Feedback
codewhale-hq/Codewhale
Report a Codewhale bug or idea as a GitHub issue. An agent skill from codewhale-hq/Codewhale.
用于处理用户对已有实现的反馈分诊与执行闭环:先判断是否需要纳入 OpenSpec 活跃变更或新建变更,再完成根因分析、实现、验证和必要测试。凡是用户针对已有实现反馈 Bug、缺陷、改进点、建议或实现遗漏,即使没有明确提到“反馈”或 OpenSpec,也必须使用本技能。
$ npx skills add linaproai/linapro --skill lina-feedback -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install linaproai/linapro lina-feedback --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/linaproai/linapro.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/lina-feedback .claude/skills/lina-feedback && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "lina-feedback" agent skill from https://github.com/linaproai/linapro/tree/main/.agents/skills/lina-feedback into .claude/skills/lina-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lina-feedback", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/linaproai/linapro/tree/main/.agents/skills/lina-feedbackType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add linaproai/linapro --skill lina-feedback -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install linaproai/linapro lina-feedback --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/linaproai/linapro.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/lina-feedback .agents/skills/lina-feedback && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "lina-feedback" agent skill from https://github.com/linaproai/linapro/tree/main/.agents/skills/lina-feedback into .agents/skills/lina-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lina-feedback", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add linaproai/linapro --skill lina-feedback -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install linaproai/linapro lina-feedback --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/linaproai/linapro.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/lina-feedback .cursor/skills/lina-feedback && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "lina-feedback" agent skill from https://github.com/linaproai/linapro/tree/main/.agents/skills/lina-feedback into .cursor/skills/lina-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lina-feedback", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/linaproai/linapro.git --path .agents/skills/lina-feedback--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add linaproai/linapro --skill lina-feedback -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install linaproai/linapro lina-feedback --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/linaproai/linapro.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/lina-feedback .gemini/skills/lina-feedback && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "lina-feedback" agent skill from https://github.com/linaproai/linapro/tree/main/.agents/skills/lina-feedback into .gemini/skills/lina-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lina-feedback", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install linaproai/linapro lina-feedbackInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add linaproai/linapro --skill lina-feedback -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/linaproai/linapro.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/lina-feedback .github/skills/lina-feedback && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "lina-feedback" agent skill from https://github.com/linaproai/linapro/tree/main/.agents/skills/lina-feedback into .github/skills/lina-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lina-feedback", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add linaproai/linapro --skill lina-feedback -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install linaproai/linapro lina-feedback --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/linaproai/linapro.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/lina-feedback .opencode/skills/lina-feedback && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "lina-feedback" agent skill from https://github.com/linaproai/linapro/tree/main/.agents/skills/lina-feedback into .opencode/skills/lina-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lina-feedback", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
lina-feedback用于处理用户对已有实现的反馈分诊与执行闭环:先判断是否需要纳入 OpenSpec 活跃变更或新建变更,再完成根因分析、实现、验证和必要测试。凡是用户针对已有实现反馈 Bug、缺陷、改进点、建议或实现遗漏,即使没有明确提到“反馈”或 OpenSpec,也必须使用本技能。
Lina Feedback is an agent skill from linaproai/linapro. 用于处理用户对已有实现的反馈分诊与执行闭环:先判断是否需要纳入 OpenSpec 活跃变更或新建变更,再完成根因分析、实现、验证和必要测试。凡是用户针对已有实现反馈 Bug、缺陷、改进点、建议或实现遗漏,即使没有明确提到“反馈”或 OpenSpec,也必须使用本技能。
Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: 依赖 openspec CLI、lina-e2e 技能、lina-review 技能。
The repository describes itself as: AI-native full-stack framework engineered for sustainable delivery. The licence is Apache-2.0.
8 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 75395c8. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
gitFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
依赖 openspec CLI、lina-e2e 技能、lina-review 技能。
From compatibility in the SKILL.md frontmatter.
Lina Feedback loads about 2.2k tokens when it runs. Until then it costs about 37 tokens; SKILL.md has 376 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from linaproai/linapro at commit 75395c8, republished under its Apache-2.0 licence (© linaproai). 376 words, ~2,237 tokens.
