118 个（obra 的仓库） · 按人气排序
Examine superpowers session records to document repeated work, departures from plans, delays, and token usage. Produce an evidence-based report with file and line references, and prepare bug-report material when requested.
中文简介正在准备中。当前显示英语简介。
Assign independent bugs or test failures to separate agents that work at the same time. Define each agent’s scope and expected report, then check for conflicting changes and run the full test suite before integrating fixes.
中文简介正在准备中。当前显示英语简介。
Evaluate code review feedback against the actual code, supported environments, and existing behavior. Clarify uncertain requests, respond with technical evidence, and implement valid changes one at a time with tests for each fix.
中文简介正在准备中。当前显示英语简介。
Finish completed development work by checking the full test suite and presenting integration choices: merge locally, create a Pull Request, or keep the branch. It carries out the selected path and handles workspace cleanup accordingly.
中文简介正在准备中。当前显示英语简介。
Guide an agent to check and invoke relevant skills before replying or taking action. It sets the order for choosing workflow and implementation skills, with reference guides for adapting the process to different agent environments.
中文简介正在准备中。当前显示英语简介。
Clarifies the purpose, preferences, and constraints of a new feature or project through conversation. When useful, it offers mockups or temporary prototypes, then captures an agreed description or written design before implementation begins.
中文简介正在准备中。当前显示英语简介。
Carry out an implementation plan by assigning each task to a separate agent, then reviewing specification compliance and code quality. Keep progress in files and review the complete set of changes after all tasks are finished.
中文简介正在准备中。当前显示英语简介。
Requests a code review from a separate agent after implementation or before merging. It provides the change summary, requirements, and commit range, then guides follow-up work according to the severity of the findings.
中文简介正在准备中。当前显示英语简介。
Checks whether work is truly complete before reporting success, committing changes, or creating a pull request. It runs the relevant checks, reads their full output, and ties status reports to current evidence.
中文简介正在准备中。当前显示英语简介。
Prepare a separate workspace for feature development using platform tools or git worktree, which gives a branch its own working directory. It checks existing isolation, prepares dependencies, and runs tests before implementation begins.
中文简介正在准备中。当前显示英语简介。
Guides feature development and bug fixes by writing tests before implementation. It confirms each test fails for the expected reason, adds only enough code to pass, and checks the full test suite before completion.
中文简介正在准备中。当前显示英语简介。
Turn specifications or requirements into an implementation plan before coding begins. Break work into testable tasks with exact files, function definitions, test assertions, and verification commands, so another developer or agent can follow the plan.
中文简介正在准备中。当前显示英语简介。
Create, revise, and validate agent skills through tests that compare behavior with and without the instructions. It helps identify unclear guidance, choose an appropriate document structure, and refine wording before deployment.
中文简介正在准备中。当前显示英语简介。
Investigate bugs, failing tests, and unexpected behavior using reproduction steps, logs, and recent changes. Follow a structured process to identify the root cause, test a specific explanation, and verify the resulting fix.
中文简介正在准备中。当前显示英语简介。
Carry out an existing implementation plan in one session, task by task. Verify each step with tests, record progress and decisions in a file, and finish with a review of all changes on the branch.
中文简介正在准备中。当前显示英语简介。
Dispatch code-reviewer subagent to review implementation against plan or requirements before proceeding
中文简介正在准备中。当前显示原文说明。
Systematically trace bugs backward through call stack to find original trigger
中文简介正在准备中。当前显示原文说明。
Flip core assumptions to reveal hidden constraints and alternative approaches - "what if the opposite were true?"
中文简介正在准备中。当前显示原文说明。
Search previous Claude Code conversations for facts, patterns, decisions, and context using semantic or text search
中文简介正在准备中。当前显示原文说明。
Force unrelated concepts together to discover emergent properties - "What if we treated X like Y?"
中文简介正在准备中。当前显示原文说明。
Four-phase debugging framework that ensures root cause investigation before attempting fixes. Never jump to solutions.
中文简介正在准备中。当前显示原文说明。
Test at extremes (1000x bigger/smaller, instant/year-long) to expose fundamental truths hidden at normal scales
中文简介正在准备中。当前显示原文说明。
Complete feature development with structured options for merge, PR, or cleanup
中文简介正在准备中。当前显示原文说明。
Execute detailed plans in batches with review checkpoints
中文简介正在准备中。当前显示原文说明。