issue-planner

namespace	aiwg
platforms	["all"]
name	issue-planner
description	Research-grounded SDLC issue planner — dispatches parallel research, generates the supporting doc corpus, then files prioritized cross-referenced issues for human review.
requires	[{"objective":"non-empty string describing the feature, capability, or initiative to plan"},{"tracker":"issue tracker accessible (gitea | github | local) — auto-detected from project config"}]
ensures	[{"issues-filed":"prioritized issue backlog with type/priority/phase labels and wave-ordered dependencies"},{"research-brief":"synthesized research findings at .aiwg/working/issue-planner/research-brief.md"},{"sdlc-corpus":"phase-appropriate SDLC artifacts (use cases, risk register, etc.)"},"if --dry-run: plan preview table shown without filing","if --induct-research: reference induction tasks filed for discovered sources"]
errors	[{"no-tracker-access":"cannot reach issue tracker; check --provider or API credentials"},{"research-failed":"all three parallel research agents returned empty results; try --skip-research with existing docs"},{"objective-too-vague":"objective is too broad to plan without clarification; use --interactive"}]
invariants	["human approval gate is mandatory before any issues are filed","no issues are filed unless user explicitly confirms the plan","every filed issue links to the SDLC artifact that generated it"]
commandHint	{"argumentHint":"<objective> [--interactive] [--dry-run] [--guidance \"text\"] [--provider gitea|github|local] [--induct-research <target>]","allowedTools":"Read, Write, Glob, Grep, Bash, Agent, mcp__gitea__issue_write, mcp__gitea__issue_read, mcp__gitea__list_issues, WebSearch, WebFetch","model":"haiku","category":"planning","modelRole":"efficiency","modelTier":"economy"}

Issue Planner

Transform a high-level objective into a fully researched, SDLC-gated issue backlog — ready for address-issues — without a human having to manually research, write docs, or decide priority order.

Triggers

Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):

• "plan out " → full research + issue filing workflow
• "file issues for " → issue-planner with dry-run preview first
• "create a backlog for " → issue-planner with priority ordering
• "research and plan " → parallel research pass then issue filing
• "use the research team to plan " → explicit parallel research dispatch
• "plan issues for using SDLC gates" → gate-checked issue generation
• "I need issues for " → issue-planner in interactive mode to confirm scope

Parameters

<objective> (required)

The feature, capability, integration, or initiative to plan. Can be a one-liner or a multi-paragraph brief.

--interactive (optional)

Ask discovery questions before researching. Surfaces: scope constraints, excluded technologies, existing artifacts, target phase, priority bias (bugs-first vs value-first).

--dry-run (optional)

Generate the full plan and issue list but do not file any issues. Outputs a preview table for human review.

--guidance "text" (optional)

Upfront direction that shapes research focus, prioritization, and scope without interactive prompts.

Examples:

• --guidance "We're in Construction phase, skip Inception artifacts"
• --guidance "Security is top priority, HIPAA compliance required"
• --guidance "Quick wins only — scope to 2-week sprint"

--provider (optional)

Override the default issue tracker (gitea | github | local). Defaults to project config in .aiwg/config.yaml or CLAUDE.md.

--skip-research (optional)

Skip the parallel research pass and go straight to SDLC doc generation. Use when research was already done externally.

--phase (optional)

Target SDLC phase for artifact generation (inception | elaboration | | ). Determines which templates are used and which gate criteria are checked.