bug-fixer
Skill19 starsChanged 30 days agoMITView on GitHub
Diagnose reproducible failures and restore established behavior. Investigate missing facts; unresolved changes to user experience belong to product requirements.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- LeilaoMi/operit-coding-skillstheir own version, first seen Oct 8, 2026
- Itsme23476/Skillstheir own version, first seen Mar 7, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- LeilaoMi/operit-coding-skills★ 4same name
- Itsme23476/Skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- design-brief-builderSkill
- design-makerSkill
- dev-builderSkill
- dev-plannerSkill
- goal-writerSkill
- product-spec-builderSkill
- project-knowledgeSkill
- release-builderSkill
- reviewerSkill
- self-evolverSkill
- skill-builderSkill
- creatorSkill
The file
Files
缺陷修复技能 (bug-fixer)
Purpose
用可复现证据定位根因并恢复已经明确的预期行为。不要靠猜测修复,也不要把新的产品决策伪装成 Bug。
Trigger
- 报错、失败测试、审查意见或稳定复现步骤表明既有行为失效。
- 正确行为能由 Product Spec、公开接口、历史行为、测试或用户确认确定。
- 仅改变内部实现且不新增能力、不改变外部契约。
正确行为不清、证据互相矛盾或需要改变公开行为时,不触发本技能,转交 product-spec-builder。
Required context
- 预期行为及来源。
- 实际现象、复现步骤、日志或失败测试。
- 范围、非目标、完成证据和 R0/R1/R2。
- 相关代码、历史变更和当前验证入口。
缺少复现条件时,先形成最小诊断假设;无法验证任何假设则停止。
Workflow
- 复现问题,区分已证实事实、合理推断和未知项。
- 提出有证据的有限根因假设,优先验证最能区分原因的检查;独立调查可并行,避免重复写入和无界尝试,收敛到最小充分证据链。
- 实施最小完整修复,不用大重构掩盖未知根因。
- 复跑原失败证据,并补充与风险相称的回归检查。
- 范围改变时更新相关契约,按具体影响重新评级;只有 R2 才自动要求 fresh reviewer,路线升级不自动等于 R2。
- 修复后同步受影响现状、命令与任务状态,不引用已失效的历史决定。
Output
- 根因与证据。
- 修改文件和修复说明。
- 原问题验证、回归结果、失败或跳过项。
- 风险级别、残余风险和 reviewer 结论(如适用)。
Stop or escalate
- 正确行为需要用户或产品决策:升级为产品变更。
- 唯一方案会改变公开 API、数据、权限、业务流程或兼容性:升级为产品变更。
- 只能通过吞错、禁用检查或扩大范围隐藏问题:停止。
- 没有可复现或可替代验证证据:标记阻塞,不声明已修复。
References
执行前读取 stage-contract.md。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

