Loading...
Loading...
Found 3,166 Skills
Execute an existing plan file. Use when a user asks to carry out a .plan.md task list.
Iteratively run a local Supabase reset, database tests, and type generation until they succeed, fixing issues between runs. Use when asked to reset the local Supabase DB, run `supabase test db`, and regenerate types (`npm run gen-types`) in a loop.
Generate cross-platform installation scripts for any software, library, or module. Use when users ask to "create an installer", "generate installation script", "automate installation", "setup script for X", "install X on any OS", or need automated deployment across Windows, Linux, and macOS. The skill follows a three-phase approach: (1) Environment exploration - detect OS, gather system info, check dependencies; (2) Installation planning - propose steps with verification; (3) Execution with documentation generation.
Identify undefined areas in the current feature specification by asking up to 5 highly targeted clarification questions, and encode the answers back into the specification. Trigger words include: "speckit-clarify", "speckit clarification", "specification clarification", "feature clarification", "identify ambiguities", "clarify requirements".
Generate release notes from git commits and GitHub PRs/issues. Use when asked to "create release notes", "generate changelog", "prepare release", "what changed since last release", or need to document changes for a new version. Analyzes commit history, merged PRs, and closed issues to produce GitHub Releases formatted notes.
Dispatch, reconcile, and upsert group webhook pushes after tasks reach terminal states. Use to trigger by TaskID/GroupID, run one-shot backfill by date for pending/failed, and write webhook plans into WEBHOOK_BITABLE_URL (JSON/JSONL).
综合页搜索完成后，从本地 sqlite capture_results 聚类/阈值筛选盗版分组；并通过 feishu-bitable-task-manager 创建子任务、通过 group-webhook-dispatch upsert webhook 计划。用于 wechat-search-collector 综合页搜索后置流程（detect.json 产出/读取、子任务创建、webhook 计划写入）。
Automated collection process for WeChat Channels search and result traversal (Android), supporting scenarios such as comprehensive page search and personal page search.
Use when setting up UI test recording in Xcode 26, enhancing recorded tests for stability, or configuring test plans for multi-configuration replay. Based on WWDC 2025-344 "Record, replay, and review".
Collect app events via evalpkgs into sqlite, then filter/report capture_results to Feishu Bitable with retry-safe writeback. Use for collect-start/collect-stop/filter/report/retry-reset workflows.
Executes OpenAI Codex CLI for code analysis, refactoring, and automated editing. Activates when users mention codex commands, code review requests, or automated code transformations requiring advanced reasoning models.
Transform infrastructure documentation, runbooks, and operational knowledge into reusable Claude Code skills. Convert Proxmox configs, Docker setups, Kubernetes deployments, and cloud infrastructure patterns into structured, actionable skills.