dev-playbooks 2.2.0 → 2.3.0

package/skills/devbooks-delivery-workflow/SKILL.md

@@ -13,240 +13,39 @@ allowed-tools:
 
 # DevBooks: Delivery Acceptance Workflow (Complete Closed-Loop Orchestrator)
 
-> **Positioning**: This Skill is a **pure orchestration layer**, not an execution layer. It only **calls sub-agents**, never performs any change work itself.
+## Progressive Disclosure
 
----
-
-## 🚨 ABSOLUTE RULES
-
-> **These rules have no exceptions. Violation means failure.**
-
-### Rule 1: Main Agent Must Not Work Directly
-
-```
-❌ FORBIDDEN: Main Agent writing proposal.md / design.md / tests/ / src/ directly
-❌ FORBIDDEN: Main Agent modifying any change package content directly
-❌ FORBIDDEN: Main Agent skipping sub-agent calls
-
-✅ REQUIRED: All work completed through Task tool sub-agent calls
-✅ REQUIRED: Every stage has corresponding sub-agent call
-✅ REQUIRED: Main Agent only orchestrates, waits, and verifies
-```
-
-### Rule 2: Must Not Skip Any Mandatory Stage
-
-```
-❌ FORBIDDEN: Skipping Challenger/Judge stages
-❌ FORBIDDEN: Skipping Test-Reviewer stage
-❌ FORBIDDEN: Skipping Code-Review stage
-❌ FORBIDDEN: Skipping Green-Verify stage
-❌ FORBIDDEN: Archiving without passing strict check
-
-✅ REQUIRED: Complete execution of all 12 mandatory stages
-✅ REQUIRED: Sub-agent must return success before continuing to next stage
-```
-
-### Rule 3: Must Not Archive with Fake Completion
-
-```
-❌ FORBIDDEN: Archiving when evidence/green-final/ doesn't exist or is empty
-❌ FORBIDDEN: Archiving when verification.md AC coverage < 100%
-❌ FORBIDDEN: Archiving when tasks.md has incomplete tasks
-❌ FORBIDDEN: Archiving when change-check.sh --mode strict fails
-
-✅ REQUIRED: Archiver sub-agent runs check script first
-✅ REQUIRED: All checks pass before executing archive
-```
-
-### Rule 4: No Demo Mode (NO DEMO MODE)
-
-```
-❌ FORBIDDEN: Treating workflow as "demonstration" or "showcase"
-❌ FORBIDDEN: Outputting "demo complete", "workflow demonstration" etc.
-❌ FORBIDDEN: Claiming completion when artifacts don't exist or are empty
-❌ FORBIDDEN: Using "simulate", "assume", "if" instead of actual execution
-
-✅ REQUIRED: Every stage must produce real, verifiable artifacts
-✅ REQUIRED: Artifacts must be written to filesystem (verifiable via ls/cat)
-✅ REQUIRED: Use "executed", "completed", "created" for actual actions
-✅ REQUIRED: If cannot actually execute, stop immediately and inform user
-```
-
-**Signs of Demo Mode**:
-- Using words like "demonstration", "showcase", "simulate"
-- Claiming completion without actual file writes
-- Providing "Option A/B" instead of executing next step
-- Outputting "recommendations for next steps" instead of continuing
-
-### Rule 5: Must Not Ignore REVISE REQUIRED
-
-```
-❌ FORBIDDEN: Continuing to next stage after receiving REVISE REQUIRED
-❌ FORBIDDEN: Claiming "completed" after receiving REVISE REQUIRED
-❌ FORBIDDEN: Providing "options" for user to choose after REVISE REQUIRED
-❌ FORBIDDEN: Continuing execution after receiving REJECTED
-
-✅ REQUIRED: Judge returns REVISE → go back to Stage 1 to rewrite proposal
-✅ REQUIRED: Judge returns REJECTED → stop workflow, inform user
-✅ REQUIRED: Test-Review returns REVISE REQUIRED → go back to Stage 7 to fix tests
-✅ REQUIRED: Code-Review returns REVISE REQUIRED → go back to Stage 8 to fix code
-✅ REQUIRED: After fixing, re-execute review stage until it passes
-```
-
-### Rule 6: Must Not Proceed with Partial Completion
-
-```
-❌ FORBIDDEN: Entering next stage when tasks.md completion rate < 100%
-❌ FORBIDDEN: Entering next stage when test coverage < AC requirements
-❌ FORBIDDEN: Entering Code stage when stub tests exist (skip/todo/not_implemented)
-❌ FORBIDDEN: Entering Review stage when unimplemented functions exist (raise NotImplementedError)
-
-✅ REQUIRED: When Stage 7 completes, all tests must be real and executable
-✅ REQUIRED: When Stage 8 completes, tasks.md all tasks 100% complete
-✅ REQUIRED: If scope too large, must split change package, cannot partially complete
-```
-
----
-
-## Prerequisites: Configuration Discovery
-
-Before execution, **must** search for configuration in the following order (stop when found):
