Data & backend
10,137 rows, by stacks then stars
233 of these skill files have been read, by 258 distinct authors, and what they tell an agent counted. What Data & backend authors agree on, and what they forbid
HeyEddi-com/skills/evals/runs/2026-07-04T22-58-59Z/backend-type-bridger-users/.cursor/skills/backend-type-bridger Skill
0★ repoSyncs FastAPI OpenAPI schema to TypeScript types and reads Firestore schema hints. Use when writing Vue composables against FastAPI or Firebase backends.
HeyEddi-com/skills/evals/runs/2026-07-04T22-58-59Z/full-product-integration/.agents/skills/backend-type-bridger Skill
0★ repoSyncs FastAPI OpenAPI schema to TypeScript types and reads Firestore schema hints. Use when writing Vue composables against FastAPI or Firebase backends.
HeyEddi-com/skills/evals/runs/2026-07-04T22-58-59Z/full-product-integration/.cursor/skills/backend-type-bridger Skill
0★ repoSyncs FastAPI OpenAPI schema to TypeScript types and reads Firestore schema hints. Use when writing Vue composables against FastAPI or Firebase backends.
Ego-System/fable-mode/skills/fable-security Skill
0★ repoFable 5's defensive-security discipline: threat-model-first procedure, a scoring rubric, and an anti-pattern catalog for writing security-sensitive code, fixing vulnerabilities, reviewing for security, and handling incidents like leaked secrets. Use whenever the work touches authentication, authorization, user input, secrets, crypto, file handling, or a reported vulnerability. Plugs into the fable-core loop (security work is Consequential by default); self-contained if fable-core is absent. Calibration exemplars in references/exemplars-security.md.
angpysha/api2skill/.agents/skills/api-local-test Skill
0★ repoLocally test a backend API at runtime with mcp2cli — turn any OpenAPI, GraphQL, or MCP endpoint into a CLI (zero codegen, token-efficient). Use to smoke-test a running local server, exercise endpoints against acceptance criteria / API contracts, and verify responses during Phase 7 integration tests and Phase 8 testing.
angpysha/api2skill/.agents/skills/graphql-contract Skill
0★ repoUniversal GraphQL contract skill. Write GraphQL schemas from approved requirements. Architect or Team Lead authors the schema in Phase 5/6; Developer implements resolvers exactly to fields and types. Use when REQ includes GraphQL API behavior.
angpysha/api2skill/.agents/skills/grpc-contract Skill
0★ repoUniversal gRPC contract skill. Write Protocol Buffers (.proto) from approved requirements. Architect or Team Lead authors the proto in Phase 5/6; Developer implements services exactly to RPCs and messages. Use when REQ includes gRPC behavior.
incuca/incuca-ads/skills/ads-server-side-tracking Skill
0★ repoServer-side tracking pipeline audit covering server-side Google Tag Manager (sGTM), Meta CAPI Gateway, Conversions API health, event deduplication via event_id, server-side hit ratio targets, pixel debugging, and PII hashing discipline. Use when user says server-side tracking, sGTM, server-side GTM, server-side tagging, CAPI, Conversions API, CAPI Gateway, Meta Conversions API, event deduplication, event_id, pixel debug, pixel health, Pixel/CAPI audit, first-party tracking, iOS 14.5 recovery, or server-side hit ratio.
vaibhavsaxena022/skills/db-query Skill
0★ repoExplore and query a database safely, especially in shared or production-like environments. Use when inspecting data or debugging via SQL through a DB tool or agent (TablePlus, psql, an MCP DB connection). Read-first, with destructive writes gated behind confirmation.
vaibhavsaxena022/skills/spring-endpoint Skill
0★ repoScaffold a clean Spring Boot REST endpoint — controller, service, DTOs, and validation — following the project's existing layered conventions. Use when adding a new REST endpoint or resource to a Spring Boot project.
vaibhavsaxena022/skills/sql-review Skill
0★ repoReview a SQL query (Postgres/MySQL) for performance and safety before it ships. Use when given a slow query, a new query, or asked to optimize SQL. Flags missing indexes, full scans, N+1 patterns, risky writes, and inefficient pagination.
