Product & Design Skills

Use when the user runs /doc-align:align to check if documentation needs updating after code changes. AI-analyzes the change impact on project docs, generates a detailed report, and updates docs after user confirmation.

Run the feature-advisor query-time subagent over the full ontology to produce a structured impact assessment for a proposed feature or change. Maintainer asks "I want to add X — what's affected?" The agent reads sidecars + concepts.yaml + implicit-adrs.md + refactoring-scopes.md + doc-gaps.md + test-map.yaml + existing adrs/ + live ODD docs (via WebFetch), and emits lineage/{repo}/feature-walks/{date}-{slug}.md — a planning aid the maintainer reads BEFORE writing code.

Analyze test coverage gaps. Use when user says "test coverage", "what's not tested", "coverage gaps", "missing tests", "coverage report", or "what needs testing".

Run the doc-gap-finder reducer subagent over the per-node enrichment sidecars + the concept catalog + the live documentation site. Produces or refreshes lineage/{repo}/doc-gaps.md — a ranked list of DOC-NNN candidates (broken URLs, missing anchors, code-doc drift, missing pages, coverage gaps, stale pages) with full citations the maintainer triages into the backlog.

Generate or refresh coverage manifest for a scanner — lists ALL items in scope so scans can track progress across sessions.

Run the adr-archaeologist reducer subagent over the per-node enrichment sidecars + concepts.yaml + existing adrs/. Applies the 3-question wisdom test (per Nygard 2011 / adr.github.io / AWS Prescriptive Guidance) to distinguish DELIBERATE architectural decisions from IMPLEMENTATION GAPS. Emits TWO artefacts: lineage/{repo}/implicit-adrs.md (real ADR candidates only — backbone decisions, classified as promote / extend-existing / drift / unique-load-bearing) AND lineage/{repo}/refactoring-scopes.md (gap-shaped findings — absent features, missing validation, buggy defaults — actionable as DOC-NNN / TEST-NNN / SEC-NNN / PERF-NNN backlog items, NOT as ADRs).

Scan a repo for mixed ADRs, PRDs, SPECs, and DOCs and bootstrap or merge the full .planning/ setup from them. Classifies each doc in parallel, synthesizes a consolidated context with a conflicts report, and routes to new-project or merge-milestone depending on whether .planning/ already exists.

Draft an upstream-repo GitHub issue on disk. Creates the next ISS file under issues/{repo}/ with paste-ready frontmatter + body skeleton. The actual filing into GitHub is a deliberate human action — this skill never opens a real issue.

Autonomous batch driver for the rev-2 agentic-ontology sprint. Picks the next pending theme from state/sprint-themes.yaml, spawns 5 file-analyser subagents in parallel, then 5 reducers in parallel, merges deltas, refreshes coverage, appends the investigator-log entry, commits, pushes to remote, marks the theme done. Designed to be fired by /loop overnight without maintainer input.

Generate probe-skeleton YAML files at lineage/{repo}/probes/{P-NNN}.yaml from feature-flows.yaml's uncovered test-matrix cells. Each skeleton carries the featureid + testclass + cross-references + a TODO-marked arrange/act/observe/assert block the maintainer fills in. Accelerates probe corpus growth — slice 4 of dynamic-verification ADR. Local-only per APPROACH.md section 5 rule 12.

Run one or more dynamic-verification probes against a local ephemeral docker-compose mirror of the target system. Captures observation traces as committed artefacts at lineage/{repo}/probe-runs/{date}-{probeid}.yaml and merges measured values back into feature-flows.yaml, test-map.yaml, and per-sidecar confidenceperfield annotations. Local-only execution per APPROACH.md section 5 rule 12 + section 9 — no remote infrastructure ever. Slice 2 of adrs/drafts/dynamic-verification-layer.md.

Run the feature-reflector subagent (Layer 4b — top-down product-owner reflection) over one composed feature flow. Produces lineage/{repo}/feature-reflections/detail/{F-NNN}.yaml with a stepped-back product-owner narrative + 5-15 falsifiable user-facing hypotheses + per-hypothesis verdicts (confirmed / contradicted / partial / probe-needed) traced through the implementation chain. Contradictions are surfaced as bug-candidate / caveat-candidate findings — cross-file intent-vs-implementation drifts no single sidecar can see in isolation. Per APPROACH.md section 15 + rev-5 LSN-020 case-law.