issues
Skill1 starsChanged 4 months agoMITView on GitHub
Breaks a plan, spec, or PRD into independently-grabbable GitHub issues using vertical slices (tracer bullets), publishes them in dependency order, and saves a local index in .yoke/ai. Activates when the user writes "issues", "break into issues", "create tickets", "split into tasks", "decompose into issues", "make implementation tickets", "tracer bullets".
21 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- pedrohcgs/claude-code-my-workflowtheir own version, first seen Nov 8, 2026
- halilural/imprimaturtheir own version, first seen Nov 8, 2026
- davidvornholt/mail-mcptheir own version, first seen Nov 5, 2026
- davidvornholt/mailboxtheir own version, first seen Nov 5, 2026
- ecosyste-ms/claude-plugintheir own version, first seen Oct 25, 2026
- dotBunny/Claudettetheir own version, first seen Oct 25, 2026
Used with
Projects with it also use architecture and commit.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
AnthropicSkillarchitecture
Create or evaluate an architecture decision record (ADR). Use when choosing between technologies (e.g., Kafka vs SQS), documenting a design decision with trade-offs and consequences, reviewing a system design proposal, or designing a new component from requirements and constraints.
Also in 3 projects that use this
SentrySkillcommit
Create commit messages following Sentry conventions. Use when committing code changes, writing commit messages, or formatting git history. Follows conventional commits with Sentry-specific issue references.
Also in 5 projects that use this
Other versions21 projects use a version of this.
Word for word · 0
None found.
Edited · 1
- ctxswitch/skills★ 128% same
Wrote their own version · 20
- pedrohcgs/claude-code-my-workflow★ 1.7ksame name
- martinus/unordered_dense★ 1.5ksame name
- bjcoombs/ai-native-toolkit★ 32same name
- 0xrafasec/ai-workflow★ 9same name
- rafagomes/ai-workflow★ 9same name
- dotBunny/Claudette★ 7same name
- Magnus-Gille/claude-skills★ 5same name
- ecosyste-ms/claude-plugin★ 3same name
- ecosyste-ms/skills★ 3same name
- davidvornholt/mail-mcp★ 2same name
10 more not listed
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 repository19 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- sync-docsSkill
- yoke-createSkill
- yoke-releaseSkill
- yoke-validateSkill
- bootstrapSkill
- doSkill
- draftSkill
- gcaSkill
- gpSkill
- grill-docsSkill
- grillSkill
- handoffSkill
- helpSkill
- journalSkill
- mergeSkill
- prdSkill
- prSkill
- reviewSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 20 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 34
Prefer many thin slices over few thick ones </vertical-slice-rules>
- Very specific: line 64
If gh is not authenticated or there is no GitHub remote, skip publishing, write the full breakdown to the local index, and tell the user.
- Distinctive: line 66
Do NOT close or modify any parent issue.
- Very specific: line 97
Use the project's domain glossary and respect ADRs.
“Common” is measured: kept by at least 6 in 10 of the 20 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Issues
Break a plan into independently-grabbable issues using vertical slices (tracer bullets). Each slice cuts end-to-end through every layer, so a completed one is demoable or verifiable on its own.
Process
1. Gather context
Work from whatever is already in the conversation context. If the user passes an issue reference (issue number, URL, or path) as an argument, fetch it (gh issue view <ref> for GitHub) and read its full body and comments. When the path points to a PRD artifact (<slug>-prd.md), also extract any **Tracking:** <URL> line under the H1 — that URL marks the parent for sub-issue linking.
2. Explore the codebase (skip if already explored this session)
If the codebase has not been explored this session, explore it now to understand its current state. Follow the domain-doc consumer rules in ${CLAUDE_PLUGIN_ROOT}/skills/grill-docs/reference/domain-docs.md: read .yoke/context.md and relevant .yoke/adr/, give issue titles and descriptions the glossary's vocabulary, and flag any ADR a slice contradicts. Also read the git memory of the areas the slices touch per ${CLAUDE_PLUGIN_ROOT}/skills/gca/reference/history-reading.md — a slice that re-proposes a Rejected: approach or crosses a Constraint: must say so.