ceilidhboy/skills/skills/troubleshooting-backend Skill
0★ repoTroubleshooting Laravel, PHP, and backend-related errors.
shinzoxD/knackbox/skills/coding/database-migrations Skill
0★ repoPlan and review database schema migrations for safety and rollback. Use whenever the user writes migrations, alters tables, backfills data, adds indexes, or asks how to deploy schema changes without downtime or lock pain.
shinzoxD/knackbox/skills/coding/graphql-schema-design Skill
0★ repoDesign and review GraphQL schemas for authz, pagination, N+1 risk, nullability, and evolution. Use whenever the user works on GraphQL types, resolvers, connections, deprecations, query cost, or schema reviews — even when they only paste an SDL snippet.
shinzoxD/knackbox/skills/coding/rate-limiting Skill
0★ repoDesign rate limiting and throttling for APIs and gateways with fair use and abuse resistance. Use whenever the user asks about rate limits, quotas, 429 responses, token buckets, leaky buckets, or protecting endpoints from overload and abuse.
shinzoxD/knackbox/skills/coding/sql-query-review Skill
0★ repoReview and improve SQL queries for correctness, performance, safety, and maintainability. Use whenever the user shares a SQL query, asks to optimize a query, check indexes, prevent SQL injection, rewrite a join, explain a slow query plan, or debug wrong database results — even for ORM-generated SQL or "why is this query slow".
shinzoxD/knackbox/skills/data/etl-pipeline-design Skill
0★ repoDesign ETL and ELT pipelines with clear contracts, quality checks, and failure modes. Use whenever the user plans data ingestion, transformations, warehouse loads, dbt-style models, batch/stream pipelines, or data pipeline architecture.
shinzoxD/knackbox/skills/data/sql-analytics Skill
0★ repoWrite analytical SQL for warehouses and BI questions with correct grain and caveats. Use whenever the user asks for warehouse SQL, BigQuery, Snowflake, Redshift, DuckDB analytics, funnel metrics in SQL, or reporting joins — as opposed to OLTP query performance tuning alone.
knownasnaffy/prompthound/dataset/case_00031 Skill
no license0★ repoMonitor the most recent run result of a configured OpenClaw cron job and send a compact Feishu private message with the latest execution time, status, and detail. Use when a user wants a standalone sk
knownasnaffy/prompthound/dataset/case_00060 Skill
no license0★ repoGuide for designing and implementing a PostgreSQL database that fuses PageIndex-style document trees with LightRAG-style entity-relationship anchors. Use this skill when Claude needs to design schemas, write ingestion logic, or implement retrieval SQL for a hybrid tree-graph knowledge base, especially when converting nested tree output into relational tables.
knownasnaffy/prompthound/dataset/case_00110 Skill
no license0★ repoWebMCP - Enable AI agents to interact with your web applications through structured tools. Implements the WebMCP standard for Next.js/React apps with tool registration, event bridge pattern, and conte
knownasnaffy/prompthound/dataset/case_00113 Skill
no license0★ repoSHA-256 prompt deduplication for LLM and TTS calls — hash normalize prompts, check cache before calling APIs, store results for instant replay. Use when making repeated or similar API calls to avoid redundant spending. Works with any database backend (SQLite, Turso, Postgres).
knownasnaffy/prompthound/dataset/case_00237 Skill
no license0★ repoGuide for designing and implementing a PostgreSQL database that fuses PageIndex-style document trees with LightRAG-style entity-relationship anchors. Use this skill when Claude needs to design schemas, write ingestion logic, or implement retrieval SQL for a hybrid tree-graph knowledge base, especially when converting nested tree output into relational tables.