-1. `.devbooks/config.yaml` (if exists) → Parse and use its mappings
-2. `dev-playbooks/project.md` (if exists) → Dev-Playbooks protocol
-3. `project.md` (if exists) → Template protocol
-4. If still unable to determine → **Stop and ask user**
-
----
-
-## Complete Closed-Loop Flow (12 Mandatory Stages)
-
-```
-┌──────────────────────────────────────────────────────────────────────────┐
-│                      Mandatory Flow (No Optional Stages)                  │
-├──────────────────────────────────────────────────────────────────────────┤
-│                                                                          │
-│  ┌─────────┐   ┌───────────┐   ┌─────────┐   ┌─────────┐                │
-│  │1.Propose│──▶│2.Challenge│──▶│ 3.Judge │──▶│4.Design │                │
-│  └─────────┘   └───────────┘   └─────────┘   └─────────┘                │
-│       │                                            │                     │
-│       │              ┌─────────────────────────────┘                     │
-│       │              ▼                                                   │
-│       │        ┌─────────┐   ┌─────────┐   ┌─────────┐                  │
-│       │        │ 5.Spec  │──▶│ 6.Plan  │──▶│7.Test-R │                  │
-│       │        └─────────┘   └─────────┘   └─────────┘                  │
-│       │                                          │                       │
-│       │              ┌───────────────────────────┘                       │
-│       │              ▼                                                   │
-│       │        ┌─────────┐   ┌──────────┐   ┌──────────┐                │
-│       │        │ 8.Code  │──▶│9.TestRev │──▶│10.CodeRev│                │
-│       │        └─────────┘   └──────────┘   └──────────┘                │
-│       │                                            │                     │
-│       │              ┌─────────────────────────────┘                     │
-│       │              ▼                                                   │
-│       │        ┌───────────┐   ┌─────────┐                              │
-│       └───────▶│11.GreenV  │──▶│12.Archive│                              │
-│                └───────────┘   └─────────┘                              │
-│                                                                          │
-└──────────────────────────────────────────────────────────────────────────┘
-```
-
-### Stage Details and Sub-Agent Calls
-
-| # | Stage | Sub-Agent | Skill | Artifact | Mandatory |
-|---|-------|-----------|-------|----------|-----------|
-| 1 | Propose | `devbooks-proposal-author` | devbooks-proposal-author | proposal.md | ✅ |
-| 2 | Challenge | `devbooks-challenger` | devbooks-proposal-challenger | Challenge opinions | ✅ |
-| 3 | Judge | `devbooks-judge` | devbooks-proposal-judge | Decision Log | ✅ |
-| 4 | Design | `devbooks-designer` | devbooks-design-doc | design.md | ✅ |
-| 5 | Spec | `devbooks-spec-owner` | devbooks-spec-contract | specs/*.md | ✅ |
-| 6 | Plan | `devbooks-planner` | devbooks-implementation-plan | tasks.md | ✅ |
-| 7 | Test-Red | `devbooks-test-owner` | devbooks-test-owner | verification.md + tests/ | ✅ |
-| 8 | Code | `devbooks-coder` | devbooks-coder | src/ implementation | ✅ |
-| 9 | Test-Review | `devbooks-reviewer` | devbooks-test-reviewer | Test review opinions | ✅ |
-| 10 | Code-Review | `devbooks-reviewer` | devbooks-reviewer | Code review opinions | ✅ |
-| 11 | Green-Verify | `devbooks-test-owner` | devbooks-test-owner | evidence/green-final/ | ✅ |
-| 12 | Archive | `devbooks-archiver` | devbooks-archiver | Archived to archive/ | ✅ |
-
----
+### Base (must read)
+Goal: complete a 12-stage closed-loop delivery by orchestrating sub-agents only.
+Input: user goal, config mapping, existing change package artifacts and stage status.
+Output: sub-agent call sequence, stage progress, and result summary.
+Boundaries: main agent does not modify files directly; must call sub-agents via Task; enforce role isolation and gates.
+Evidence: artifact paths, script outputs, and review notes per stage.
 
