78 skills · sorted by relevance
This skill should be used when the user asks to "fix a bug with minimal changes", "analyze change scope for a bugfix", "find the minimal set of files to change", "do a focused bugfix", or "scope a minimal repair".
The English summary is being prepared. Showing the original description.
系统性 Bug 修复流水线（P0-P8）：一次修一个，强制根因分析、独立 worktree、TDD、双层验收报告、forge-qa 回归；多会话经 .forge/active.md 防撞车。 铁律：不做根因分析不写代码；新发现禁止顺手修；没有用户最终结论不合并。 触发方式：用户说"bugfix"、"反馈个问题"、"修这个 bug"、"这里有问题"、"为什么不对"、"排查一下"、"investigate"、"forge-bugfix"，或报告错误、异常行为、功能失效时。
The English summary is being prepared. Showing the original description.
Root cause based one-shot bug fix. debugger diagnosis → requirements.md generation → /execute. /bugfix "error description" Full investigation pipeline: debugger + gap-analyzer + standard verify. QA suggestion after successful fix.
The English summary is being prepared. Showing the original description.
软件开发团队主理人（齐活林 · 交付总监）。统筹 4 位专家（产品经理/架构师/工程师/QA）按 SOP 工作流完成软件交付。支持快速模式（小需求/BugFix）和标准 SOP（中大型需求）。 触发词："帮我开发"、"帮我做一个"、"写一个应用"、"做个游戏"、"开发一个系统"、"修复 Bug"、"搭建项目"。 路由逻辑：小需求（≤10源文件/单页/小游戏）走快速模式 → 工程师直写；Bug修复走BugFix路径；中大型需求走完整PRD→架构→编码→测试SOP。
The English summary is being prepared. Showing the original description.
QA 纯验收（只测不修）：Mode A 完整验收（test-spec → 10 维度断言引擎 → 报告 + User Gate）；Mode B 供 forge-bugfix P6 调用做单 bug 回归并回填 BF 报告。 铁律：每个测试必须有 pass/fail 和深层断言；console.error 零容忍；不猜端口，只用传入的 app_url。 触发方式：Mode A 用户说"测试"、"QA"、"forge-qa"或 forge-dev 调度；Mode B 由 forge-bugfix P6 调用（传 review_doc）。
The English summary is being prepared. Showing the original description.
系统的 6 阶段 Core Debugging 协议。结构化 Bug 处理流程，包含快速检查、隔离测试、20分钟规则和 Bug 报告模板。
The English summary is being prepared. Showing the original description.
Систематический 6-фазный протокол отладки. Структурированный подход к багам с быстрыми проверками, изолированным тестированием, правилом 20 минут и шаблоном отчета об ошибке.
The English summary is being prepared. Showing the original description.
Protocolo sistemático de depuración en 6 fases. Enfoque estructurado ante errores con verificaciones rápidas, pruebas aisladas, regla de los 20 minutos y plantilla de informe de errores.
The English summary is being prepared. Showing the original description.
体系的な 6 段階デバッグプロトコル。クイックチェック、孤立テスト、20分ルール、バグレポートテンプレートを備えた構造化アプローチ。
The English summary is being prepared. Showing the original description.
Systematic 6-phase debugging protocol. Structured approach to bugs with quick checks, isolated testing, 20-minute rule, and bug report template.
The English summary is being prepared. Showing the original description.
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.
Format completed work in Grok Bot's claude-mem workflow as searchable XML records with a title, facts, file paths, and narrative. Return a skip marker for idle or initialization states, or when no tool results exist.
Create and check Git branch names using Conventional Branch rules. Choose a prefix for the task, normalize the description, detect the repository’s base branch, and create and switch to the new branch.
Fix bugs reported in GitHub issues through a reproduce-first process. The workflow guides code changes, build checks, verification, regression tests that check for recurring failures, and review before considering the fix complete.
Manage separate local development environments for multiple branches using the project's pnpm worktree CLI. Each environment has its own ports and dependencies, with options to share Supabase or isolate database changes for testing.
Triage incorrect MNN outputs and regressions by matching symptoms to focused debugging guides. Use backend comparisons, minimal reproductions, and controlled experiments to investigate memory issues, quantization, concurrency, numeric limits, caches, and inconsistent results across runs.
Develop features and fix bugs by writing a behavior test first, observing its expected failure, and adding the minimum code needed to pass. Then clean up the code while keeping tests passing, applying this process where regression risk warrants it.
Run Nexent requirements and bugfixes through SPEC acceptance, traditional UT and applicable D1-D5 test design, product/test implementation, local verification, and delivery evidence. Use for features, fixes, refactors and post-development test backfill across APIs, UI, model and Agent behavior.
The English summary is being prepared. Showing the original description.
Implement and maintain Nexent's traditional Python UT for product changes and bugfixes under test/backend, test/sdk, and test/ext_components. Cover unit behavior, boundaries, errors and regression assertions with isolated pytest tests. Formal D1-D5 assets in test-e2e use nexent-test-assets.
The English summary is being prepared. Showing the original description.
Use when implementing any feature or bugfix, before writing implementation code
The English summary is being prepared. Showing the original description.
Triggers the WORK-PIPELINE when a user request starts with a [] tag (e.g., [new-feature], [bugfix], [WORK start]). Use this skill whenever you detect a [] tag at the beginning of a user message.
The English summary is being prepared. Showing the original description.
[omh] Software feature or bugfix not yet planned: structured planning before execution. Use when the user says: plan, implementation plan, make a plan, write a plan, write the plan, task breakdown, safe feature, safely add a feature.
The English summary is being prepared. Showing the original description.
Use when implementing any feature or bugfix, before writing implementation code
The English summary is being prepared. Showing the original description.
Drives implementation by writing a failing test first, then the smallest code that passes it. Use this before writing implementation code for any feature or bugfix, when a bug needs a regression test, when existing code is hard to change safely, or when someone asks whether a change is covered. Also use to decide what is worth testing and what is not.
The English summary is being prepared. Showing the original description.