API 开发
API 设计、REST 与 GraphQL
pydoll-antibot-bypasser
Esonhugh
Stealth browser automation using pydoll library, specialized in bypassing Cloudflare WAF, Turnstile CAPTCHA, and other bot detection systems. You MUST invoke this skill in ANY of these situations: (1) The user explicitly asks to bypass WAF, anti-bot, CAPTCHA, or human verification (Cloudflare, DataDome, PerimeterX, Akamai, etc.). (2) You encounter Cloudflare protection while scraping or fetching a URL — signs include HTTP 403/503 responses, pages containing "Checking your browser", "Just a moment...", "Attention Required", "cf-browser-verification", "cf-chl-bypass", "_cf_chl_opt", Turnstile widget HTML, or any response body mentioning "cloudflare" with a challenge/block page. (3) A WebFetch or curl fails with what appears to be bot detection or WAF blocking. (4) The user wants to crawl, scrape, or automate interaction with a website known to use anti-bot protection. When in doubt about whether a site is WAF-protected, invoke this skill — it is better to invoke and not need it than to miss a bypass opportunity. Also suitable for: stealth browser operations, Shadow DOM handling, human-like behavior simulation, and concurrent web automation.
merge-reconciler
p-wegner
Land a whole BATCH of stranded/mergeable-but-conflicting workspaces onto the base branch in the most efficient way. You are handed the full batch as injected JSON ({{strandedBatch}}), analyze the whole set first (clean-independent / file-overlap clusters / migration collisions / dependencies), then land everything via the board's SAFE primitives — never manual git in the main checkout. Resolve each overlapping cluster's union ONCE in an integration worktree instead of N re-conflicting rebases. Report what landed and what was escalated.
cleanup
p-wegner
"Clean up stale agentic-kanban resources including git worktrees, Claude Code sessions, and E2E test artifacts."
board-monitor
p-wegner
System-level board health — conflict scan, server/frontend health check. Board operations (relaunch/merge/nudge/auto-start) are handled by the app's built-in monitor (Settings → Workflow → Board Monitoring). Run Sections 0-3 every cycle; only do Section 4 if the app monitor is OFF.
robotframework-restinstance-skill
manykarim
Guide AI agents in creating REST API tests using RESTinstance library. Use when building API tests with JSON Schema validation, built-in assertions, response field validation, and OpenAPI spec integration.
endpoint-docs
p-wegner
Create, maintain, and query a concise Markdown catalog of the REST API (docs/api/endpoints.md) — method, path, request shape, response, semantic — with a frontmatter SHA so staleness is detected via git diff. Use when asked "what endpoints exist", "is there an API for X", "where is endpoint Y used", "document the API", or after adding/changing Hono routes.
robotframework-appium-skill
manykarim
Guide AI agents in creating AppiumLibrary tests for iOS and Android native apps, hybrid apps, and mobile browsers. Load when asked about mobile testing, Appium, or mobile app automation.
dev-server
p-wegner
Start/stop/health-check the dev server safely — worktree ports, process-signature kills, never kill-all-node
behavior-discovery
p-wegner
Build a high-confidence model of a software system's EXTERNALLY OBSERVABLE behaviour — capabilities, actors, permissions, entry points, workflows, state transitions and error states — by combining many evidence sources (domain docs, OpenAPI/GraphQL schemas, source, routing, running-UI exploration, existing tests, git history) and degrading gracefully when some are absent. Infers business semantics; never paraphrases code. Marks unknowns explicitly instead of guessing. Output is the shared _behavior-model.json that the coverage-intelligence and e2e-test-author skills consume. Use when the user asks to "model what the app does", "discover observable behaviour", "build a verification/behaviour model", "explore the running app and map its capabilities", or as phase 1 of an end-to-end verification effort.
learning-step
p-wegner
Analyze agent session data (kanban sessions, JSONL transcripts, or inline context), detect friction points, and produce targeted improvements to documentation, hooks, skills, or code.
sentinel
p-wegner
The board-orchestrator WATCH role. Check the out-of-process board-monitor loop (the "Conductor") once and report a concise one-line status — loop health, board state, profile≠mock, and the current Strategy-Bullseye targets/weights it's steering by; alert with detail and recover ONLY when something needs attention. Use for "check the board monitor", "is the Conductor healthy?", or as a recurring watch scheduled with ScheduleWakeup. Distinct from the board-monitor skill (that's the system-health checklist a monitor CYCLE runs; this is what the human-side supervisor checks between cycles).
robotframework-requests-skill
manykarim
Guide AI agents in creating REST API tests using RequestsLibrary. Use when building HTTP client tests, JSON/XML API testing, session management, authentication, file uploads, and response validation.
pywayne-llm-chat-window
wangyendt
PyQt5-based GUI chat window for LLM conversations with streaming responses and stop functionality. Use when working with pywayne.llm.chat_window module to create desktop chat applications with customizable window configuration, system message management, and real-time streaming display.
unstuck
p-wegner
Drive a stuck kanban issue all the way to master. Diagnose why the agent stopped, answer pending questions, run the agent to commit, then merge via the kanban endpoint and verify master actually advanced.
set-provider-default
p-wegner
Set the board's default agent provider+profile (and optional model) in ONE place, atomically, across every consumer that can drift — the Strategy Bullseye, the Settings provider/claude_profile mirror, and the provider-scoped default_model_<provider> — then verify they agree. Use whenever the user says "set the provider default", "switch the board to claude/codex/copilot", "use profile X", "make anth the default", or after a provider stall where the sources drifted out of sync.
pywayne-helper
wangyendt
Project configuration management helper for YAML config files. Use when projects need cross-process/cross-file parameter sharing via a centralized config file. Supports automatic project root detection, nested config key management, and waiting mechanism for values set by other processes.
django-tdd
xu-xiang
使用 pytest-django、测试驱动开发（TDD）方法论、factory_boy、Mock 模拟、覆盖率统计以及 Django REST Framework API 测试的 Django 测试策略。
golang-testing
xu-xiang
Go 测试模式，包括表格驱动测试、子测试、基准测试、模糊测试和测试覆盖率。遵循测试驱动开发（TDD）方法论及地道的 Go 语言实践。
项目指南技能（Project Guidelines Skill，示例）
xu-xiang
tdd-workflow/ - æµè¯é©±å¨å¼å (TDD) æ¹æ³è®º
springboot-patterns
xu-xiang
Spring Boot 架构模式、REST API 设计、分层服务、数据访问、缓存、异步处理和日志记录。适用于 Java Spring Boot 后端开发工作。
coding-standards
xu-xiang
适用于 TypeScript、JavaScript、React 和 Node.js 开发的通用编码标准、最佳实践和模式。
tdd-workflow
xu-xiang
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
springboot-security
xu-xiang
Spring Boot 服务中关于身份认证/授权（authn/authz）、校验、CSRF、密钥管理、响应头、限流及依赖安全的 Spring Security 最佳实践。
agentii-investment-intelligence
agentii-ai
Institutional-grade equity research skills for AI agents. 25 Claude-type skills across 4 verticals (equity-research-core, business-intelligence, industry-analysis, models-and-pitches) powered by agentii.ai's agent-use-ready SEC filing data plane — 10 years of filings, XBRL financials, earnings calendars, and company profiles for 165+ US-public-equity tickers. Features the three-layer retrieval protocol (Document Discovery → Page Map → Deep Read) for ~99% token efficiency, server-side parallel multi-period search via search_cross_period, and a full Excel/PPT generation pipeline with 3-tier office backend support.