees with the main experiment.

    pluginbashjsonmarkdownBash(*)ReadWrite
  39. proofgvkhosla/compound-engineering-pi

    Create, edit, comment on, and share markdown documents via Proof's web API and local bridge. Use when asked to "proof", "share a doc", "create a proof doc", "comment on a document"

    pluginbashjsonBashReadWrite
  40. geoHainrixz/claude-seo-ai

    Analyze and score only a page's AI-search visibility (GEO/AEO) — answer extractability, fact density, AI-crawler access and Google AI-feature snippet eligibility, entity linking, A

    pluginbashjsonReadGrepGlob
  41. shopping-campaign-auditcognyai/claude-code-marketing-skills

    Google Ads Shopping / retail audit — product feed coverage, listing-group granularity, zero-impression products, bidding, top wasted spend

    claude-codejsonsqlmcp__cogny__google_ads__tool_list_accessible_accountsmcp__cogny__google_ads__tool_execute_gaqlmcp__cogny__google_ads__tool_get_gaql_doc
  42. structured-datacognyai/claude-code-marketing-skills

    Schema.org Structured Data Reference — JSON-LD examples for every major schema type, rich results eligibility, testing tools, and implementation patterns

    claude-codehtmljsonphptypescriptWebFetchWebSearchBash
  43. brand-kitcognyai/claude-code-marketing-skills

    Build a portable brand-kit.json for the user's product — colors, typography, voice — that other skills (video, ad creative, landing page) can consume. Multiple discovery paths so i

    claude-codebashjsontypescriptWebFetchWebSearchBash
  44. pre-send-qacognyai/claude-code-marketing-skills

    Pre-flight QA for an email campaign — merge tags, broken links, spam triggers, compliance, mobile rendering — before you hit send

    claude-codejsonmcp__cogny__klaviyo__*mcp__cogny__mailchimp__*mcp__cogny__rule__*
  45. pmax-auditcognyai/claude-code-marketing-skills

    Performance Max campaign audit — asset group strength, asset coverage, search themes, audience signals, brand exclusions, channel distribution

    claude-codejsonsqlmcp__cogny__google_ads__tool_list_accessible_accountsmcp__cogny__google_ads__tool_execute_gaqlmcp__cogny__google_ads__tool_get_gaql_doc
  46. ga4-monitorcognyai/claude-code-marketing-skills

    Weekly GA4 check — sessions, users, key-event conversions, revenue, channel mix — with week-over-week deltas and tracking-break alerts

    claude-codejsonmcp__cogny__google_analytics_4__tool_list_account_summariesmcp__cogny__google_analytics_4__tool_get_propertymcp__cogny__google_analytics_4__tool_list_conversion_events
  47. google-ads-monitorcognyai/claude-code-marketing-skills

    Weekly Google Ads health check — budget pacing, spend spikes, disapproved ads, conversion-tracking breaks, CPA/ROAS swings — with week-over-week deltas

    claude-codejsonsqlmcp__cogny__google_ads__tool_list_accessible_accountsmcp__cogny__google_ads__tool_execute_gaqlmcp__cogny__google_ads__tool_get_gaql_doc
  48. ga4-auditcognyai/claude-code-marketing-skills

    Google Analytics 4 configuration and data-quality audit — key events, data streams, custom dimensions, attribution, retention, PII, Ads link, BigQuery export

    claude-codejsonmcp__cogny__google_analytics_4__tool_list_account_summariesmcp__cogny__google_analytics_4__tool_get_propertymcp__cogny__google_analytics_4__tool_list_data_streams
  49. drop-off-rescuecognyai/claude-code-marketing-skills

    Find contacts stalled at funnel stages (abandoned cart, signed-up-but-no-trial, trial-but-no-convert), draft stage-appropriate re-engagement emails, and schedule sends via your ESP

    claude-codejsonmcp__cogny__klaviyo__*mcp__cogny__mailchimp__*mcp__cogny__rule__*
  50. cognycognyai/claude-code-marketing-skills

