From aidoc-flow
Automates the end-to-end change management pipeline: detects changes, classifies levels, drafts CHG records, traces cross-layer impact, and prepares gate approval. Works from diffs, incidents, prompts, or artifact edits.
How this skill is triggered — by the user, by Claude, or both
Slash command
/aidoc-flow:doc-chg-autopilotThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Automated **CHG pipeline**. From a change request — a diff, an incident, a
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 | 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 |
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.
For each target, check whether the CHG already exists in the change registry
(CHG-00_index.md):
Infer the change source (upstream/midstream/design/execution/external/ feedback) and level (C1/C2/C3/Emergency) from the changed artifacts and the trigger.
../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).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).../doc-chg-audit/SKILL.md from scratch.../doc-chg-fixer/SKILL.md, then re-audit. On pass, update
CHG-00_index.md; on exhausting iterations, flag for manual review.../gate-check/SKILL.md to run the formal/post-hoc gate and
complete GATE_APPROVAL_FORM. For Emergency, schedule the post-mortem
(framework/governance/chg/templates/POST_MORTEM-TEMPLATE.md) within 48h of
the fix deploy.../gate-check/SKILL.md. There is no numeric readiness score.| 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 |
../doc-chg/SKILL.md · Audit: ../doc-chg-audit/SKILL.md · Fix:
../doc-chg-fixer/SKILL.md · Gate: ../gate-check/SKILL.mdframework/governance/chg/CHG-TEMPLATE.yaml,
framework/governance/chg/README.md,
framework/governance/chg/CHG-00_index.TEMPLATE.md,
framework/governance/chg/gates/npx claudepluginhub vladm3105/aidoc-flow-framework --plugin aidoc-flowAuthors a Change Management (CHG) record to classify change level, route by source to the entry gate, assess cross-layer cascade impact, and register the change. Use when modifying an existing SDD artifact across any of the 8 layers.
Manages baseline and scope changes, artifact updates, traceability impact, approvals, and handoff revisions in SDLC workflows.
Design change control processes that prevent production surprises while avoiding process paralysis. Use when coordinating multiple team changes or managing infrastructure modifications.