This skill is experimental and not yet stable. Behavior, structure, and outputs may change between versions.
Use this skill when you need an actionable task plan for a User Story issue before implementation.
Do not use this skill for direct code implementation, PR review, or GitHub mutations without explicit confirmation.
If missing inputs block planning, ask up to 3 focused follow-up questions from
assets/follow-up-questions.md
.
Execute in order and state assumptions explicitly.
-
Probe preferred skills and classify drafting mode
- : both and available; full workflow with explicit publish gates handled by the orchestrator.
- : only available; operate in draft-only mode using its templates and safeguards, do not perform any GitHub mutations, and surface drafts plus clear instructions for how an orchestrator or user should publish them.
- : neither available; stay in draft-only mode, generate task drafts with a minimal built-in structure (, , ,
Acceptance criteria mapping
, , ), and avoid direct references to another skill's files.
- Prefer whenever it is available; do not bypass it with direct cross-skill file references.
- Never stop due to missing preferred skills; degrade gracefully.
-
Research the user story
- Gather title, body, acceptance criteria, scenarios, ancestor chain, existing sub-issues, and related links.
- If issue type is ambiguous, confirm whether to proceed as .
-
Clarify only when needed
- Ask at most 3 questions per batch.
- Continue with explicit assumptions when safe defaults exist.
-
Extract planning anchors
- Outcomes
- Constraints and non-goals
- Verification points
-
Build dependency-ordered tasks
- For each task include objective, scope boundary, deliverable, verification method, and mapped AC references.
- Prefer independently verifiable slices.
-
Generate task issue drafts
- : route through with issue type
- : invoke in draft-only mode and output explicit publish instructions that delegate final mutation to
- : write drafts using the minimal built-in structure from step 1
- Keep drafts local until explicit publish approval.
-
Generate plan preview
- Write
.tmp/USER-STORY-TASK-PLAN-<context>.md
from assets/task-plan-template.md
.
- Include summary, traceability, ordered tasks, draft paths, publish plan, assumptions, risks.
-
Publish only after explicit confirmation
- Require explicit confirmation in the same turn.
- Stop if unresolved assumptions remain.
- Delegate publish execution to and prefer sub-agent invocation for task issue creation/update/linking.
- Pass required context to : , , parent story reference, ordered task drafts, labels/assignee intent, and dependency ordering.
- Require to keep MCP-first behavior and apply GraphQL fallback only when MCP write coverage is unavailable.
- The orchestrator's session-cache rules apply to all delegated calls: labels, assignee candidates, and issue types are fetched once per session and reused across all task issues in the batch.
- Budget awareness: a task-planning publish of N tasks costs ~N issue-write mutations + optional sub-issue link mutations. If N > 5, warn the user about rate-limit risk and offer to publish in batches.
- Do not call MCP write tools directly from this skill in publish mode.
- Hard fail publish mode if delegated execution returns unresolved item-level failures.
-
Repair mode for already-created tasks
- If tasks were created but are missing or parent linkage, delegate repair to and prefer sub-agent invocation.
- Provide per-issue repair intent (, add missing parent links, preserve order) and require verification results from the delegated run.
- Repair mode must be idempotent: skip already-correct issues and fix only missing metadata.
- Run post-flight verification after repairs and return actionable failures.
Always include:
Status: Awaiting user approval
until publish is confirmed and completed.
For
or
mode, include a per-issue post-flight report with: