查找技能

Converts XLSX spreadsheets, including multi-sheet workbooks, into CSV files that can be read and grepped directly. Use whenever an .xlsx report needs processing — exports from Xero, Cryptio, bank statements, or any tool that delivers spreadsheet output.

中文简介正在准备中。当前显示原文说明。

Runs the full implement-and-commit loop over a task list — selects the next incomplete sub-task, implements it, runs linters and tests, marks it done, commits, and repeats until the list is finished. Use when asked to work through a feature's task list at .ai/[feature]/tasks.md unattended, or to keep going until every sub-task is complete. For a single sub-task with no commit, use task-implementation; to stop for approval between each one, use iterative-development.

中文简介正在准备中。当前显示原文说明。

Reports how local Git branches are progressing toward canonical upstream inclusion as a compact terminal table plus a browser-rendered HTML report, with branch purpose, stack dependencies, Git Machete topology, ahead/behind counts, change-request status, and next action. Use when asked for upstreaming status, local branch submission progress, which branches have change requests, or what remains before they can land.

中文简介正在准备中。当前显示原文说明。

Watch a CI run's jobs to completion without idling or hand-writing a poll loop. Use when a dispatched or pushed build takes minutes to finish and its per-job results decide the next step.

中文简介正在准备中。当前显示原文说明。

Scan every open pull request in a GitHub repository, filter to the ones that are genuinely mergeable now, and report a compact verdict with a suggested merge order. Use when the user asks which PRs can be merged, wants an open-PR backlog triaged or reviewed in bulk, asks why a PR is blocked, or wants to clear a queue of stale or bot-reviewed PRs.

中文简介正在准备中。当前显示原文说明。

Prepare and publish upstream issues, feature requests, discussions, pull or merge requests, and patch submissions in the channel the canonical project expects. Use when reporting a problem upstream, requesting a feature, contributing a change, or asking to submit upstream.

中文简介正在准备中。当前显示原文说明。

Discover and run tests that provide meaningful evidence for a code change. Use after implementation, before handoff or commit, or when the user asks to validate behavior.

中文简介正在准备中。当前显示原文说明。

Implements one numbered sub-task from a task list at .ai/[feature]/tasks.md, running linters and tests, without staging, committing, or marking the task complete. Use when asked to carry out a specific sub-task by number, or as the inner step of a larger loop that handles commits separately. For the full loop including commits, use task-orchestration.

中文简介正在准备中。当前显示原文说明。

Makes the agent reconsider a task it just handed back to the human and find a way to do it itself, checking memory, CLI tools, skills, MCP servers, and documentation in turn. Use when the user invokes `/you` or `$you`, or replies that the agent should do something itself rather than asking them.

中文简介正在准备中。当前显示原文说明。

General Xero browser automation notes. Use when automating any Xero page with agent-browser — covers non-standard UI patterns, waiting, and dropdown menus.

中文简介正在准备中。当前显示原文说明。

Use the Xero MCP server — troubleshoot its self-refreshing OAuth2 token file, maintain the local best-of-breed server build, and pick up other operational notes for working with Xero MCP tools. Use when Xero MCP tools fail with authentication errors, before starting any Xero workflow, when adding or updating upstream xero-mcp-server PRs, or for general guidance on Xero MCP usage.

中文简介正在准备中。当前显示原文说明。

Turns an existing Product Requirements Prompt at .ai/[feature]/prp.md into a step-by-step task list of parent tasks and sub-tasks, saved to .ai/[feature]/tasks.md and committed. Use when a PRP is ready to be broken down into implementable work, or when planning how a feature will be built before any implementation starts. To write the PRP itself first, use prp- generation.

中文简介正在准备中。当前显示原文说明。

Review staged changes and create atomic Git commits whose messages match repository conventions. Use when the user asks to commit, write a commit message, or finalize already staged work.

中文简介正在准备中。当前显示原文说明。

Structures git branches and worktrees: keeps unrelated changes on separate branches, isolates each in its own worktree created so the repository's setup runs, records dependencies with git-machete, and recombines them into a temporary mixdown branch for local testing. Use before creating any branch or worktree in a codebase that works on more than one branch, including branching off the default branch to start a change; when starting work in a fork, clone, or third-party checkout; when choosing what a new branch should be based on; when a branch is growing a second unrelated concern; when deciding whether to stack branches or keep them independent; when preparing a change for a pull request or patch submission; when handed an existing worktree or branch to implement and commit in a fork; or when a local build needs several in-progress branches combined. Not needed where the repository clearly commits everything to the trunk, or holds notes or personal data rather than code.

中文简介正在准备中。当前显示原文说明。

Use when working in a repository that uses bd or Beads for durable project task tracking, issue dependencies, blocker management, multi-session handoff, or shared work memory. Trigger when the user asks to find ready work, claim or close tasks, create follow-up work, inspect blockers, recover project context, or choose between local planning and persistent project tracking.

中文简介正在准备中。当前显示原文说明。

Generates a minimal .editorconfig with sensible defaults for a repository. Use when starting work in a new repository, when a project has no .editorconfig, or when the user asks to add or standardise editor and formatting settings.

中文简介正在准备中。当前显示原文说明。

Capture durable project or workflow knowledge discovered during work. Use when a mistake, hidden constraint, repeated question, or changed behavior reveals a documentation gap. To root-cause one specific mistake the agent just made and let the user pick fixes, use `learn` (`/learn`) instead.

中文简介正在准备中。当前显示原文说明。

Grind through ready beads serially in priority order, one at a time in the current worktree, without stopping between issues. Use when asked to work the beads queue, grind the backlog, keep working through ready issues, or make unattended progress overnight. For concurrent worktrees instead, use beads-parallel-grinding.

中文简介正在准备中。当前显示原文说明。

Stores a persistent memory or learning with `bd remember` so it survives across sessions. Use when the user invokes `/bdr` or `$bdr`, or asks to remember, note, or persist an insight in a Beads workspace.

中文简介正在准备中。当前显示原文说明。

Triages an already-dirty Git working tree: breaks down every uncommitted change hunk by hunk, separates deliberate edits from tool-written churn, possibly accidental reversions, misplaced scope, and sensitive content, asks the user about the ambiguous cases, and proposes an ordered set of commits plus a list of hunks to hold back. Use when the user invokes `/pc` or `$pc`, asks what they should commit, wants their uncommitted changes broken down, or wants commits proposed for a dirty working tree or pile of accumulated local modifications. To plan commit boundaries for a change before or while implementing it, use `incremental-commits` instead.

中文简介正在准备中。当前显示原文说明。

Decompose an approved implementation plan into self-contained Linear issues with zero guesswork. Use when breaking down a plan into actionable Linear tasks via the MCP server.

中文简介正在准备中。当前显示原文说明。

Researches and compares free and open source software projects in a supplied domain, using either user-named candidates or a discovered shortlist. Use when evaluating FOSS alternatives, comparing GitHub popularity, maintenance, licences, domain fit, trade-offs, or producing a linked HTML comparison report.

中文简介正在准备中。当前显示原文说明。

Puts the agent into a cautious production mode for live systems: read-only inspection may proceed, but credentials and out-of-scope personal data need permission first, every state-changing action needs explicit per-action approval with its resource risks and rollback stated, and anything unexpected halts work until the user decides. Use when the user invokes `/prod` or `$prod`, or says they are working on production, a live or customer-facing server, a mail server, or a production database, or asks for care on a system where mistakes affect real users.

中文简介正在准备中。当前显示原文说明。

Open a URL or local file in the user's regular browser, including live-rendered local Markdown. Use for `/open` or when the user asks to view a target outside the agent browser.

中文简介正在准备中。当前显示原文说明。