3. Draft vertical slices
Break the plan into tracer bullet issues. Each issue is a thin vertical slice that cuts through ALL integration layers end-to-end, NOT a horizontal slice of one layer.
Slices may be 'HITL' or 'AFK'. HITL slices require human interaction, such as an architectural decision or a design review. AFK slices can be implemented and merged without human interaction. Prefer AFK over HITL where possible.
<vertical-slice-rules>
- Each slice delivers a narrow but COMPLETE path through every layer (schema, API, UI, tests)
- A completed slice is demoable or verifiable on its own
- Prefer many thin slices over few thick ones
</vertical-slice-rules>4. Confirm the breakdown
Present the proposed breakdown as a numbered list. For each slice, show:
- Title: short descriptive name
- Type: HITL / AFK
- Blocked by: which other slices (if any) must complete first
- User stories covered: which user stories this addresses (if the source material has them)
Granularity, dependency order, and HITL/AFK marking are the skill's own job — decide them and show the result, do not interview the user slice by slice. Publishing creates real GitHub issues, so gate it with a single approval: ask once via AskUserQuestion — "Publish these N issues, or tell me what to change?" with Publish (Recommended) first. Apply any requested edits in one pass, then publish. No multi-question loop.
5. Publish
Publish in dependency order (blockers first) to reference real issue identifiers in the "Blocked by" field. Follow reference/github-issues.md for the gh conventions and triage labels.
Order the slices so every blocker is created before the slices that depend on it. For each slice, in that order: write its body (the <issue-template> below) to a file, substitute the real issue numbers of its blockers into the "Blocked by" section, then create it:
gh issue create --title "<slice title>" --body-file <slice body file>Label AFK slices ready-for-agent and HITL slices ready-for-human (per the reference; create a label if the repo lacks it, unless the user objects). Capture each returned issue number for its dependents to cite.
Once each child exists, run two best-effort follow-ups per the reference: set its type to Task (per "Issue types"; leave it untyped and warn if unavailable), and — if a parent issue is known (from the input argument or from a **Tracking:** <URL> line in a PRD artifact) — link the child as a sub-issue of the parent (per "Sub-issues"; leave it unlinked and warn if unavailable). The textual ## Parent section in the issue body remains the human-readable fallback.
Build the slug as in /yoke:prd — an English kebab-case description, prefixed with a ticket id if one exists; reuse the parent PRD/issue's slug when the source was one, so <slug>-prd.md and <slug>-issues.md sit together. Save a local index to .yoke/ai/<slug>/<slug>-issues.md (mkdir -p .yoke/ai/<slug> first) listing every slice: title, type, blocked-by, the created issue URL, and its body.
If gh is not authenticated or there is no GitHub remote, skip publishing, write the full breakdown to the local index, and tell the user.
Do NOT close or modify any parent issue.
<issue-template>
## ParentA reference to the parent issue (if there is one, otherwise omit this section).
What to build
A concise description of this vertical slice. Describe the end-to-end behavior, not layer-by-layer implementation.
Avoid specific file paths or code snippets — they go stale fast. Exception: if a prototype produced a snippet that encodes a decision more precisely than prose can (state machine, reducer, schema, type shape), inline it here and note briefly that it came from a prototype. Trim to the decision-rich parts — not a working demo, just the important bits.
Acceptance criteria
- Criterion 1
- Criterion 2
- Criterion 3
Blocked by
- A reference to the blocking ticket (if any)
Or "None - can start immediately" if no blockers.
</issue-template>Rules
- Vertical slices, not horizontal layers. Prefer many thin slices.
- Publish in dependency order so "Blocked by" can reference real issue numbers.
- Use the project's domain glossary and respect ADRs. Pair with
/yoke:prdupstream. - Language: match the conversation language, or follow the project-level definition in CLAUDE.md / AGENTS.md.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

