Agent skills that run python, that ask for Edit, in claude-code format

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. agentica-sdkparcadei/Continuous-Claude-v3

   Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration

   claude-codejsonpythonBashReadWrite
2. skill-developerparcadei/Continuous-Claude-v3

   Meta-skill for creating and managing Claude Code skills

   claude-codebashjsonmarkdownpythonBashReadWrite
3. skill-developervibeeval/vibecosystem

   Meta-skill for creating and managing Claude Code skills

   claude-codebashjsonmarkdownpythonBashReadWrite
4. agentica-sdkvibeeval/vibecosystem

   Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration

   claude-codejsonpythonBashReadWrite
5. canvas-humanizer-surgicalX-isdoingreat/canvas-pilot

   Second-pass humanizer that fixes specific issues left over from canvas-humanizer (v2) without re-introducing LLM-shaped prose. v3 design uses per-position-differentiated ESL regist

   claude-codejsonpythonyamlBashReadWrite
6. 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
7. 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
8. canvas-ics33X-isdoingreat/canvas-pilot

   Generic code-course handler — programming assignments where the spec lives outside Canvas (instructor's external site, attached PDF, or referenced textbook), starter code is downlo

   claude-codemarkdownpythonBashReadWrite
9. canvas-awkward-syntaxX-isdoingreat/canvas-pilot

   Direct-commit syntactically-marked rewrite humanizer. Single sub-agent per sentence (K=1, no candidate competition), role-aware transformation allowlist, paragraph-balanced constra

   claude-codejsonpythonBashReadWrite
10. canvas-humanizerX-isdoingreat/canvas-pilot

    Reduces AI-detection signals in drafted text by routing every non-locked sentence through round-trip translation (English → intermediate language → English) and selecting the candi

    claude-codejsonpythonyamlBashReadWrite
11. 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
12. canvas-setupX-isdoingreat/canvas-pilot

    Use this skill on a fresh Canvas Pilot install when the student has never configured the project before. Trigger phrases include "set me up", "set up canvas pilot", "install canvas

    claude-codebashpythonyamlBashReadWrite
13. 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
14. 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
15. canvas-humanizer-loopX-isdoingreat/canvas-pilot

    Nested-loop wrapper around canvas-humanizer that runs the round-trip humanizer, audits its output for meaning/structure/rubric damage via 3 parallel sub-agents with majority vote,

    claude-codejsonpythonBashReadWrite
16. qiskit-mcp-devQiskit/mcp-servers

    Guide development of Qiskit MCP servers. Use when creating tools, resources, tests, or new servers. Helps with async patterns, pytest fixtures, GitHub CI/CD setup, and code quality

    claude-codebashpythontomlReadGrepGlob+1 files
17. zach-product-researchzach22-1999/amazon-skills

    基于Sorftime MCP的选品分析，发现高潜力市场机会、多维度属性标注与交叉分析、验证竞争格局、测算投入产出、输出Go/No-Go决策与选品报告。 使用时机：选品立项前的市场调研。新品上架工作流第一步。 触发词：/zach-product-research

    claude-codebashjsonmarkdownpythonReadWriteEdit
18. intelligence-engineerVinix24/vnx-orchestration

    VNX-specific domain expertise for the intelligence system, central state databases, and dispatch lifecycle. Use when working on quality_intelligence.db / runtime_coordination.db /

    claude-codepythonsql[ReadWriteEdit
19. database-engineerVinix24/vnx-orchestration

    SQLite database expertise for migrations, multi-tenant patterns, transactional safety, FTS5 virtual tables, and schema evolution. Use this skill for ANY work involving schema chang

    claude-codepythonsql[ReadWriteEdit
20. deep-analysisnicepkg/auto-company

    Analytical thinking patterns for comprehensive evaluation, code audits, security analysis, and performance reviews. Provides structured templates for thorough investigation with ex

    claude-codemarkdownpythonBashReadWrite
21. deep-analysisNikitaDmitrieff/auto-co-meta

    Analytical thinking patterns for comprehensive evaluation, code audits, security analysis, and performance reviews. Provides structured templates for thorough investigation with ex

    claude-codemarkdownpythonBashReadWrite
22. releasespinje/pflow

    Run the pflow release process — generate changelog, bump version, commit, and create GitHub Release

    claude-codebashpythonBash(uv run pflow:*)Bash(git:*)Bash(gh:*)
23. intelligent-testingdefinableai/definable.ai

    Enforces the project's testing strategy whenever writing, editing, or reviewing tests. Triggers on any test-related work including writing new tests, fixing failing tests, adding t

    claude-codebashinipythonReadWriteEdit
24. prometheusCloudChef/atlasclaw-providers

    Prometheus monitoring and alerting for cloud-native observability. Use when implementing metrics collection, PromQL queries, alerting rules, service discovery, recording rules, and

    claude-codebashgopromqlpythonReadGrepGlob
25. scaffold-api-servicebbvch-ai/aihub-core

    Generate a new API service layer with stateless static methods, OpenTelemetry tracing, DTO conversion, pagination, and error handling. Use when user says "create service layer", "s

    claude-codepythonReadWriteEdit
26. debug-agentbbvch-ai/aihub-core

    Debug an AI agent using code analysis and MCP-powered runtime inspection (NATS streams, MongoDB events, Langfuse traces). Covers execution semantics, race conditions, engineering c

    claude-codebashgherkinjsonmarkdownReadWriteEdit
27. scaffold-api-repositorybbvch-ai/aihub-core

