universal-dev-standards 6.7.5 → 6.9.0

package/bundled/skills/brainstorm-assistant/guide.md

@@ -10,8 +10,8 @@ description: |
 
 > **Language**: English | [繁體中文](../../locales/zh-TW/skills/brainstorm-assistant/guide.md)
 
-**Version**: 4.1.0
-**Last Updated**: 2026-07-09
+**Version**: 4.2.0
+**Last Updated**: 2026-08-21
 **Applicability**: All software projects
 **Scope**: universal
 **Type**: Utility Skill (no core standard)
@@ -286,7 +286,7 @@ A single LLM is a weak, biased evaluator (Li et al., 2025: LLMs are strong at ge
 | **User impact** | Impact 70% · Alignment 30% |
 | **Strategic alignment** | Alignment 60% · Impact 40% |
 
-**Per-criterion guide (1–5):**
+**Per-criterion guide (1–5, reference format — not a script the critic must walk through):**
 
 | Criterion | 5 | 3 | 1 |
 |-----------|---|---|---|
@@ -312,7 +312,7 @@ A soft "please critique this" yields mostly agreement — LLMs are sycophantic u
 - **Devil's Advocate**: "Your job is to argue this idea WILL fail. Produce 2 specific failure conditions."
 - **Steelman**: "State the strongest, most charitable version of the counterargument — the one a thoughtful opponent would actually make."
 
-Each counterargument must take the form: **"This idea will fail in [specific context] because [specific reason]."**
+Constraint: each counterargument must name a **specific context** and a **specific reason**. The sentence pattern **"This idea will fail in [specific context] because [specific reason]"** is a reference format, not a required phrasing (v4.2 — the critic brief is goal + constraints, see SKILL.md "Critic brief shape").
 
 **NOT acceptable** (too vague): "This might be difficult." / "There could be edge cases."
 
@@ -348,6 +348,7 @@ Each idea that remains receives a badge: `✓ Passed rebuttal — [one-line summ
 **Personas Used**: [domain expert, skeptic, analogist, ...]
 **Lenses Used**: [analogical, reversal, ...]
 **Pre-flight**: [Completed / Skipped]   **Rebuttal**: [Completed / Skipped]   **Tier**: [Baseline / Enhanced]
+**Critic model level (D4 mind axis)**: [vendor-neutral level label per core/model-selection.md — naming a vendor model is a violation; not declared → D4 [degraded]]
 
 ## Problem Statement
 [Refined problem + root cause from 5 Whys]
@@ -561,9 +562,9 @@ BQS v1 is an **additive quality contract**, not a rewrite. Everything from v3 is
 
 - **All flags**: `--personas`, `--lens`, `--enhanced`, `--skip-preflight`, `--no-rebuttal`, `--quick`, `--technique` behave exactly as in v3. v4 adds one optional flag, `--intent`, for the Layer 0 declaration.
 - **All mechanisms**: PRE-FLIGHT anti-anchoring, FRAME 5-Whys/HMW, the persona ensemble, diversity lenses, the multi-critic panel, the hard-role rebuttal (Devil's Advocate + Steelman), the Diversity-Collapse Guardrail, and the Enhanced Tier are unchanged.
-- **The `--enhanced` isolated-agent host** is what lets BQS **D4 pass** (judge ≠ generator); on a baseline single context the panel is marked `[degraded]`, never silently passed.
+- **The `--enhanced` isolated-agent host** is what satisfies BQS **D4's seat axis** (judge ≠ generator); since v4.2 (XSPEC-388) a D4 pass additionally requires the review to declare its **model level** (mind axis — vendor-neutral labels per core/model-selection.md). On a baseline single context the panel is marked `[degraded]`, never silently passed.
 