knownasnaffy/prompthound/dataset/case_00263 Skill
no license0★ repoBrowser automation skill using Selenium for web scraping, form filling, and UI testing. Use when Codex needs to automate browser interactions including: (1) Filling forms and submitting data, (2) Web scraping and data extraction, (3) UI testing and validation, (4) Clicking buttons and navigating pages, (5) Handling alerts and popups, (6) Taking screenshots of web pages
knownasnaffy/prompthound/dataset/case_00372 Skill
no license0★ repoWeb scraping and data extraction using the Python Scrapling library. Use to scrape static HTML pages, JavaScript-rendered pages (Playwright), and anti-bot or Cloudflare-protected sites (stealth browser). Supports CSS selectors, XPath, adaptive DOM relocation so selectors survive site redesigns, session-based scraping with cookie persistence, and outputs to JSON or Markdown. Use when asked to scrape a URL, extract text/links/tables/prices from a webpage, crawl a site, or automate web data collection.
knownasnaffy/prompthound/dataset/case_00427 Skill
no license0★ repoHigh-performance containerized web scraper (Docker + Crawlee + Playwright). Use when user mentions any of these: 爬虫, 爬取, 抓取, 采集, 数据采集, 爬数据, 抓数据, 获取数据, scrape, crawl, extract, fetch data, pull data, 亚马
knownasnaffy/prompthound/dataset/case_00443 Skill
no license0★ repoCreate and publish WeChat Official Account (公众号) articles. Use when: (1) User wants to auto-post to WeChat Official Account, (2) Create draft from title + content, (3) Publish draft to 公众号, (4) Schedu
knownasnaffy/prompthound/dataset/case_00459 Skill
no license0★ repoSearch, enrich, and manage family heritage and historical relationship data from the LiùDào (六道) SQLite database. Use this skill when answering questions about historical figures, calculating relationship paths (A的B), or adding new personal records with privacy controls.
knownasnaffy/prompthound/dataset/case_00485 Skill
no license0★ repoPersistent adaptive memory for AI agents. Store memories that fade naturally over time (temporal decay), deduplicate automatically (0.85 cosine threshold), score novel information higher (surprise scoring), and search semantically via sqlite-vec KNN. Use when: you need long-term memory across sessions, memory that adapts to what matters, persistent identity blocks, multi-agent memory isolation, or memory that works without cloud services. NOT for: simple key-value storage, ephemeral session context, or when you need a full vector database like Qdrant/Pinecone. Runs entirely on SQLite — no external database server needed.
knownasnaffy/prompthound/dataset/case_00487 Skill
no license0★ repoDatabase schema management using idempotent sync script instead of Alembic migrations. Use when (1) Adding new database tables, (2) Adding new columns to existing tables, (3) Modifying database schema, (4) Deploying to production, (5) Syncing schema across environments. REQUIRED APPROACH - ALWAYS use scripts/sync-production-schema.py with --dry-run first, NEVER run Alembic migrations directly in production.
knownasnaffy/prompthound/dataset/case_00560 Skill
no license0★ repoZero-bot-detection web scraping for OpenClaw. Bypass Cloudflare, handle JavaScript-heavy sites, and adapt to website changes automatically. Use when you need to scrape protected websites, extract data from dynamic JavaScript SPAs, or bypass anti-bot detection systems. Supports three modes - basic (fast HTTP), stealth (undetectable), dynamic (browser automation).
knownasnaffy/prompthound/dataset/case_00584 Skill
no license0★ repo大数据开发工程师级数据分析与SQL技能。(1)多数据引擎SQL编写(Hive/SparkSQL/Presto/ClickHouse/Doris/MySQL/PG/BigQuery)。(2)复杂SQL改造调试与性能优化。(3)数仓建模(ODS/DWD/DWS/ADS)维度设计/SCD变更。(4)数据探查/指标设计/ETL管线编排。(5)数据质量检测与异常分析。(6)SQL改写(方言迁移/语法适配)。(7)UDF/UDTF开发规范。(8)表结构文档自动生成与迁移支持。(9)知识库目录生成与维护(schema/metrics/relations/enums)。触发:写SQL/改SQL/数仓建模/ETL/SQL优化/数据质量/指标设计/整理文档/生成md/迁移文档/知识库
knownasnaffy/prompthound/dataset/case_00614 Skill
no license0★ repoSearch, enrich, and manage family heritage and historical relationship data from the LiùDào (六道) SQLite database. Use this skill when answering questions about historical figures, calculating relationship paths (A的B), or adding new personal records with privacy controls.