.claude/skills/lina-feedback/SKILL.md (or your agent's skills folder).当用户在实现后发现 Bug、改进点或提出建议时,此技能先判断反馈是否值得沉淀为 OpenSpec 记录,再选择追加活跃变更、新建变更、直接修复或仅答复说明。进入 OpenSpec 路径的问题需要组织到tasks.md中的可追踪任务列表;未达到 OpenSpec 记录门槛的问题也必须完成清晰的根因分析、实现取舍、验证和结果说明。
核心原则:
openspec validate、静态扫描、文件检查、格式检查或审查结论等治理验证方式交互语言:与用户交互的内容语言以用户上下文使用的语言为准,用户使用英文则使用英文,用户使用中文则使用中文。
关键规则:
openspec/changes/下、且未被移入openspec/changes/archive/的变更目录。不要将status: complete、所有任务已勾选或其他完成信号视为"非活跃",除非实际已归档。openspec list --json
# 或:ls openspec/changes/ | grep -v archive当两个信号不一致时,优先遵循文件系统规则:
openspec/changes/下且不在archive/中,则为活跃变更。openspec list --json可能仍将此类变更报告为status: complete;这仅表示实现任务已完成,不表示变更已归档。openspec/changes/archive/下的已归档变更才是非活跃的。处理路径:
| 路径 | 判定标准 | 操作 |
|---|---|---|
openspec-existing | 反馈直接修正或补全某个活跃变更的目标、验收、实现缺口、回归问题或治理门禁 | 追加到该活跃变更的tasks.md,必要时更新specs/ |
openspec-new | 反馈形成新的可持续产品能力、模块/API/数据/权限契约、跨模块设计、架构决策或需要长期追踪的治理规则 | 新建变更,再写入最小必要 OpenSpec 文档 |
direct-fix | 反馈是局部实现问题、文案/技能说明微调、轻量治理修正、低风险测试补充,或不具备长期规范沉淀价值 | 不创建或追加 OpenSpec;直接做根因分析、修复和验证,并在结果中说明跳过 OpenSpec 的理由 |
no-change | 反馈只是讨论、已被现有实现覆盖、暂不采纳的建议,或需要先澄清而不能安全落地 | 不修改文件;输出判断依据、已检查证据和下一步条件 |
应进入 OpenSpec 的常见信号:
通常不进入 OpenSpec 的信号:
分诊后必须先告知:
### 反馈分诊
- 处理路径:direct-fix / openspec-existing / openspec-new / no-change
- 判断依据:<反馈是否达到 OpenSpec 记录门槛的原因>
- 活跃变更:<无 / 已考虑的变更及相关性>
- 后续动作:<直接修复 / 写入目标变更 / 新建变更 / 仅说明>存在多个活跃变更时:
只有在处理路径为openspec-existing且多个活跃变更都高度相关、无法可靠自主选择时,才向用户确认目标变更。
检测到多个活跃变更。此反馈应追加到哪个变更?
1. config-management — 系统配置 CRUD 管理
2. user-auth — 用户认证增强
请选择 1 或 2:如果只有一个活跃变更与反馈强相关,则自动选择并告知;如果存在活跃变更但均不相关,不要强行追加。
需要新建变更时:
openspec new change "<name>"proposal.md(一段话概述上下文)design.md,除非涉及架构变更OpenSpec 路径告知:"将反馈修复应用到变更:<名称>"
如果处理路径为openspec-existing或openspec-new,读取目标变更上下文:
| 文件 | 用途 |
|---|---|
tasks.md | 任务结构、命名规范、编号 |
design.md | 架构上下文 |
proposal.md | 功能范围和意图 |
specs/ | 增量规范定义 |
# 查找目标模块目录内的 TC ID,用于按模块本地递增规划测试编号
find hack/tests/e2e/<module> -maxdepth 1 -type f -name 'TC*.ts' | sort
# 或源码插件:
find apps/lina-plugins/<plugin-id>/hack/tests/e2e/<module> -maxdepth 1 -type f -name 'TC*.ts' | sort如果处理路径为direct-fix或no-change,只读取判断和验证所需的源码、文档、测试、规则文件或运行证据;不要为了形式化流程创建 OpenSpec 文档。
外部规则文件:
AGENTS.md作为顶层规范入口。AGENTS.md的强制规则加载矩阵识别反馈命中的规则域,并在分诊、记录任务、修改规范、修复代码或输出审查结论前读取所有对应的.agents/rules/*.md。i18n、缓存一致性、数据权限、开发工具跨平台和测试影响。若存在影响,必须读取对应规则文件并按其中的设计、实现、验证和审查要求执行;若确认无影响,也必须在该反馈的影响分析或审查结论中明确记录。.agents/rules/backend-go.md;API 契约读取.agents/rules/api-contract.md;SQL 和 DAO 读取.agents/rules/database.md;缓存读取.agents/rules/cache-consistency.md;数据权限读取.agents/rules/data-permission.md;源码插件、动态插件、插件同构开发目录和插件生命周期资源读取.agents/rules/plugin.md;前端 UI 读取.agents/rules/frontend-ui.md;测试读取.agents/rules/testing.md;开发工具读取.agents/rules/dev-tooling.md;文档治理读取.agents/rules/documentation.md;OpenSpec 流程读取.agents/rules/openspec.md;i18n读取.agents/rules/i18n.md。对每个报告的问题:
按类型分类:
按规范影响分类:
| 级别 | 定义 | 操作 |
|---|---|---|
| implementation | 规范正确,代码有误 | 仅修复代码 |
| spec-level | 需求缺失/不完整/已变更 | 先更新规范,再修复 |
| internal | 无用户可观察变更但涉及可执行行为 | 修复代码,优先单元测试 |
| governance | 文档命名、规范文本、OpenSpec 记录、审查规则说明等项目治理问题 | 修复文档/规范,使用治理验证 |
关联问题分组 — 同一根因 → 合并为单个任务,包含多个验证点。
同时记录 OpenSpec 门槛判断:
openspec-existing:说明关联的活跃变更、关联原因和需要更新的tasks.md/specs/范围。openspec-new:说明为什么不能放入现有活跃变更,以及新变更的最小范围。direct-fix:说明为什么不值得沉淀为 OpenSpec,以及采用的验证方式。no-change:说明不修改的原因和未来触发条件。对于规范级别的问题,在记录任务前先更新规范:
specs/<capability>/spec.md<!-- ADDED: 新增需求 -->
### Requirement: 父级选择器循环引用防护
系统应在父级选择器中禁用当前菜单及其所有子菜单,
以防止循环引用。
#### Scenario: 编辑包含子菜单的菜单
WHEN 用户编辑一个包含子菜单的菜单
THEN 父级选择器应禁用当前菜单及所有子菜单
<!-- MODIFIED: 变更需求(包含完整原始块) -->
### Requirement: 导入错误处理
系统应在导入失败时显示错误信息。
**MODIFIED:** 错误信息应包含行号、字段名和校验失败原因。
<!-- REMOVED: 废弃需求 -->
### Requirement: 旧版导入格式
系统应支持旧版 CSV 格式。
**REMOVED:** 此格式不再支持。
**迁移方案:** 使用带表头行的新版 CSV 格式。在tasks.md中追加反馈章节:
## Feedback
- [ ] **FB-1**: 父级选择器在菜单编辑中允许循环引用
- [ ] **FB-2**: 导入错误信息缺少行号和字段详情
- [ ] **FB-3**: 重置密码功能缺少测试覆盖编号: 顺序使用FB-1、FB-2等。如果章节已存在,从最后编号继续。
每个任务一行 — 不使用子字段。分析在修复阶段进行。
写入前说明分诊结论和拟写入任务;只有在多个目标变更归属不清、任务范围存在高风险取舍或用户明确要求确认时,才暂停等待用户选择。
如果处理路径为direct-fix或no-change,跳过本步骤,并在最终结果中记录未更新tasks.md的原因。
验证覆盖规划(内部):
apps/lina-plugins/<plugin-id>/hack/tests/e2e/,专属 POM/helper 放在插件同级hack/tests/pages/、hack/tests/support/openspec validate、静态扫描、文件存在性检查、格式检查或审查结论对每个 OpenSpec 反馈任务或直接修复项:
a. 告知: ## 修复 FB-X: <问题标题>或## 直接修复: <问题标题>
b. 调查 — 读取源文件,确认根因
c. 实现 — 最小化、聚焦的修复,遵循现有模式
d. 编写/更新测试或治理验证 — 行为修复按AGENTS.md选择单元测试或lina-e2e测试;项目治理类反馈使用规范校验、静态扫描或文件检查
e. 评估影响范围(必须)
实现后,识别回归风险:
| 变更类型 | 关联验证 |
|---|---|
| 后端 API 端点 | 所有调用该端点的前端页面 |
| 共享组件/工具函数 | 所有使用该组件的页面 |
| 数据库 Schema/DAO | 所有读写受影响表的功能 |
| 认证/权限 | 所有认证测试 + 权限相关测试 |
| 页面特定 | 该模块目录下的所有测试 |
| 项目治理文档/规范 | openspec validate、静态扫描、文件存在性检查或格式检查 |
# 示例:查找用户 API 变更的相关测试,包含宿主和源码插件自有 E2E
git grep -l "api/user" -- 'hack/tests/e2e/**/TC*.ts' 'apps/lina-plugins/**/TC*.ts'告知:
### FB-X 影响分析
- 修改文件:apps/lina-core/internal/controller/menu.go
- 受影响模块:菜单管理
- 回归测试:hack/tests/e2e/iam/menu/TC001-menu-crud.ts, hack/tests/e2e/iam/menu/TC002-auth-menu.ts同时必须记录:
i18n影响:涉及时列出资源归属、目标语言、验证命令;不涉及时写明无运行时行为、前端 UI、API 文档源文本、插件清单或语言包资源影响。AGENTS.md命中的.agents/rules/*.md;若某规则域确认无影响,写明无影响判断。命中规则但未读取对应规则文件时,不得标记该反馈完成。f. 验证(标记完成前必须执行)
tasks.md中将任务标记为[x];直接修复路径不修改tasks.md如果回归测试失败:
g. 运行审查 — 完成后必须调用lina-review技能
所有修复完成后:
### 综合验证结果
- 总测试数:N
- 通过:N
- 失败:N(列出详情)
- 回归测试:全部通过 ✓ / X 个失败如果存在失败 → 重新执行反馈分诊,必要时添加新的 FB 任务,回到步骤 6。
## 反馈完成
**处理路径:** direct-fix / openspec-existing / openspec-new / no-change
**变更:** <名称>
**OpenSpec 记录:** 已写入 <change>/tasks.md / 已新建 <change> / 未记录(原因:<原因>)
**报告问题数:** X
**已修复问题数:** Y/X
**新增测试:** Z 个测试用例 / 子断言
**回归测试:** 跨 N 个模块运行 R 个测试
**验证结果:** 全部通过 / 剩余 N 个问题
### 本次已修复
- [x] FB-1: <标题> ✓(测试:TC001a | 回归:iam/menu TC001, TC002 ✓)
- [x] FB-2: <标题> ✓(测试:已有覆盖 | 回归:auth TC003 ✓)
### 剩余(如有)
- [ ] FB-3: <标题> — 被 <原因> 阻塞| 场景 | 处理方式 |
|---|---|
| 单个问题 | 先分诊;达到 OpenSpec 门槛才写入变更 |
| 仅缺少测试用例 | 分类为 test-gap;若只是局部覆盖缺口可直接补测试,不强制写入 OpenSpec |
| 修复后发现更多问题 | 重新分诊;达到门槛才添加 FB 任务 |
| "Bug"实为功能请求 | 重新分类为 spec-level;达到 OpenSpec 门槛时先更新规范 |
| 存在活跃变更但反馈不相关 | 不强行追加;按direct-fix、openspec-new或no-change处理 |
| 轻量文档、技能或治理措辞改进 | 通常走direct-fix;若会改变 OpenSpec 工作流或团队治理门禁,必须同步规则文件并重新判断记录门槛 |
| 测试不可行(时序、基础设施) | 通过完整测试套件验证,在摘要中说明原因 |
| 多轮反馈 | 每轮先分诊;同一目标变更中的任务在单个 Feedback 章节中顺序编号 |
openspec-existing和openspec-new路径需要先记录再修复,direct-fix路径需要先说明分诊和根因再修复[x]© linaproai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .agents/skills/lina-feedback of linaproai/linapro.
