doc-ears-autopilot
Generate EARS documents end-to-end from a PRD, a prompt, or an IPLAN - detect input, validate readiness, generate formal statements, validate, and run the audit/fix cycle. Use to create or batch-create EARS.
What this skill does
# doc-ears-autopilot
## Purpose
Automated **EARS generation pipeline**. From an upstream PRD, a user prompt, or
an implementation plan (`IPLAN-*`), it analyzes the source, verifies upstream
readiness, generates a complete EARS document of atomic WHEN-THE-SHALL-WITHIN
statements, validates readiness, maintains `EARS-00_index.md`, and drives the
audit↔fix cycle to a passing score — for one EARS or a batch.
**Layer**: 3. **Upstream**: a PRD (and its BRD), a prompt, or an IPLAN.
**Downstream**: a validated EARS + index entry.
## Skill Dependencies
| Skill | Role |
|-------|------|
| `../doc-ears/SKILL.md` | EARS structure, the four patterns, syntax rules |
| `../doc-ears-audit/SKILL.md` | quality gate (scoring + findings) |
| `../doc-ears-fixer/SKILL.md` | applies fixes from the audit report |
| `../doc-naming/SKILL.md` | element-ID standards and `@threshold:` tags |
## Input Contract
Accepts: a target EARS id/path; an upstream PRD id/path; 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 EARS already exists (nested folder
`docs/03_EARS/EARS-NN_{slug}/`):
- **Missing** → *generate* mode (from the upstream PRD / prompt / IPLAN).
- **Exists** → *review & fix* mode (audit, then fix if below threshold).
Determine `deliverable_type` (`code`/`document`/`ux`/`risk`/`process`,
inherited from the upstream PRD) from the source content.
## Workflow
1. **Input analysis** — classify the input (PRD / prompt / IPLAN), locate the
upstream PRD and its BRD, and decide generate vs review-and-fix.
2. **Readiness check** — confirm the upstream PRD exists and is EARS-Ready
(score ≥ threshold); reserve the next `EARS-NN`. Categorize PRD requirements
into the four EARS patterns (Event, State, Unwanted, Ubiquitous).
3. **Generation** — produce the EARS per `../doc-ears/SKILL.md`: Document
Control first, all 5 sections, atomic WHEN-THE-SHALL-WITHIN statements,
tabular Quality Attributes (percentile timing), element IDs `EARS.NN.SS.xxxx`,
cumulative `@brd`/`@prd` tags, `@threshold:` references, state/sequence
diagram tags via `../charts-flow/SKILL.md`.
4. **Validation** — run `../doc-ears-audit/SKILL.md` from scratch.
5. **Audit ↔ fix cycle** — while score < threshold and iterations < max: run
`../doc-ears-fixer/SKILL.md`, then re-audit. On pass, update
`docs/03_EARS/EARS-00_index.md`; on exhausting iterations, flag for manual
review.
## Execution Modes
- **Single** — one EARS (generate or review-and-fix).
- **Batch** — multiple EARS, processed in **chunks of 3** to bound context;
generate each EARS only after its upstream PRD is confirmed ready.
- **Dry-run** — report the planned actions (patterns, sections, IDs) without
writing files.
## Quality Gates
- Generation does not complete until the audit passes (BDD-Ready ≥ threshold, 0
Tier-1 errors) or the iteration cap is hit (then: manual-review flag).
- The EARS index is updated only after an EARS passes.
- Fresh audit every cycle — no cached scores.
## Error Handling
| Situation | Action |
|-----------|--------|
| Upstream PRD missing or below EARS-Ready threshold | stop; report the missing/unready dependency |
| 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 EARS |
| Vague/compound statement cannot be auto-resolved | flag for manual review, continue batch |
| 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: `${CLAUDE_PLUGIN_ROOT}/framework/governance/ADAPTATION.md`.
## Related Resources
- Create: `../doc-ears/SKILL.md` · Audit: `../doc-ears-audit/SKILL.md` · Fix:
`../doc-ears-fixer/SKILL.md`
- Authority: `${CLAUDE_PLUGIN_ROOT}/framework/layers/03_EARS/EARS-TEMPLATE.yaml`,
`${CLAUDE_PLUGIN_ROOT}/framework/layers/03_EARS/README.md`,
`${CLAUDE_PLUGIN_ROOT}/framework/layers/03_EARS/EARS-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.