-## 📚 Reference Documentation
+### Advanced (optional)
+Use when you need: ban details, stage table, resume rules.
 
-### Must Read (Read Immediately)
+### Extended (optional)
+Use when you need: gate handling, traceability templates, script pointers.
 
-1. **Subagent Invocation Specification**: `references/subagent-invocation-spec.md`
-   - Invocation format and examples
-   - Role isolation constraints
-   - When to read: Before starting orchestration
-
-2. **Orchestration Logic Pseudocode**: `references/orchestration-logic-pseudocode.md`
-   - Complete orchestration logic
-   - Detailed implementation of 12 stages
-   - When to read: When needing to understand orchestration logic
-
-### Read as Needed
-
-3. **Gate Checks and Error Handling**: `references/gate-checks-and-error-handling.md`
-   - Stage gate checkpoints
-   - Error handling flow
-   - Rollback execution rules
-   - When to read: When encountering errors or needing rollback
-
-4. **Delivery Acceptance Workflow**: `references/delivery-acceptance-workflow.md`
-   - Complete workflow description
-   - When to read: When needing detailed workflow understanding
-
-5. **Change Verification and Traceability Template**: `references/9-change-verification-traceability-template.md`
-   - Verification template
-   - When to read: When needing template reference
-
----
+## Core Notes
 
-## Context Awareness
+- Orchestration only: do not directly write proposal/design/tests/implementation.
+- 12 stages are mandatory; any failure triggers rollback to the corresponding stage.
+- Run config discovery first (prefer `.devbooks/config.yaml`), then invoke sub-agents.
 
-### Detection Flow
+## References
 
-1. Detect if change package exists
-2. Detect current stage (which stages completed)
-3. Resume from checkpoint
-
-### Resume from Checkpoint
-
-If change package already has partial artifacts, continue from most recently completed stage:
-
-```
-Detection results:
-- Change package: exists
-- Completed stages: 1-6 (proposal, challenge, judge, design, spec, plan)
-- Next stage: 7 (Test-Red)
-- Run mode: Resume from checkpoint
-```
-
----
-
-## MCP Enhancement
-
-This Skill supports MCP runtime enhancement, automatically detecting and enabling advanced features.
-
-### Dependent MCP Services
-
-| Service | Purpose | Timeout |
-|---------|---------|---------|
-| `mcp__ckb__getStatus` | Detect CKB index availability | 2s |
-
-### Detection Flow
-
-1. Call `mcp__ckb__getStatus` (2s timeout)
-2. Mark index availability in workflow status report
-3. If unavailable → Suggest generating index before apply stage
-
----
+- `skills/devbooks-delivery-workflow/references/orchestration-bans-and-stage-table.md`: bans, 12-stage table, resume notes.
+- `skills/devbooks-delivery-workflow/references/subagent-invocation-spec.md`: sub-agent invocation format and isolation rules.
+- `skills/devbooks-delivery-workflow/references/orchestration-logic-pseudocode.md`: orchestration main logic.
+- `skills/devbooks-delivery-workflow/references/gate-checks-and-error-handling.md`: gate checkpoints and rollback strategy.
+- `skills/devbooks-delivery-workflow/references/delivery-acceptance-workflow.md`: full workflow description.
+- `skills/devbooks-delivery-workflow/references/9-change-verification-traceability-template.md`: verification & traceability templates.
 
-## Optional Check Scripts
+## Recommended MCP Capability Types
 
-Scripts are located in this Skill's `scripts/` directory:
+- Code search (code-search)
+- Reference tracking (reference-tracking)
+- Impact analysis (impact-analysis)
 
-- Initialize change package skeleton: `change-scaffold.sh`
-- One-click change package validation: `change-check.sh`
-- Structural guardrail decision validation: `guardrail-check.sh`
-- Evidence collection: `change-evidence.sh`
-- Progress dashboard: `progress-dashboard.sh`

package/skills/devbooks-delivery-workflow/references/orchestration-bans-and-stage-table.md

@@ -0,0 +1,45 @@
+# Orchestration bans and stage table (reference)
+
+This file carries the orchestration bans and the 12-stage table for `devbooks-delivery-workflow`, to keep `SKILL.md` compact.
+
+## Absolute bans (mandatory)
+
+1) Main agent orchestrates only
+- Do not directly write `proposal.md` / `design.md` / `tasks.md` / `verification.md`
+- Do not directly modify `tests/**` or implementation code
+
+2) Do not skip mandatory stages
+- Must run: Proposal → Challenge → Judge → Design → Spec → Plan → Test → Code → Test Review → Code Review → Green Verify → Archive
+
+3) No fake archive
+- Do not archive if `evidence/green-final/` is missing/empty
+- Do not archive if `change-check.sh <change-id> --mode strict` fails
+
+4) No “demo/simulate”
+- Every stage must produce real artifacts on disk; do not replace execution with assumptions
+
+5) `REVISE REQUIRED` triggers rollback
+- If Judge/Test-Review/Code-Review returns `REVISE REQUIRED`: go back, fix, and rerun review until it passes
+
+## 12-stage table (mandatory)
+
+| # | Stage | Sub-agent | Skill | Key artifact(s) |
+|---:|---|---|---|---|
+| 1 | Propose | Proposal Author | `devbooks-proposal-author` | `proposal.md` |
+| 2 | Challenge | Proposal Challenger | `devbooks-proposal-challenger` | `challenge-*.md` |
+| 3 | Judge | Proposal Judge | `devbooks-proposal-judge` | writes back Decision Log |
+| 4 | Design | Design Owner | `devbooks-design-doc` | `design.md` |
+| 5 | Spec | Spec Owner | `devbooks-spec-contract` | `specs/**` |
+| 6 | Plan | Planner | `devbooks-implementation-plan` | `tasks.md` |
+| 7 | Test-Red | Test Owner | `devbooks-test-owner` | `verification.md` + `tests/**` + Red evidence |
+| 8 | Code | Coder | `devbooks-coder` | implementation changes (must not change tests) |
+| 9 | Test-Review | Test Reviewer | `devbooks-test-reviewer` | `test-review-*.md` |
+| 10 | Code-Review | Reviewer | `devbooks-reviewer` | `code-review-*.md` |
+| 11 | Green-Verify | Test Owner | `devbooks-test-owner` | Green evidence |
+| 12 | Archive | Archiver | `devbooks-archiver` | moved under `archive/` |
+
+## Resume (recommended)
+
+- If a change package already exists: resume from the most recent completed stage, do not redo confirmed artifacts.
+- After each stage: write evidence under `evidence/` and leave trace in the change package docs.
+

package/skills/devbooks-design-backport/SKILL.md

@@ -99,9 +99,22 @@ Detection Results:
 
 ---
 
-## MCP Enhancement
 
-This Skill does not depend on MCP services; no runtime detection required.
+## Progressive Disclosure
+### Base (Required)
+Goal: Clarify this Skill's core outputs and usage scope.
+Inputs: User goals, existing documents, change package context, or project path.
+Outputs: Executable artifacts, next-step guidance, or recorded paths.
+Boundaries: Does not replace other roles; does not touch `tests/`.
+Evidence: Reference output paths or execution records.
 
-MCP enhancement rules reference: `skills/_shared/mcp-enhancement-template-mcp-enhancement.md`
+### Advanced (Optional)
+Use when you need to refine strategy, boundaries, or risk notes.
 
+### Extended (Optional)
+Use when you need to coordinate with external systems or optional tools.
+
+## Recommended MCP Capability Types
+- Code search (code-search)
+- Reference tracking (reference-tracking)
+- Impact analysis (impact-analysis)

package/skills/devbooks-design-doc/SKILL.md

@@ -11,6 +11,26 @@ allowed-tools:
 
 # DevBooks: Design Document (Design Doc)
 
+## Progressive Disclosure
+
+### Base (Required)
+Goal: Produce `<change-root>/<change-id>/design.md` with What/Constraints and AC-xxx only.
+Inputs: approved `proposal.md`, impact notes (if any), and project context.
+Outputs: `design.md` (What/Constraints/AC-xxx + Documentation Impact).
+Boundaries: do not write implementation steps; do not write tests; do not modify code.
+Evidence: reference artifact paths and the AC list.
+
+### Advanced (Optional)
+Use when you need: option sets, boundary cases, dependency/architecture deltas.
+
+### Extended (Optional)
+Use when you need: faster search/impact via optional MCP capabilities.
+
+## Recommended MCP Capability Types
+- Code search (code-search)
+- Reference tracking (reference-tracking)
+- Impact analysis (impact-analysis)
+
 ## Workflow Position Awareness
 
 > **Core Principle**: Design Doc executes after Proposal is approved, serving as the starting point for implementation phase.
@@ -237,19 +257,11 @@ After completing design-doc, output:
 OR
 **Next: `devbooks-implementation-plan`** (if no external contract changes)
 
-Reason: Design is complete. The next step is to [define external contracts / create implementation plan].
+Next: [define external contracts / create implementation plan].
 
 ### How to invoke
 ```
 Run devbooks-<skill-name> skill for change <change-id>
 ```
-```
 
 ---
-
-## MCP Enhancement
-
-This Skill does not depend on MCP services, no runtime detection required.
-
-MCP enhancement rules reference: `skills/_shared/mcp-enhancement-template-mcp-enhancement.md`
-

package/skills/devbooks-docs-consistency/SKILL.md

@@ -0,0 +1,170 @@
+---
+name: devbooks-docs-consistency
+description: devbooks-docs-consistency: Check and maintain consistency between project documentation and code, supporting incremental scanning, custom rules, and completeness checks. Can run on-demand within change packages or globally. Old name devbooks-docs-sync is retained as an alias with deprecation notice.
+recommended_experts: ["Technical Writer", "System Architect"]
+allowed-tools:
+  - Glob
+  - Grep
+  - Read
+  - Edit
+  - Write
+  - Bash
+---
+
+# DevBooks: Documentation Consistency (Docs Consistency)
+
+## Progressive Disclosure
+
+### Base (Required)
+Goal: Check documentation consistency and completeness and produce reports.
+Inputs: user docs, changed files (change-scoped) or full repo docs (global).
+Outputs: evidence reports under `<change-root>/<change-id>/evidence/` (or specified output paths).
+Boundaries: check-only by default; do not modify code or `tests/**`.
+Evidence: reference generated report paths.
+
+### Advanced (Optional)
+Use when you need: rules customization, doc classification tuning, completeness dimensions.
+
+### Extended (Optional)
+Use when you need: faster search/impact via optional MCP capabilities.
+
+## Recommended MCP Capability Types
+- Code search (code-search)
+- Reference tracking (reference-tracking)
+- Impact analysis (impact-analysis)
+
+## Prerequisites: Configuration Discovery (Protocol-Agnostic)
+
+Before execution, **must** search for configuration in the following order (stop when found):
+1. `.devbooks/config.yaml` (if exists) -> Parse and use mappings within
+2. `dev-playbooks/project.md` (if exists) -> Dev-Playbooks protocol, use default mappings
+3. `project.md` (if exists) -> template protocol, use default mappings
+4. If still undetermined -> **Stop and ask user**
+
+---
+
+## Compatibility and Deprecation
+
+- Old name: `devbooks-docs-sync`
+- Current name: `devbooks-docs-consistency`
+- Behavior: Old name continues to work as an alias with deprecation notice.
+- Runtime notice: Alias points to new directory via symlink, can execute `scripts/alias.sh` to output notice.
+
+Deprecation notice example:
+
+```
+devbooks-docs-sync is deprecated, please use devbooks-docs-consistency.
+```
+
+---
+
+## Role Definition
+
+**docs-consistency** is the documentation consistency check role in the DevBooks Apply phase, responsible for identifying discrepancies between documentation and code and generating reports, without directly modifying code.
+
+### Document Classification
+
+| Document Type | Target Audience | Checked by This Skill | Examples |
+|---------------|-----------------|:---------------------:|----------|
+| **Living Documents** | End Users | Yes | README.md, docs/*.md, API.md |
+| **Historical Documents** | End Users | Limited (minimal checks only) | CHANGELOG.md |
+| **Conceptual Documents** | Design/Architecture | Yes (structural checks) | architecture/*.md |
+
+Classification rules are configurable, default rules in `references/doc-classification.yaml`.
+
+---
+
+## Execution Modes
+
+### Mode 1: Incremental Scan (Change-Scoped)
+
+**Trigger condition**: Running within change package context.
+
+**Behavior**:
+1. Read change scope
+2. Scan only changed files
+3. Record token consumption and scan time
+4. Output check report
+
+### Mode 2: Full Scan (Global Check)
+
+**Trigger condition**: User explicitly requests global check (e.g., `devbooks-docs-consistency --global`).
+
+**Behavior**:
+1. Scan all user documentation
+2. Generate diff report
+3. Output improvement suggestions
+
+### Mode 3: Check Mode (Check Only)
+
+**Trigger condition**: User uses `--check` parameter.
+
+**Behavior**: Check only, no modifications, output report.
+
+---
+
+## Command Examples
+
+```
+# Rules engine: persistent rules
+bash scripts/rules-engine.sh --rules references/docs-rules-schema.yaml --input README.md
+
+# Rules engine: one-time task
+bash scripts/rules-engine.sh --once "remove:@augment" --input README.md
+
+# Document classification
+bash scripts/doc-classifier.sh README.md
+
+# Completeness check
+bash scripts/completeness-checker.sh --input README.md --config references/completeness-dimensions.yaml --output evidence/completeness-report.md
+```
+
+---
+
+## Completeness Checks
+
+Execute completeness checks on living documents, covering by default: environment dependencies, security permissions, troubleshooting, configuration instructions, API documentation.
+
+- Dimension configuration: `references/completeness-dimensions.yaml`
+- Report output: `<change-root>/<change-id>/evidence/completeness-report.md`
+- Methodology reference: [Completeness Thinking Framework](../_shared/references/completeness-thinking-framework.md)
+
+---
+
+## Style Preferences
+
+Style preference reading priority: command-line arguments > config file > defaults.
+
+- Documentation maintenance metadata: `dev-playbooks/specs/_meta/docs-maintenance.md`
+
+---
+
+## Output and Reports
+
+Default output reports (change package context):
+
+- `evidence/completeness-report.md`
+- `evidence/token-usage.log`
+- `evidence/scan-performance.log`
+
+---
+
+## Workflow Integration
+
+Triggered by `devbooks-archiver` during archiving phase, generates documentation maintenance metadata during brownfield initialization by `devbooks-brownfield-bootstrap`.
+
+---
+
+
+## Metadata
+
+| Field | Value |
+|-------|-------|
+| Skill Name | devbooks-docs-consistency |
+| Phase | Apply (post-implementation, pre-archiving) |
+| Artifacts | Documentation consistency check reports |
+| Constraints | Check only, do not modify code |
+
+---
+
+*This Skill documentation follows devbooks-* conventions.*