knownasnaffy/prompthound/dataset/case_00719 Skill
no license0★ repoBrowser automation skill using Selenium for web scraping, form filling, and UI testing. Use when Codex needs to automate browser interactions including: (1) Filling forms and submitting data, (2) Web scraping and data extraction, (3) UI testing and validation, (4) Clicking buttons and navigating pages, (5) Handling alerts and popups, (6) Taking screenshots of web pages
knownasnaffy/prompthound/dataset/case_00802 Skill
no license0★ repoScrapes commercial real estate listings from Crexi and LoopNet using Claude in Chrome on a Mac Mini with residential IP. Bypasses Cloudflare bot protection. Extracts structured financials, broker contacts, and AI investment analysis. Saves to SQLite and syncs to OpenClaw Command Center dashboard.
knownasnaffy/prompthound/dataset/case_00851 Skill
no license0★ repoPersistent adaptive memory for AI agents. Store memories that fade naturally over time (temporal decay), deduplicate automatically (0.85 cosine threshold), score novel information higher (surprise scoring), and search semantically via sqlite-vec KNN. Use when: you need long-term memory across sessions, memory that adapts to what matters, persistent identity blocks, multi-agent memory isolation, or memory that works without cloud services. NOT for: simple key-value storage, ephemeral session context, or when you need a full vector database like Qdrant/Pinecone. Runs entirely on SQLite — no external database server needed.
knownasnaffy/prompthound/dataset/case_00882 Skill
no license0★ repoWeb scraping and data extraction using the Python Scrapling library. Use to scrape static HTML pages, JavaScript-rendered pages (Playwright), and anti-bot or Cloudflare-protected sites (stealth browser). Supports CSS selectors, XPath, adaptive DOM relocation so selectors survive site redesigns, session-based scraping with cookie persistence, and outputs to JSON or Markdown. Use when asked to scrape a URL, extract text/links/tables/prices from a webpage, crawl a site, or automate web data collection.
knownasnaffy/prompthound/dataset/case_00887 Skill
no license0★ repoCaptures data quality issues, metric drift, pipeline failures, misleading visualizations, metric definition mismatches, and data freshness problems to enable continuous analytics improvement. Use when: (1) An ETL/ELT pipeline fails, (2) A metric value shows anomalous behavior, (3) Two teams define the same metric differently, (4) A dashboard shows wrong or misleading data, (5) A data freshness SLA is missed, (6) A schema change breaks downstream consumers.
knownasnaffy/prompthound/dataset/case_00949 Skill
no license0★ repoStealth web scraper. Give it any URL and it punches through Cloudflare, bot detection, and WAFs automatically using a 3-tier cascade (plain HTTP → TLS spoof → full JS). No API keys, no proxies, no CDP Chrome. Free from the Flow team. Use when scraping any website, bypassing bot protection, spidering a full site, or extracting clean markdown from any page.
knownasnaffy/prompthound/dataset/case_00995 Skill
no license0★ repoPersistent adaptive memory for AI agents. Store memories that fade naturally over time (temporal decay), deduplicate automatically (0.85 cosine threshold), score novel information higher (surprise scoring), and search semantically via sqlite-vec KNN. Use when: you need long-term memory across sessions, memory that adapts to what matters, persistent identity blocks, multi-agent memory isolation, or memory that works without cloud services. NOT for: simple key-value storage, ephemeral session context, or when you need a full vector database like Qdrant/Pinecone. Runs entirely on SQLite — no external database server needed.
knownasnaffy/prompthound/dataset/case_01083 Skill
no license0★ repoWeb scraping and data extraction using the Python Scrapling library. Use to scrape static HTML pages, JavaScript-rendered pages (Playwright), and anti-bot or Cloudflare-protected sites (stealth browser). Supports CSS selectors, XPath, adaptive DOM relocation so selectors survive site redesigns, session-based scraping with cookie persistence, and outputs to JSON or Markdown. Use when asked to scrape a URL, extract text/links/tables/prices from a webpage, crawl a site, or automate web data collection.
