From aidd-refine
Analytically scans a written artifact (spec, PRD, user stories) for blind spots: unstated assumptions, missing actors, failure modes, ambiguous terms, missing acceptance criteria, edge cases, and dependencies. Emits a categorized, severity-sorted shadow report.
How this skill is triggered — by the user, by Claude, or both
Slash command
/aidd-refine:04-shadow-areasThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Analytically scans a written artifact for gaps the author has not addressed. Unlike iterative Q&A clarification, this skill reads the existing material and emits a structured report: each gap carries a category from a locked 7-category taxonomy, a 3-tier severity, and a direct-question probe the author can act on immediately.
Analytically scans a written artifact for gaps the author has not addressed. Unlike iterative Q&A clarification, this skill reads the existing material and emits a structured report: each gap carries a category from a locked 7-category taxonomy, a 3-tier severity, and a direct-question probe the author can act on immediately.
| # | Action | Role | Input |
|---|---|---|---|
| 01 | detect | Parse input, extract gaps, classify category and severity, emit probes | file path or inline text |
| 02 | render-report | Render markdown grouped by category and sorted by severity, write report | gap list from detect |
| 03 | diff | Load prior report, classify gaps as closed / still-open / newly-introduced | gap list from detect + prior report path |
Router dispatches by context:
01-detect then 02-render-report01-detect then 03-diff then 02-render-reportThe 02-render-report action always runs last and writes <source>-shadow-report.md next to the source.
category, severity, probe.?.@references/locked-sets.json.status: clean.category + normalized snippet - not probe wording - so minor probe rephrasing does not create spurious "newly introduced" gaps.@references/categories.md: locked 7-category taxonomy with definition and example per category.@references/severity-rubric.md: blocker / major / minor decision rules and examples.@references/probe-style.md: direct-question form rules.@references/locked-sets.json: machine-readable sets reused by the validator.@assets/report-template.md: report skeleton with header, per-category sections, and status: clean block.npx claudepluginhub ai-driven-dev/framework --plugin aidd-refineDetects one gap category (orphan, unverified, duplicate, contradictory, lifecycle, etc.) in a sphinx-needs corpus and returns ordered list of affected needs with evidence.
Reviews specifications and technical requirements for gaps, inconsistencies, and contradictions from Google Docs, GitHub issues, Docmost docs, pasted text, or local files with configurable depth: --quick to --exhaustive.
Identifies gaps in product specifications like spec.md and generates clarifying questions with concrete stakeholder options. Useful before implementation or for requirement validation.