-BQS v1 是**疊加的品質契約**，不是打掉重練。v3 的一切都保留：所有旗標（`--personas`/`--lens`/`--enhanced`/`--skip-preflight`/`--no-rebuttal`/`--quick`/`--technique`）行為不變，v4 僅新增一個可選的 `--intent` 旗標供第 0 層宣告；所有機制（PRE-FLIGHT 防錨定、FRAME 5-Whys/HMW、persona 集成、多樣性透鏡、多評審面板、硬角色反駁、多樣性崩塌防護、Enhanced 層）不變；`--enhanced` 的隔離 agent 宿主正是讓 BQS **D4 pass**（判官≠產生者）的條件，baseline 單 context 標 `[degraded]`、不靜默通過。
+BQS v1 是**疊加的品質契約**，不是打掉重練。v3 的一切都保留：所有旗標（`--personas`/`--lens`/`--enhanced`/`--skip-preflight`/`--no-rebuttal`/`--quick`/`--technique`）行為不變，v4 僅新增一個可選的 `--intent` 旗標供第 0 層宣告；所有機制（PRE-FLIGHT 防錨定、FRAME 5-Whys/HMW、persona 集成、多樣性透鏡、多評審面板、硬角色反駁、多樣性崩塌防護、Enhanced 層）不變；`--enhanced` 的隔離 agent 宿主滿足的是 BQS **D4 的座位軸**（判官≠產生者），自 v4.2（XSPEC-388）起 D4 pass 另需評審宣告**模型層級**（心智軸——依 core/model-selection.md 的廠商中立標籤），baseline 單 context 標 `[degraded]`、不靜默通過。
 
 ---
 
@@ -598,6 +599,7 @@ BQS v1 是**疊加的品質契約**，不是打掉重練。v3 的一切都保留
 | [Requirement Engineering](../../core/requirement-engineering.md) | Brainstorm output feeds requirement writing |
 | [Spec-Driven Development](../../core/spec-driven-development.md) | Brainstorm output feeds SDD proposals |
 | [Anti-Hallucination](../../core/anti-hallucination.md) | Critic feasibility claims must be evidence-based, not asserted |
+| [Model Selection](../../core/model-selection.md) | The D4 mind axis (declared model level) and the divergence-side level (Standard or higher) defer to this standard's criteria — cited, never restated |
 
 ---
 
@@ -605,6 +607,7 @@ BQS v1 是**疊加的品質契約**，不是打掉重練。v3 的一切都保留
 
 | Version | Date | Changes |
 |---------|------|---------|
+| 4.2.0 | 2026-08-21 | XSPEC-388: D4's pass condition gains a second axis — the seat (independent context, unchanged) plus the mind (the review must declare its required **model level**, expressed only with the vendor-neutral labels of core/model-selection.md; naming a concrete vendor model is a violation; missing declaration → `[degraded]`, never pass). CONVERGE critic briefs re-shaped as goal + constraints per MS-009: D5–D8 presented as criteria the judgment must satisfy, never as an ordered procedure; the fixed rebuttal sentence pattern, per-criterion 1–5 guides, and critic weight formulas are kept as reference formats, not mandatory steps. Divergence side cites MS-004/Criterion 2 (Standard or higher — deliberately not "highest"), validated through the calibration loop's existing Diversity (D2/D3) lagging column. Terminology: the model-capability axis is written "model level" throughout, because "tier" is already taken by BQS tiering and the Enhanced Tier. All v3 flags and mechanisms preserved. |
 | 4.1.0 | 2026-07-09 | XSPEC-325: Replaced the fixed Top-3 recommendation cap with a score-threshold **Recommended Set** (Agg. Score ≥ 3.5, uncapped in count) throughout BQS Layer 2 — the product gate (D5–D8), the hard-role rebuttal round (Devil's Advocate + Steelman), the Meta stop rule (set-membership stability), the Diversity-Collapse Guardrail, and the OUTPUT Recommendations block all now key off the Recommended Set instead of a fixed 3. If no idea reaches 3.5, the single highest-scoring idea is still shown, marked "below threshold — shown for reference", so the report is never empty. |
 | 4.0.0 | 2026-06-22 | XSPEC-296: Brainstorm Quality Standard (BQS v1) — a four-layer × timeline quality contract layered additively on v3. Layer 0 explore/exploit intent (modulates D2 weight); Layer 1 process leading dimensions D1–D4 with a hard sequence gate (D5–D8 forbidden during divergence); Layer 2 product leading dimensions D5–D8 applied to Top 3 only, with a Seeds column and high-variance contested zone; Layer 3 Judgment Override (overrides aggregate score). D4 judge≠generator (independent context else `[degraded]`); D5 claim split (external-fact floor cross-tier); D7 two-state falsifiability ("need to do X" → next-step, not fail); Meta stop rule (Top-3 set stability + hard cap 2 rounds). Session Self-Evaluation re-positioned as the calibration loop's lagging end (Adoption→D6, Diversity→D2/D3, Cognitive Load→cost; two parallel evaluations forbidden). First principle refined to "decisions use leading, calibration uses lagging". Tiering bound to objective Mode Selection triggers. New flag `--intent`. All v3 flags/mechanisms preserved. |
 | 3.0.0 | 2026-06-01 | XSPEC-247: DIVERGE re-centred on persona ensemble + diversity lenses (analogical/reversal/morphological); CONVERGE re-centred on multi-critic panel + hard-role rebuttal (Devil's Advocate + Steelman); Diversity-Collapse Guardrail; Enhanced Tier (parallel persona/critic agents, graceful fallback); Research Foundations rebuilt on 6 verified 2024–2026 sources; Validity Caveats re-rated (pre-flight LOW, Nijstad/Nemeth demoted); new flags `--personas`/`--lens`/`--enhanced`; anti-seed guardrail |

