doc-adr-autopilot
Automates the full ADR lifecycle from source documents (BRD, PRD, EARS, BDD) or free-text prompts through generation, validation, and iterative refinement. Detects whether an ADR exists, routes to generation or review-and-fix accordingly, and maintains the ADR index with passing scores. Supports single or batch processing with configurable quality thresholds and fix iteration limits.
doc-adr-autopilot generates architecture decision records end-to-end from upstream artifacts like BRDs and PRDs, handling detection, scoping, generation, validation, and audit cycles.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-27
doc-adr-autopilot generates architecture decision records end-to-end from upstream artifacts like BRDs and PRDs, handling detection, scoping, generation, validation, and audit cycles. Automates the full ADR lifecycle from source documents (BRD, PRD, EARS, BDD) or free-text prompts through generation, validation, and iterative refinement. Detects whether an ADR exists, routes to generation or review-and-fix accordingly, and maintains the ADR index with passing scores. Supports single or batch processing with configurable quality thresholds and fix iteration limits.
Use it when
- doc-adr-autopilot supports batch-create multiple ADRs with configurable quality gates and scoring.
- doc-adr-autopilot's workflow detects whether an ADR already exists for a given decision scope.
Verify before relying
Read SKILL.md below before installing (1 file). Open directory: indexed for reading, not audited.
Install
vladm3105/aidoc-flow-framework/doc-adr-autopilot · repository language: Python
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
Can doc-adr-autopilot generate ADR from BRD automatically?
Yes. doc-adr-autopilot automates ADR generation end-to-end from upstream artifacts including BRD, PRD, EARS, and BDD documents. It detects the input type and scope, then generates architecture decision records with full traceability back to your source requirements. The tool handles both single and batch creation workflows.
How does doc-adr-autopilot handle batch ADR creation?
doc-adr-autopilot supports batch-create multiple ADRs with configurable quality gates and scoring. It processes multiple records in a single run, validates each against your thresholds, and automatically routes any that fail validation into audit-fix cycles. You can set iteration limits and pass/fail score targets for the entire batch.
What is the ADR autopilot workflow?
doc-adr-autopilot's workflow detects whether an ADR already exists for a given decision scope. If it doesn't, the tool generates a new record from your source artifact. If one exists, it routes to review-and-fix instead. All records are validated against quality gates, scored, and indexed for traceability. The cycle repeats until pass thresholds are met or iteration limits are reached.
Does doc-adr-autopilot validate and score generated ADRs?
Yes. doc-adr-autopilot includes ADR quality gate automation and validation scoring. Every generated or refined record is scored against configurable thresholds. Records that fail validation are automatically routed into audit-fix cycles with a set number of refinement iterations before final acceptance or rejection.
How does doc-adr-autopilot maintain decision traceability?
doc-adr-autopilot maintains an ADR index and traces decisions back to their source requirements. When you generate ADRs from BRD, PRD, EARS, or BDD inputs, the tool preserves the link between each decision record and the upstream artifact that triggered it, enabling full audit trails and impact analysis.
What input formats does doc-adr-autopilot support?
doc-adr-autopilot detects input type and scope from BRD, PRD, EARS, or BDD documents, as well as free-text prompts. The tool automatically identifies which format you're using and routes it through the appropriate generation pipeline, so you can feed it whatever upstream artifact or specification you have available.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
doc-adr-autopilot
Purpose
Automated ADR generation pipeline. From an upstream artifact
(BRD §8 / PRD §14 / EARS / BDD), a user prompt, or an implementation plan
(IPLAN-*), it analyzes the source, scopes the decision, generates a complete
Context-Decision-Consequences record, validates readiness, maintains
ADR-00_index.md, and drives the audit↔fix cycle to a passing score — for one
ADR or a batch.
Layer: 5. Upstream: BRD → PRD → EARS → BDD (or a
(truncated - see the full file via the links below)
File tree — 1 file
platforms/claude-code-plugin/skills/doc-adr-autopilot/SKILL.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Generate architecture decision records end-to-end from upstream artifacts”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
doc-adr captures a single architectural decision using the Context-Decision-Consequences pattern, positioned as Layer 5 in the specification-driven development flow. It records the rationale, chosen approach, evaluated alternatives, and accepted trade-offs for decisions that bridge container and component design.
doc-adr-fixer consumes audit reports and patches ADRs to resolve structural, referential, and content issues identified during quality review. It supports both team-mode validation (with multi-lens dispatch) and single-pass remediation, backing up originals and reverting regressions to prevent silent failures.
doc-validator enforces consistency rules across your entire SDD documentation corpus—catching broken links, orphaned artifacts, cumulative-tag gaps, duplicate IDs, and traceability gaps across all 8 layers. It runs declarative checks against your corpus structure and can optionally repair safely-fixable issues like missing reciprocal links or stale metadata. Use it before releases or after batch generation to ensure your documentation chain stays machine-verifiable and traceable.
doc-bdd translates EARS requirements into Layer 4 acceptance scenarios using structured YAML (not Gherkin), each with Given-When-Then phases, element-level trace links to upstream EARS, and forward mapping to SPEC sections. Use this after EARS is complete and before ADR/SPEC authoring; for batch generation across multiple documents, the autopilot skill handles orchestration.
doc-tdd generates Layer 7 TDD artifacts that translate component contracts into concrete test cases with quality thresholds. It maps BDD scenarios to unit, integration, functional, and end-to-end tests, establishes coverage targets per type, and sequences the Red-Green-Refactor workflow before implementation begins.
doc-prd generates a Product Requirements Document as Layer 2 of the SDD workflow, converting business requirements into product capabilities, user personas, and measurable success criteria. It structures features and acceptance criteria at the container level, sitting between upstream BRD and downstream EARS artifacts.