package/skills/devbooks-docs-consistency/references/completeness-dimensions.yaml

@@ -0,0 +1,31 @@
+- name: Environment dependencies
+  patterns:
+    - "Node.js"
+    - "Python"
+    - "Dependencies"
+    - "Requirements"
+- name: Security and permissions
+  patterns:
+    - "Security"
+    - "Permissions"
+    - "API key"
+    - "Token"
+    - "Secret"
+- name: Troubleshooting
+  patterns:
+    - "Troubleshooting"
+    - "FAQ"
+    - "Common issues"
+    - "Error"
+- name: Configuration
+  patterns:
+    - "Configuration"
+    - "config"
+    - ".env"
+    - "Environment variables"
+- name: API documentation
+  patterns:
+    - "API"
+    - "Endpoint"
+    - "Request"
+    - "Response"

package/skills/devbooks-docs-consistency/references/doc-classification.yaml

@@ -0,0 +1,11 @@
+living_docs:
+  - "README.md"
+  - "docs/**/*.md"
+  - "API.md"
+  - "docs/*.md"
+history_docs:
+  - "CHANGELOG.md"
+  - "**/CHANGELOG.md"
+concept_docs:
+  - "architecture/*.md"
+  - "architecture/**/*.md"

package/skills/devbooks-docs-consistency/references/docs-rules-schema.yaml

@@ -0,0 +1,11 @@
+rules:
+  - id: forbid-strongest-mind
+    type: persistent
+    target: content
+    action: check
+    pattern: "strongest mind"
+  - id: remove-augment
+    type: once
+    target: content
+    action: remove
+    pattern: "@augment"

package/skills/devbooks-docs-consistency/scripts/alias.sh

@@ -0,0 +1,5 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+echo "devbooks-docs-sync is deprecated; please use devbooks-docs-consistency." >&2
+exit 0