knownasnaffy/prompthound/dataset/case_01154 Skill
no license0★ repoReconcile Indian GST invoice data with UPI transaction statements and produce audit-ready matched/unmatched reports. Use when the user asks to reconcile GST vs UPI collections, find missing payments,
knownasnaffy/prompthound/dataset/case_01156 Skill
no license0★ repoBrowser automation skill using Selenium for web scraping, form filling, and UI testing. Use when Codex needs to automate browser interactions including: (1) Filling forms and submitting data, (2) Web scraping and data extraction, (3) UI testing and validation, (4) Clicking buttons and navigating pages, (5) Handling alerts and popups, (6) Taking screenshots of web pages
knownasnaffy/prompthound/dataset/case_01175 Skill
no license0★ repoPowerful web scraping, crawling, and data extraction with stealth anti-bot bypass (Cloudflare Turnstile, CAPTCHAs). Use when: (1) scraping websites that block normal requests, (2) extracting structured data from web pages, (3) crawling multiple pages with concurrency, (4) taking screenshots of web pages, (5) extracting links, (6) any web scraping task that needs stealth/anti-detection, (7) user asks to scrape/crawl/extract from URLs, (8) need to bypass Cloudflare or other bot protection. Supports CSS/XPath selectors, adaptive element tracking (survives site redesigns), multi-session spiders, pause/resume crawls, proxy rotation, and async operations. Powered by MyClaw.ai.
knownasnaffy/prompthound/dataset/case_01219 Skill
no license0★ repoDecode, inspect, and validate JWT (JSON Web Token) tokens from the command line. Shows header, payload, algorithm, expiry status, and known claim labels. Use when debugging auth tokens, checking if a JWT is expired, inspecting JWT claims, decoding Bearer tokens, or analyzing token structure. Triggers on "decode JWT", "inspect token", "JWT expired", "parse JWT", "check Bearer token", "token claims".
knownasnaffy/prompthound/dataset/case_01334 Skill
no license0★ repoSend images directly in Feishu chat as native image messages (not file attachments). Use when: need to send a generated image, chart, screenshot, or any local image file to a Feishu user or group chat
knownasnaffy/prompthound/dataset/case_01343 Skill
no license0★ repoDesign, analyze, optimize and evolve database schemas. Use when the user asks to design schemas from scratch, choose between SQL and NoSQL engines, analyze or fix an existing schema (normalization, naming, constraints), plan index strategy, generate migration scripts, or interpret EXPLAIN plans.
knownasnaffy/prompthound/dataset/case_01348 Skill
no license0★ repoWeb scraping and data extraction using the Python Scrapling library. Use to scrape static HTML pages, JavaScript-rendered pages (Playwright), and anti-bot or Cloudflare-protected sites (stealth browser). Supports CSS selectors, XPath, adaptive DOM relocation so selectors survive site redesigns, session-based scraping with cookie persistence, and outputs to JSON or Markdown. Use when asked to scrape a URL, extract text/links/tables/prices from a webpage, crawl a site, or automate web data collection.
knownasnaffy/prompthound/dataset/case_01369 Skill
no license0★ repo大数据开发工程师级数据分析与SQL技能。(1)多数据引擎SQL编写(Hive/SparkSQL/Presto/ClickHouse/Doris/MySQL/PG/BigQuery)。(2)复杂SQL改造调试与性能优化。(3)数仓建模(ODS/DWD/DWS/ADS)维度设计/SCD变更。(4)数据探查/指标设计/ETL管线编排。(5)数据质量检测与异常分析。(6)SQL改写(方言迁移/语法适配)。(7)UDF/UDTF开发规范。(8)表结构文档自动生成与迁移支持。(9)知识库目录生成与维护(schema/metrics/relations/enums)。触发:写SQL/改SQL/数仓建模/ETL/SQL优化/数据质量/指标设计/整理文档/生成md/迁移文档/知识库
knownasnaffy/prompthound/dataset/case_01411 Skill
no license0★ repoConnect AI agents to 700+ external APIs using Nango. Handles OAuth, authentication flows, and tool calling for any API. Use when integrating agents with external services (Google, Slack, GitHub, Salesforce, etc.), setting up API access for agents, or when you need OAuth/API key management for AI tools. Triggers on "nango", "api integration", "oauth for agents", "connect api", "external api access".
knownasnaffy/prompthound/dataset/case_01591 Skill
no license0★ repoWeb scraping and data extraction using the Python Scrapling library. Use to scrape static HTML pages, JavaScript-rendered pages (Playwright), and anti-bot or Cloudflare-protected sites (stealth browser). Supports CSS selectors, XPath, adaptive DOM relocation so selectors survive site redesigns, session-based scraping with cookie persistence, and outputs to JSON or Markdown. Use when asked to scrape a URL, extract text/links/tables/prices from a webpage, crawl a site, or automate web data collection.
knownasnaffy/prompthound/dataset/case_01696 Skill
no license0★ repoAtlassian Confluence expert for creating and managing spaces, knowledge bases, and documentation. Configures space permissions and hierarchies, creates page templates with macros, sets up documentatio
knownasnaffy/prompthound/dataset/case_01697 Skill
no license0★ repoUse Bitquery GraphQL through UXC for onchain trades, transfers, token holder analysis, balances, and market structure queries across supported networks, with OAuth client_credentials authentication and query-first execution.
knownasnaffy/prompthound/dataset/case_01759 Skill
no license0★ repoUse when context is lost after switching surfaces (Telegram to WhatsApp, TUI to Telegram), when handing off tasks between agents (Jon → Eddie, Cipher → Eddie), when an agent needs to know what was dis
knownasnaffy/prompthound/dataset/case_01813 Skill
no license0★ repoZero-bot-detection web scraping for OpenClaw. Bypass Cloudflare, handle JavaScript-heavy sites, and adapt to website changes automatically. Use when you need to scrape protected websites, extract data from dynamic JavaScript SPAs, or bypass anti-bot detection systems. Supports three modes - basic (fast HTTP), stealth (undetectable), dynamic (browser automation).
knownasnaffy/prompthound/dataset/case_01854 Skill
no license0★ repoSHA-256 prompt deduplication for LLM and TTS calls — hash normalize prompts, check cache before calling APIs, store results for instant replay. Use when making repeated or similar API calls to avoid redundant spending. Works with any database backend (SQLite, Turso, Postgres).
knownasnaffy/prompthound/dataset/case_01871 Skill
no license0★ repoRecord daily work items in a local SQLite database, replace a day's report when the user wants to correct it, edit or delete one logged task by entry id, track entry history, inspect the historical changes for a specific report date, and retrieve daily or weekly progress summaries. Use when the user asks Codex to log completed work for a day, modify an existing daily report, update or delete a single logged task, inspect version history, inspect date-level history, look up what they worked on on a specific date, or summarize progress for the current or requested week.
knownasnaffy/prompthound/dataset/case_01915 Skill
no license0★ repoFormat, minify, and lint SQL queries from the command line. Formats SQL with proper indentation and keyword casing, minifies by removing whitespace and comments, and lints for common anti-patterns (SELECT *, inconsistent casing, missing semicolons, trailing whitespace). No external dependencies — pure Python. Use when formatting SQL queries, cleaning up SQL files, minifying SQL for production, or checking SQL quality.
knownasnaffy/prompthound/dataset/case_01921 Skill
no license0★ repoExpert n8n workflow builder that creates, deploys, and manages n8n workflows programmatically via the n8n REST API. Use when asked to create n8n workflows, automate n8n tasks, build automations, design workflow pipelines, connect services via n8n, or manage existing n8n workflows. Handles webhook flows, scheduled tasks, AI agents, database syncs, conditional logic, error handling, and any n8n node configuration.
knownasnaffy/prompthound/dataset/case_01951 Skill
no license0★ repoCaptures data quality issues, metric drift, pipeline failures, misleading visualizations, metric definition mismatches, and data freshness problems to enable continuous analytics improvement. Use when: (1) An ETL/ELT pipeline fails, (2) A metric value shows anomalous behavior, (3) Two teams define the same metric differently, (4) A dashboard shows wrong or misleading data, (5) A data freshness SLA is missed, (6) A schema change breaks downstream consumers.