to-issues
将正式文档或 BMad 执行发现转成本地 issues。Use when user wants to convert a spec or plan into implementation issues, or create BMad control-panel issues for blockers, HITL…
Skill by pop1414
Chalk Labs
Need help deploying to-issues?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/pop1414-to-issues
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/to-issues
What's inside
- Skill name
to-issues- Description
- 将正式文档或 BMad 执行发现转成本地 issues。Use when user wants to convert a spec or plan into implementation issues, or create BMad control-panel issues for blockers, HITL decisions, cross-story risks, tech debt, review follow-ups, or documentation fixes.
- License
- MIT
- Instructions
- 252 lines in SKILL.md · view on GitHub
Files (2)
- .decision-log.md
- SKILL.md
SKILL.md (first lines)
# To Issues 把正式文档中的未解决工作写入 `docs/features/<feature>/issues/`。本 skill 有两种模式: - **Normal Mode**:把 `SPEC.md`、Plan 或 PRD 拆成可独立领取的 vertical-slice implementation issues。 - **BMad Control Mode**:当 BMad stories 是主执行队列时,只创建控制面板 issues:blocker、HITL decision、cross-story risk、tech debt、review follow-up、documentation fix。 核心规则:**不要让 local issues 和 BMad stories 同时充当执行队列。** 如果 feature 使用 BMad `sprint-status.yaml` / story files 作为执行主线,local issues 只记录影响多个 stories、需要人类裁决、改变长期契约或不适合塞进单条 story 的事项。 Document workflow、issue tracker 和 triage label vocabulary 应该已经提供给你;如果没有,运行 `/setup-ai-document-system`。 ## Mode Selection 进入工作前先判断模式: | 条件 | 模式 | | --- | --- | | 用户明确要求拆 `SPEC.md` / Plan / PRD 为可执行任务,且没有 BMad story cycle | Normal Mode | | 存在与当前 feature / epic 相关的 `_bmad-output/implementation-artifacts/sprint-status.yaml` 或 BMad story files,或用户说当前 feature 用 BMad stories 执行 | BMad Control Mode | | 输入来自 BMad review、readiness、dev-story 中发现的 blocker / risk / follow-up | BMad Control Mode | | 不确定执行主线 | 先问一句:这个 feature 的实现队列是 local issues 还是 BMad stories? | BMad Control Mode 的硬约束: - 不要为每个 BMad story 创建一个重复的 `ready-for-agent` issue。 - 当前 story 内可直接完成、只影响当前 story 的工作,应写入 BMad story follow-up,而不是创建 local issue。 - 影响多个 stories、需要人类决策、改变 PRD / SPEC / ADR / README 的事项,创建 local issue。 - 如果 issue 的解决会改变实现契约,`Resolution Target` 必须指向 `SPEC`、`ADR`、`PRD` 或 `README`。 ## Gather Context 基于 conversation context 中已有内容工作。如果用户传入 issue reference(issue number、URL 或 path)作为参数,从 issue tracker 获取它,并读取完整 body 和 comments。 优先读取: 1. repo 中实际存在的 agent adapter,例如 `AGENTS.md`、`CLAUDE.md`、`.cursor/rules/` 或 `.github/copilot-instructions.md` 2. `docs/agents/document-system.md` 3. `docs/agents/issue-tracker.md` 4. `docs/agents/triage-labels.md` 5. `docs/features/<feature>/SPEC.md` 6. `docs/features/<feature>/PLAN.md`(如果存在) 7. `docs/features/<feature>/PRD.md` 如果没有 `SPEC.md`,但任务需要实现行为、API、状态或数据契约,先运行 `/to-spec`,或只创建一个 HITL issue 要求人类补 Spec。 