package/bundled/skills/code-review-assistant/SKILL.md

@@ -82,6 +82,7 @@ After `/code-review` completes, the AI assistant should suggest:
 
 ## Reference | 參考
 
+- [Pre-Commit Checklist](./checkin-checklist.md) — Read it before committing, as the pre-commit pass.
 - Detailed guide: [guide.md](./guide.md)
 - Core standard: [code-review-checklist.md](../../core/code-review-checklist.md)
 

package/bundled/skills/commands/brainstorm.md

@@ -28,7 +28,7 @@ PRE-FLIGHT ──► FRAME ──► DIVERGE ──────────► C
 | **PRE-FLIGHT** | Prevent AI anchoring | User writes 3 ideas first; no analogy seed; **BQS Layer 0 intent (explore/exploit)** | 防止錨定 |
 | **FRAME** | Define problem clearly | 5 Whys, HMW, Stakeholder Map; **D1 frame purity** | 清楚定義問題 |
 | **DIVERGE** | Force viewpoint diversity | Persona ensemble + diversity lenses; **BQS Layer 1 D1–D4, hard gate hides D5–D8** | 逼出視角多樣性 |
-| **CONVERGE** | Bias-checked selection | Multi-critic panel + Devil's Advocate/Steelman; **BQS Layer 2 D5–D8 on Top 3, D4 judge≠generator** | 降偏誤選擇 |
+| **CONVERGE** | Bias-checked selection | Multi-critic panel + Devil's Advocate/Steelman; **BQS Layer 2 D5–D8 on the Recommended Set (Agg. ≥ 3.5), D4 judge≠generator (two axes: independent context + declared model level)** | 降偏誤選擇 |
 | **OUTPUT** | Actionable report | Brainstorm Report + Seeds + Contested Zone + **Layer 3 Judgment Override** | 可執行的報告 |
 
 > **BQS v1 (XSPEC-296):** v4 layers a four-layer × timeline quality contract on v3. Full oracles and structural rules are in the skill — see [Brainstorm Assistant Skill](../brainstorm-assistant/SKILL.md#bqs-v1--quality-contract--bqs-v1--品質契約).
@@ -64,7 +64,7 @@ PRE-FLIGHT ──► FRAME ──► DIVERGE ──────────► C
 ## Problem Statement
 [Refined problem from FRAME phase]
 
-## Top 3 Recommendations
+## Recommendations (Agg. Score ≥ 3.5 — uncapped)
 1. **[Idea]** — Agg. X.X ✓ Passed rebuttal — Persona: [..] — [Why recommended]
 
 ## Diversity Note
@@ -96,7 +96,7 @@ After brainstorming, the typical workflow is:
 | `/brainstorm "topic"` | 以指定主題啟動 PRE-FLIGHT，再進入 FRAME |
 | `/brainstorm --personas "a,b,c"` | 以自訂 persona 組進入 DIVERGE |
 | `/brainstorm --lens <name>` | 以指定多樣性透鏡為主進入 DIVERGE |
-| `/brainstorm --enhanced` | 若宿主支援子代理則平行跑 persona/評審，否則靜默退回 baseline；此模式下 BQS D4 方可 pass |
+| `/brainstorm --enhanced` | 若宿主支援子代理則平行跑 persona/評審，否則靜默退回 baseline；此模式滿足 BQS D4 的座位軸（獨立 context），pass 另需宣告模型層級（心智軸，見 skill D4） |
 | `/brainstorm --intent exploit` | 以 exploit 意圖啟動（BQS Layer 0），D2 低覆蓋不扣分 |
 