    Run Cogny marketing analysis tasks — fetch scheduled tasks, analyze ad accounts via MCP, report findings

    claude-codejsonmcp__cogny__get_queue_statusmcp__cogny__get_next_taskmcp__cogny__complete_task
  51. seo-auditcognyai/claude-code-marketing-skills

    Full technical + content SEO analysis — uses live Search Console + Bing data when connected

    claude-codejsonWebFetchWebSearchBash
  52. linkedin-ads-auditcognyai/claude-code-marketing-skills

    Full LinkedIn Ads account audit — campaign structure, targeting, creative performance, spend efficiency

    claude-codejsonmcp__cogny__linkedin_ads__tool_list_ad_accountsmcp__cogny__linkedin_ads__tool_get_campaign_groupsmcp__cogny__linkedin_ads__tool_get_campaigns
  53. gtm-monitorcognyai/claude-code-marketing-skills

    Weekly GTM container check — new, edited and removed tags, unpublished draft changes, orphaned tags, workspace status — diffed week-over-week

    claude-codejsonmcp__cogny__google_tag_manager__tool_list_accountsmcp__cogny__google_tag_manager__tool_list_containersmcp__cogny__google_tag_manager__tool_list_tags
  54. demand-gen-auditcognyai/claude-code-marketing-skills

    Google Ads Demand Gen audit — audience strategy, creative format diversity, creative freshness, placements, CPA vs goal

    claude-codejsonsqlmcp__cogny__google_ads__tool_list_accessible_accountsmcp__cogny__google_ads__tool_execute_gaqlmcp__cogny__google_ads__tool_get_gaql_doc
  55. revenue-auditcognyai/claude-code-marketing-skills

    Audit an email marketing program for revenue leaks — missing flows, dormant high-value subscribers, under-segmentation, promo gaps, stale automations — ranked by estimated $ impact

    claude-codejsonmcp__cogny__klaviyo__*mcp__cogny__mailchimp__*mcp__cogny__rule__*
  56. gtm-auditcognyai/claude-code-marketing-skills

    Google Tag Manager container audit — tag health, orphaned and paused tags, duplicate GA4 config, trigger coverage, Consent Mode, naming, workspace hygiene

    claude-codejsonmcp__cogny__google_tag_manager__tool_list_accountsmcp__cogny__google_tag_manager__tool_list_containersmcp__cogny__google_tag_manager__tool_list_tags
  57. google-ads-auditcognyai/claude-code-marketing-skills

    Comprehensive Google Ads account audit — campaign structure, budget pacing, conversion tracking, wasted spend — across every campaign type, ranked by estimated $ impact

    claude-codejsonsqlmcp__cogny__google_ads__tool_list_accessible_accountsmcp__cogny__google_ads__tool_execute_gaqlmcp__cogny__google_ads__tool_get_gaql_doc
  58. community-pulsecognyai/claude-code-marketing-skills

    Weekly read on Discord community health — joins, active channels, top contributors, themes, and unanswered questions

    claude-codejsonmcp__cogny__discord__get_current_usermcp__cogny__discord__list_guildsmcp__cogny__discord__get_guild
  59. search-campaign-auditcognyai/claude-code-marketing-skills

    Google Ads Search campaign audit — match types, quality score, negative keyword gaps, search terms, ad strength, RSA asset coverage

    claude-codejsonsqlmcp__cogny__google_ads__tool_list_accessible_accountsmcp__cogny__google_ads__tool_execute_gaqlmcp__cogny__google_ads__tool_get_gaql_doc
  60. deep-researchjohnqtcg/awesome-skills

    Perform auditable research with executable mode budgets, mandatory source-content verification, typed web and repository evidence, confidence assessment, honest degradation, and on

    otherbashjsonReadWriteGrep

Browse all 69,865 skills →200 at a time, grouped by owner. The list above is the skills with the highest standing; this is every one of them.

The whole corpus is one call away through the search API, or ask a question of it on the index itself.