BMad Control Mode 还要读取相关材料: - `docs/BMAD_INTEGRATION.md` - `docs/LEVEL3_BMAD_WORKFLOW.md` - `_bmad-output/implementation-artifacts/sprint-status.yaml`(如果存在) - 相关 BMad story file、readiness report、code review 或 retrospective 输出 ## Normal Mode 把计划拆成 **tracer bullet** issues。每个 issue 都是一个薄 vertical slice,end-to-end 穿过所有 integration layers,而不是某一层的 horizontal slice。 Slices 可以是 `HITL` 或 `AFK`。HITL slices 需要人类交互,例如 architecture decision 或 design review。AFK slices 可以无人交互地实现并合并。尽可能优先 AFK。 Vertical slice rules: - 每个 slice 都交付一条窄但 COMPLETE 的路径,穿过每一层(schema, API, UI, tests)。 - 完成后的 slice 自身可 demo 或验证。 - 偏好多而薄的 slices,而不是少而厚的 slices。 把 proposed breakdown 作为编号列表展示。每个 slice 显示: - **Title**:短描述名 - **Type**:HITL / AFK - **Blocked by**:哪些其他 slices 必须先完成(如果有) - **User stories covered**:覆盖哪些 user stories(如果 source material 中有) 询问用户: - Granularity 是否合适?(too coarse / too fine) - Dependency relationships 是否正确? - 是否需要 merge 或继续 split 某些 slices? - HITL 和 AFK 标记是否正确? 迭代直到用户批准 breakdown。 ## BMad Control Mode 从 BMad 执行材料中提取控制面板 issues。不要拆 implementation queue;BMad story files 和 `sprint-status.yaml` 已经承担这个职责。 只创建这些 Issue Kind。写入 issue 时使用表格中的 canonical string: | Issue Kind | 适合场景 | 通常状态 | | --- | --- | --- | | `blocker` | 不解决会阻塞一个或多个 BMad stories | `ready-for-human` 或 `needs-info` | | `HITL decision` | 必须由人类裁决的产品、技术、设计或合规问题 | `ready-for-human` | | `cross-story risk` | 影响多个 stories 的一致性、架构、测试或交付风险 | `needs-triage` 或 `ready-for-human` | | `tech debt` | 当前 story 可完成,但留下跨模块或长期维护问题 | `needs-triage` | | `review follow-up` | code review 发现的问题超出当前 story 修复范围 | `needs-triage` 或 `ready-for-agent` | | `documentation fix` | PRD / SPEC / ADR / README 与实现或 BMad 输出不一致 | `ready-for-agent` 或 `ready-for-human` | 判断放 story 还是 issue: | 问题 | 处理 | | --- | --- | | 当前 BMad story 内能直接完成,且只影响当前 story | 写入 BMad story follow-up | | 影响多个 BMad stories | 创建 local issue | | 需要人类裁决 | 创建 local issue | | 改变长期契约或正式文档 | 创建 local issue,并设置 `Resolution Target` | | 只是当前 story 缺少测试或实现细节 | 留在 story tasks / follow-up | 发布前展示 proposed control issues。每项显示: - **Title** - **Issue Kind** - **Related BMad Stories** - **Blocks BMad Stories** - **Resolution Target** - **Suggested Status** 询问用户这些事项是否真的应该脱离当前 story、是否遗漏受影响 stories、以及 resolution target 是否正确。 ## Publish 对每个批准的 issue,把新 issue 发布到 issue tracker。对于本地 Markdown,写入 `docs/features/<feature>/issues/<NN>-<slug>.md`。
From pop1414/ai-native-doc-system, MIT.
More from pop1414/ai-native-doc-system
- 0.479score
git-guardrails-claude-code
pop1414
设置 Claude Code hooks,在危险 git commands(push, reset --hard, clean, branch -D 等)执行前阻止它们。Use when user wants to prevent destructive git operations, add git safety…
SkillCFreshness: CClaude Code +9 - 0.479score
diagnose
pop1414
面向棘手 bug、性能回退和 BMad story execution failures 的纪律化 diagnosis loop。Reproduce → minimise → hypothesise → instrument → fix → regression-test.
