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
Install
vladm3105/aidoc-flow-framework/doc-adr-autopilot · repository language: Python
git clone https://github.com/vladm3105/aidoc-flow-framework
cp -r aidoc-flow-framework/platforms/claude-code-plugin/skills/doc-adr-autopilot ~/.claude/skills/doc-adr-autopilotnpx skillfed install vladm3105/aidoc-flow-framework/doc-adr-autopilotFrequently 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)
Read as markdown · JSON record · Browse the source repository
File tree — 1 file
platforms/claude-code-plugin/skills/doc-adr-autopilot/SKILL.md