doc-chg-autopilot
Drive a Change Management record end-to-end with minimal prompts - detect the change, classify the level, draft the CHG, assess cross-layer cascade, and prep the entry gate. Use to author or batch CHGs hands-off.
What this skill does
# doc-chg-autopilot
## Purpose
Automated **CHG pipeline**. From a change request — a diff, an incident, a
prompt, or an upstream artifact edit — it detects the change, classifies the
level, drafts a complete CHG record, traces the cross-layer cascade, registers
it, and prepares the entry gate for approval — for one change or a batch.
CHG is **NOT a lifecycle layer**: no layer number, no template chain, no
readiness score. The pipeline closes on **gate approval**, not a numeric score.
## Skill Dependencies
| Skill | Role |
|-------|------|
| `../doc-chg/SKILL.md` | CHG structure, classification, and routing rules |
| `../doc-chg-audit/SKILL.md` | gate-readiness check (pass/fail + fix list) |
| `../doc-chg-fixer/SKILL.md` | applies fixes from the audit report |
| `../gate-check/SKILL.md` | runs the formal gate (C3/Emergency) + approval form |
## Input Contract
Accepts: a target `CHG-NN`/path; a diff or list of edited artifacts; an incident
reference; or a free-text change description. Optional: max fix iterations
(default 3), batch list. With no explicit input, treat the request as a change
description and infer the source.
## Smart Document Detection
For each target, check whether the CHG already exists in the change registry
(`CHG-00_index.md`):
- **Missing** → *generate* mode (draft a new CHG record).
- **Exists** → *review & fix* mode (audit, then fix if it fails gate-readiness).
Infer the change **source** (upstream/midstream/design/execution/external/
feedback) and **level** (C1/C2/C3/Emergency) from the changed artifacts and the
trigger.
## Workflow
1. **Input analysis** — classify the input (diff / incident / prompt / upstream
edit), locate the touched artifacts, and decide generate vs review-and-fix.
2. **Type & scope** — classify the change level and source per
`../doc-chg/SKILL.md`; select the entry gate (GATE-01/03/06/08/CODE, or
GATE-SPEC for a `framework/`-spec change — set `semver_impact`, ≥C2);
reserve the next `CHG-NN` (or `CHG-EMG-YYYYMMDD-HHMM` for Emergency).
3. **Generation** — populate `${CLAUDE_PLUGIN_ROOT}/framework/governance/chg/CHG-TEMPLATE.yaml`:
metadata, change_control, description (what/why/trigger), implementation,
verification. **Impact assessment** is mandatory — trace the cascade along
`BRD→PRD→EARS→BDD→ADR→SPEC→TDD→IPLAN→Code` (downstream for upstream/external,
bubble-up for feedback, lateral for midstream) and list every affected
artifact. Add `rollback_plan` (C2/C3), `gate_approval` (C3),
`emergency_change` (Emergency).
4. **Validation** — run `../doc-chg-audit/SKILL.md` from scratch.
5. **Audit ↔ fix cycle** — while the audit FAILs and iterations < max: run
`../doc-chg-fixer/SKILL.md`, then re-audit. On pass, update
`CHG-00_index.md`; on exhausting iterations, flag for manual review.
6. **Gate prep** — C1 commits directly; C2 routes to peer review; **C3/Emergency
hand off to `../gate-check/SKILL.md`** to run the formal/post-hoc gate and
complete `GATE_APPROVAL_FORM`. For Emergency, schedule the post-mortem
(`${CLAUDE_PLUGIN_ROOT}/framework/governance/chg/templates/POST_MORTEM-TEMPLATE.md`) within 48h of
the fix deploy.
## Execution Modes
- **Single** — one CHG (generate or review-and-fix).
- **Batch** — multiple changes, processed in **chunks of 3** to bound context;
generate upstream-source CHGs before the downstream ones that depend on them.
- **Dry-run** — report the planned classification, source, entry gate, and
cascade list without writing files.
## Quality Gates
- A CHG is not "done" until the audit passes (0 blocking findings) **and** the
required approval is obtained: C1 self, C2 peer review, C3/Emergency gate via
`../gate-check/SKILL.md`. There is **no numeric readiness score**.
- The change registry is updated only after a CHG passes the audit.
- Fresh audit every cycle — no cached results.
## Error Handling
| Situation | Action |
|-----------|--------|
| Source ambiguous | infer from touched layers; record the assumption in the CHG |
| Cascade incomplete (E003) | re-trace the chain before drafting impact assessment |
| Entry gate mismatch (E002) | re-route per the source table; correct `entry_gate` |
| Max iterations reached, still failing | write reports, flag for manual review, continue batch |
| Emergency post-mortem overdue | block sign-off; escalate; keep `post_mortem_completed: false` |
## Related Resources
- Create: `../doc-chg/SKILL.md` · Audit: `../doc-chg-audit/SKILL.md` · Fix:
`../doc-chg-fixer/SKILL.md` · Gate: `../gate-check/SKILL.md`
- Authority: `${CLAUDE_PLUGIN_ROOT}/framework/governance/chg/CHG-TEMPLATE.yaml`,
`${CLAUDE_PLUGIN_ROOT}/framework/governance/chg/README.md`,
`${CLAUDE_PLUGIN_ROOT}/framework/governance/chg/CHG-00_index.TEMPLATE.md`,
`${CLAUDE_PLUGIN_ROOT}/framework/governance/chg/gates/`,
`${CLAUDE_PLUGIN_ROOT}/framework/governance/AUTHORING_STYLE.md`
Related in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.