    Generate a MongoEngine Document entity that combines schema definition with repository classmethods in packages/core/persistence/. Follows the Entity-as-repository pattern (no sepa

    claude-codepythonReadWriteEdit
28. scaffold-bot-handlerbbvch-ai/aihub-core

    Scaffold a new bot conversation handler in packages/bot following the BaseChatBot + CompletionHandler strategy pattern. Generates ChatBot subclass, streaming variant, CompletionHan

    claude-codebashpythonReadWriteEdit
29. scaffold-api-endpointbbvch-ai/aihub-core

    Generate a new REST API controller with fluent builder pattern, typed endpoints, permission-based auth, DTOs, and main.py registration. Use when user says "create API endpoint", "s

    claude-codepythonyamlReadWriteEdit
30. mlops-engineertranhieutt/software_development_department
    claude-codepythonyamlReadGlobGrep
31. fastapi-protranhieutt/software_development_department
    claude-codebashpythonReadGlobGrep
32. gemini-api-integrationtranhieutt/software_development_department
    claude-codebashjavascriptpythonReadGlobGrep
33. llm-app-patternstranhieutt/software_development_department
    claude-codepythonReadGlobGrep
34. devops-deploytranhieutt/software_development_department
    claude-codebashdockerpythonyamlReadGlobGrep
35. django-patternstranhieutt/software_development_department
    claude-codepythonReadGlobGrep
36. pii-engineeranonde-io/anonde

    Apply when designing, building, benchmarking, or debugging local-first PII detection / anonymization systems. Covers metric tradeoffs (leak rate vs F1), NER backend selection (patt

    claude-codegopythonyamlReadBashEdit
37. pdfcharlieviettq/awesome-agent-skill

    Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitt

    claude-codebashpythonBashReadWrite
38. scikit-learncharlieviettq/awesome-agent-skill

    Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction),

    claude-codebashpythonBashReadWrite
39. xlsxcharlieviettq/awesome-agent-skill

    \"Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, o

    claude-codebashjsonpythonBashReadWrite
40. pytorch-lightningcharlieviettq/awesome-agent-skill

    Deep learning framework (PyTorch Lightning). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, T

    claude-codepythonBashReadWrite
41. scientific-visualizationcharlieviettq/awesome-agent-skill

    Meta-skill for publication-ready figures. Use when creating journal submission figures requiring multi-panel layouts, significance annotations, error bars, colorblind-safe palettes

    claude-codepythonBashReadWrite
42. matplotlibcharlieviettq/awesome-agent-skill

    Low-level plotting library for full customization. Use when you need fine-grained control over every plot element, creating novel plot types, or integrating with specific scientifi

    claude-codebashpythonBashReadWrite
43. exploratory-data-analysischarlieviettq/awesome-agent-skill

    Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats. This skill should be used when analyzing any scientific data file to understand i

    claude-codebashmarkdownpythonBashReadWrite
44. statistical-analysischarlieviettq/awesome-agent-skill

    Guided statistical analysis with test selection and reporting. Use when you need help choosing appropriate tests for your data, assumption checking, power analysis, and APA-formatt

    claude-codepythonBashReadWrite
45. compound-engineeringaegntic/cldcde

    Orchestration layer that coordinates Debt-Sentinel, Red Team Tribunal, and Spec-Lock into unified workflows. Use when you need comprehensive quality assurance with multiple validat

    claude-codebashjsonpythonsqlBashReadWrite
46. debt-sentinelaegntic/cldcde

    Architectural pattern enforcer that prevents technical debt. Use when editing code to check for anti-patterns, hardcoded secrets, SQL injection, inline styles, and other code quali

    claude-codebashjsonmarkdownpythonBashReadEdit
47. red-team-tribunalaegntic/cldcde

    Multi-agent adversarial verification system. Use when you need thorough code review, security auditing, or quality validation. Spawns three specialized agents (Skeptic, User Proxy,

    claude-codebashjsonpythonyamlBashReadWrite
48. dashboardminhlucvan/notebookmd

    Generate a metrics dashboard using notebookmd with KPIs, charts, and data tables. Use when the user wants a dashboard, scorecard, or metrics overview saved as Markdown.

    claude-codepythonBashReadWrite
49. analyzeminhlucvan/notebookmd

    Generate a structured data analysis report using notebookmd. Use when the user asks to analyze data, a CSV file, a DataFrame, financial data, or any dataset and wants a readable Ma

    claude-codepythonBashReadWrite
50. reportminhlucvan/notebookmd

    Generate a structured Markdown report using notebookmd. Use when the user asks for a report, documentation, summary, or writeup that should be saved as a formatted Markdown file wi

    claude-codepythonBashReadWrite
51. ptrade-devkay-ou/ClaudeSkills

    PTrade/SimTradeLab strategy development guardrails. Auto-loads PTrade API reference, enforces platform constraints (no f-string, no import io/sys), validates lifecycle function usa

    claude-codepythonReadEditWrite
52. spec-workflow-orchestratorahmedibrahim085/Claude-Multi-Agent-Research-System-Skill

    Orchestrate comprehensive planning phase from ideation to development-ready specifications using 3 specialized agents (Full workflow documentation at docs/workflows/planning-workfl

    claude-codebashjavascriptmarkdownpythonTaskReadGlob
53. frontend-ui-cloneinstantX-research/skills

    Pixel-perfect website cloner. Given a URL, faithfully reproduces the page as a single self-contained HTML file. Uses Playwright to render the page in a real browser, then directly

    claude-codebashcssjavascriptpythonReadWriteEdit

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.