Open the folder on GitHubat commit 75395c8
Lina Feedback next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Lina Feedback this skilllinaproai/linapro | 161 | — | ~2.2k | Automated safety check: Pass | Apache-2.0 | |
| Feedbackcodewhale-hq/Codewhale | 41k | — | ~272 | Automated safety check: Pass | MIT | |
| Feedbacknexu-io/nexu | 3.3k | — | ~660 | Automated safety check: Warn | MIT | |
| OpenSpec Guided OnboardingFission-AI/OpenSpec | 72k | 1 repos | ~4.5k | Automated safety check: Pass | MIT | |
| Feedbacktinyfish-io/tinyfish-cookbook | 2.2k | — | ~600 | Automated safety check: Pass | MIT | |
| UX Feedbacksickn33/agentic-awesome-skills | 47k | 1 repos | ~994 | Automated safety check: Pass | MIT |
codewhale-hq/Codewhale
Report a Codewhale bug or idea as a GitHub issue. An agent skill from codewhale-hq/Codewhale.
nexu-io/nexu
Send feedback to the Nexu team. An agent skill from nexu-io/nexu.
Fission-AI/OpenSpec
Walks you through a complete OpenSpec workflow cycle with narration while doing real work in your codebase.
tinyfish-io/tinyfish-cookbook
File structured feedback about TinyFish — bug reports, confusing setup steps, missing features, or a doctor diagnostic report.
sickn33/agentic-awesome-skills
Add appropriate user feedback states (loading, success, error, empty) to a component or page
davila7/claude-code-templates
Navigate difficult conversations and deliver constructive feedback using structured frameworks.
linaproai/linapro
通过 make db.init/mock 重置数据库、重启服务、安装并启用所有内置插件、准备压测数据,并启动并发子代理; 通常需要几十分钟到数小时,且会消耗大量 Token。不得从其他技能、CI、定时任务、 Git 钩子或模糊的性能请求中触发。
linaproai/linapro
Vben Admin 5.0 前端框架开发技能。用于开发基于 Vue3、Vite、TypeScript 的中后台管理系统。
linaproai/linapro
手动触发:为 LinaPro 主仓库及 apps/lina-plugins 子模块完成提交、PR 前 rebase、推送、创建 PR, 主仓 CI 修复回路,以及 PR 合并后恢复原始分支并同步 main。禁止自动触发。
linaproai/linapro
排查并修复给定的 LinaPro GitHub Actions 失败问题;修复完成后保留本地改动, 禁止自动提交、推送或创建 PR。
linaproai/linapro
审查 LinaPro 社区 GitHub Issues,并按项目规范和源码实现分类处理. An agent skill from linaproai/linapro.
linaproai/linapro
手动触发:将主仓库与 apps/lina-plugins 对齐最新 main 后, 按提示在两侧各建独立分支;分支就绪后继续处理提示词中的后续请求。
用于处理用户对已有实现的反馈分诊与执行闭环:先判断是否需要纳入 OpenSpec 活跃变更或新建变更,再完成根因分析、实现、验证和必要测试。凡是用户针对已有实现反馈 Bug、缺陷、改进点、建议或实现遗漏,即使没有明确提到“反馈”或 OpenSpec,也必须使用本技能。. Lina Feedback is an agent skill from linaproai/linapro.
Run `npx skills add linaproai/linapro --skill lina-feedback -a claude-code`. Or copy the skill folder (.agents/skills/lina-feedback in linaproai/linapro) into .claude/skills/lina-feedback in your project. Claude Code loads it when a task matches its description.
Run `npx skills add linaproai/linapro --skill lina-feedback -a codex`. Or copy the skill folder (.agents/skills/lina-feedback in linaproai/linapro) into .agents/skills/lina-feedback in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add linaproai/linapro --skill lina-feedback -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/lina-feedback, .gemini/skills/lina-feedback, .github/skills/lina-feedback and .opencode/skills/lina-feedback in your project.
Going by SKILL.md and its folder, Lina Feedback needs the command-line tools its instructions call (git). Compatibility (from SKILL.md): 依赖 openspec CLI、lina-e2e 技能、lina-review 技能。.
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Lina Feedback is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.2k tokens (SKILL.md is roughly 8.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Lina Feedback: Feedback (codewhale-hq/Codewhale, 41k stars), Feedback (nexu-io/nexu, 3.3k stars), OpenSpec Guided Onboarding (Fission-AI/OpenSpec, 72k stars) and Feedback (tinyfish-io/tinyfish-cookbook, 2.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
linaproai (a GitHub organization) maintains it in linaproai/linapro, which has 161 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on September 7, 2026.
Source: linaproai/linapro on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.