doc-adr-autopilot
Generate ADRs end-to-end from an upstream artifact (BRD/PRD/EARS/BDD), a prompt, or an IPLAN - detect input, scope the decision, generate, validate, and run the audit/fix cycle. Use to create or batch-create ADRs.
What this skill does
# 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 prompt/IPLAN).
**Downstream**: a validated ADR + index entry.
## Skill Dependencies
| Skill | Role |
|-------|------|
| `../doc-adr/SKILL.md` | ADR structure and authoring rules (generation) |
| `../doc-adr-audit/SKILL.md` | quality gate (scoring + findings) |
| `../doc-adr-fixer/SKILL.md` | applies fixes from the audit report |
| `../doc-naming/SKILL.md` | element-ID standards |
| `../adr-roadmap/SKILL.md` | plans the set of ADRs a project needs |
## Input Contract
Accepts: a target ADR id/path; an upstream id (`BRD-NN`/`PRD-NN`/`EARS-NN`/
`BDD-NN`) or topic element id; a free-text prompt; or an IPLAN path. Optional:
score threshold (default 90), max fix iterations (default 3), batch list. With
no explicit input, treat the request as a prompt.
## Smart Document Detection
For each target, check whether the ADR already exists (nested folder
`docs/05_ADR/ADR-NN_{slug}/`):
- **Missing** → *generate* mode (synthesize the decision from the upstream).
- **Exists** → *review & fix* mode (audit, then fix if below threshold).
Determine `deliverable_type` (`code`/`document`/`ux`/`risk`/`process`,
inherited from upstream) and the originating topic (PRD §14, tracing back to
BRD §8) from the source content. One ADR records **one** decision.
## Workflow
1. **Input analysis** — classify the input (upstream id / prompt / IPLAN),
locate the originating topic (PRD §14 → BRD §8), and decide generate vs
review-and-fix.
2. **Decision scope** — confirm exactly one decision; reserve the next
`ADR-NN`; verify the cited upstream artifacts exist.
3. **Generation** — produce the ADR per `../doc-adr/SKILL.md`: Document Control
first (status `Proposed`/`Accepted`), §2–§10 + glossary + appendix, 2–3 alternatives with
cost/fit, internal element IDs `ADR.NN.SS.xxxx`, cumulative tags
`@brd @prd @ears @bdd`, the `@adr: ADR-NN` self-tag, architecture-flow
diagram via `../charts-flow/SKILL.md`.
4. **Validation** — run `../doc-adr-audit/SKILL.md` from scratch.
5. **Audit ↔ fix cycle** — while score < threshold and iterations < max: run
`../doc-adr-fixer/SKILL.md`, then re-audit. On pass, update
`docs/05_ADR/ADR-00_index.md`; on exhausting iterations, flag for manual
review.
## Execution Modes
- **Single** — one ADR (generate or review-and-fix).
- **Batch** — multiple ADRs, processed in **chunks of 3** to bound context;
generate ADRs that others depend on (`@depends: ADR-NN`) first.
- **Dry-run** — report the planned actions (decision scope, sections, IDs)
without writing files.
## Quality Gates
- Generation does not complete until the audit passes (SPEC-Ready ≥ threshold,
0 Tier-1 errors) or the iteration cap is hit (then: manual-review flag).
- The ADR index is updated only after an ADR passes.
- Fresh audit every cycle — no cached scores.
## Error Handling
| Situation | Action |
|-----------|--------|
| Cited upstream artifact missing (BRD/PRD/EARS/BDD) | stop; report the missing dependency |
| Source describes more than one decision | split into separate ADRs (one decision each) |
| Max iterations reached below threshold | write reports, flag for manual review, continue batch |
| Source input ambiguous | fall back to prompt mode; record assumptions in the ADR |
| Write/permission error | log, skip the item, continue the batch |
## Adaptation
Before applying defaults, read the project adaptation profile
(`.aidoc/profile.yaml`) and apply it in both the generation and the internal
audit/fix phases. Honor `section_toggles`, `active_layers`, `audit_threshold`
(raise-only — stricter only), and `glossary`. Ignore any unknown or
out-of-surface key; absent a profile, use framework defaults.
Authority: `${CLAUDE_PLUGIN_ROOT}/framework/governance/ADAPTATION.md`.
## Related Resources
- Create: `../doc-adr/SKILL.md` · Audit: `../doc-adr-audit/SKILL.md` · Fix:
`../doc-adr-fixer/SKILL.md`
- Decision planning: `../adr-roadmap/SKILL.md`
- Authority: `${CLAUDE_PLUGIN_ROOT}/framework/layers/05_ADR/ADR-TEMPLATE.yaml`,
`${CLAUDE_PLUGIN_ROOT}/framework/layers/05_ADR/README.md`,
`${CLAUDE_PLUGIN_ROOT}/framework/layers/05_ADR/ADR-00_index.TEMPLATE.md`
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.