SkillCFreshness: CClaude Code +9 - 0.474score
caveman
pop1414
超压缩 communication mode。Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy.
SkillCFreshness: CClaude Code +9 - 0.474score
to-plan
pop1414
Converts a feature PRD, spec, BMad epics/stories, release goal, or conversation context into an execution plan at `docs/plans/<plan>.md` or…
SkillCFreshness: CClaude Code +9 - 0.474score
to-prd
pop1414
将当前 conversation context 或 BMad PRD 输出转成 `docs/features/<feature>/PRD.md`,并接入 AI-native 文档链。Use when user wants to create a PRD, write product requirements…
SkillCFreshness: CClaude Code +9 - 0.474score
to-spec
pop1414
Converts a feature PRD, plan, BMad architecture/epics/stories output, or conversation context into `docs/features/<feature>/SPEC.md` with functional behavior…
SkillCFreshness: CClaude Code +9 - 0.474score
write-a-skill
pop1414
创建结构正确、支持 progressive disclosure 并带 bundled resources 的新 agent skills。Use when user wants to create, write, or build a new skill.
SkillCFreshness: CClaude Code +9 - 0.474score
grill-with-docs
pop1414
Grilling session that challenges a plan against the existing domain model, feature docs, and documented decisions, then updates CONTEXT.md and ADRs as…
SkillCFreshness: CClaude Code +9 - 0.474score
improve-codebase-architecture
pop1414
根据 CONTEXT.md 中的 domain language 和 docs/adr/ 中的 decisions,寻找 codebase 的 deepening opportunities。Use when the user wants to improve architecture, find…
SkillCFreshness: CClaude Code +9 - 0.474score
migrate-to-shoehorn
pop1414
将 test files 从 `as` type assertions 迁移到 @total-typescript/shoehorn。Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.
SkillCFreshness: CClaude Code +9 - 0.474score
scaffold-exercises
pop1414
创建包含 sections、problems、solutions 和 explainers 的 exercise directory structures,并确保通过 linting。Use when user wants to scaffold exercises, create exercise stubs…
SkillCFreshness: CClaude Code +9 - 0.474score
setup-ai-document-system
pop1414
Sets up repo-local adapters and `docs/agents/` configuration so engineering skills share one issue tracker, triage vocabulary, domain layout, AI-native…
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 3, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/pop1414/ai-native-doc-system
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from pop1414
- 0.479score
git-guardrails-claude-code
pop1414
设置 Claude Code hooks,在危险 git commands(push, reset --hard, clean, branch -D 等)执行前阻止它们。Use when user wants to prevent destructive git operations, add git safety…
SkillCFreshness: CClaude Code +9 - 0.479score
diagnose
pop1414
面向棘手 bug、性能回退和 BMad story execution failures 的纪律化 diagnosis loop。Reproduce → minimise → hypothesise → instrument → fix → regression-test.
SkillCFreshness: CClaude Code +9 - 0.474score
improve-codebase-architecture
pop1414
根据 CONTEXT.md 中的 domain language 和 docs/adr/ 中的 decisions,寻找 codebase 的 deepening opportunities。Use when the user wants to improve architecture, find…
SkillCFreshness: CClaude Code +9 - 0.474score
grill-with-docs
pop1414
Grilling session that challenges a plan against the existing domain model, feature docs, and documented decisions, then updates CONTEXT.md and ADRs as…
SkillCFreshness: CClaude Code +9 - 0.474score
caveman
pop1414
超压缩 communication mode。Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy.
SkillCFreshness: CClaude Code +9 - 0.474score
migrate-to-shoehorn
pop1414
将 test files 从 `as` type assertions 迁移到 @total-typescript/shoehorn。Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.
SkillCFreshness: CClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get to-issues running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
to-issues skill. Agent Mart. https://agentmart.dev/skills/pop1414-to-issues (last updated 2026-10-24)