 ### Interaction Script | 互動腳本
@@ -121,12 +121,13 @@ After brainstorming, the typical workflow is:
 3. 至少套用一個多樣性透鏡（類比／假設反轉／形態矩陣）
 4. 以多樣性（覆蓋的 persona/透鏡數，D2/D3）而非數量為繼續門檻
 5. **硬序列閘**：D5–D8 在最後一個 persona 產完前**不得揭示或評分**；CONVERGE critic 不得提前呼叫
+6. **模型層級（發散側）**：以 **Standard 或更高**層級執行——依 core/model-selection.md 的 MS-004／Criterion 2（引用，不複述；不是「最高層級」）
 
-#### CONVERGE Phase (BQS Layer 2 — D5–D8 on Top 3 only)
-1. 以 3 個獨立評審（工程可行性／使用者影響／策略一致）各自評分後聚合
-2. 對前 3 名跑硬角色 Devil's Advocate（論證會失敗）+ Steelman；使用者以 (a)修改/(b)反駁/(c)移除 回應。**D4 判官≠產生者**：評審須在獨立 context（`--enhanced`）方可 pass，否則標 `[degraded]` 不得 pass
-3. **僅對 Top 3** 套用 D5 接地（外部事實需 file:line／來源、跨級地板；假說免接地）、D6 淨值（解誰問題／真有嗎／不做代價＋掛 lagging 欄）、D7 二態證偽（「需先做 X」轉 next-step、不算 fail）、D8 next-step 裁決
-4. **Meta 停止規則**：維度全綠且再跑一輪 Top 3 集合成員不變→停；硬上限 2 輪
+#### CONVERGE Phase (BQS Layer 2 — D5–D8 on the Recommended Set only)
+1. 以 3 個獨立評審（工程可行性／使用者影響／策略一致）各自評分後聚合；**評審提示以「目標＋約束」表達**（判準，不是步驟清單——理由見 skill 引用的 core/model-selection.md MS-009），加權公式與逐準則指南為參考格式
+2. 對**推薦集**（Agg. Score ≥ 3.5，不限筆數）跑硬角色 Devil's Advocate（論證會失敗）+ Steelman；使用者以 (a)修改/(b)反駁/(c)移除 回應。**D4 判官≠產生者，兩軸**：(1) 評審在獨立 context（`--enhanced`）執行，且 (2) 宣告模型層級（core/model-selection.md 的廠商中立標籤；指名具體廠商模型即違規）——缺任一軸標 `[degraded]` 不得 pass
+3. **僅對推薦集**套用 D5 接地（外部事實需 file:line／來源、跨級地板；假說免接地）、D6 淨值（解誰問題／真有嗎／不做代價＋掛 lagging 欄）、D7 二態證偽（「需先做 X」轉 next-step、不算 fail）、D8 next-step 裁決——四者為判準、不限順序
+4. **Meta 停止規則**：維度全綠且再跑一輪推薦集集合成員不變→停；硬上限 2 輪
 
 🛑 **STOP**: 展示 Brainstorm Report（含 Seeds／爭議區／Judgment Override）後等待使用者決定下一步
 
@@ -147,13 +148,15 @@ After brainstorming, the typical workflow is:
 | 使用「像 X 但給 Y」種子 | 改寫為底層問題再繼續（反種子 guardrail） |
 | 指定的 persona/透鏡不存在 | 列出可用選項供選擇 |
 | `--enhanced` 但宿主不支援子代理 | 靜默退回 baseline，照常進行 |
-| 前 3 名全來自同一 persona/透鏡 | 標示並在輸出前再跑一個透鏡 |
+| 推薦集全來自同一 persona/透鏡 | 標示並在輸出前再跑一個透鏡 |
 | baseline 單 context 跑評審（無獨立 context） | BQS D4 標 `[degraded]`，不得標 pass |
+| 評審未宣告模型層級（或以具體廠商模型名宣告） | BQS D4 標 `[degraded]` 不得 pass；模型名改為 core/model-selection.md 的層級標籤 |
 | 外部事實宣稱無 file:line／來源 | D5 接地 fail，要求補來源或改標 `[假說]` |
 
 ## References | 參考
 
 * [Brainstorm Assistant Skill](../brainstorm-assistant/SKILL.md)
 * [Brainstorm Assistant Guide](../brainstorm-assistant/guide.md)
+* [Model Selection](../../core/model-selection.md) — model-level labels for BQS D4 and the divergence side (cited, not restated)
 * [Requirement Assistant](../requirement-assistant/SKILL.md)
 * [Spec-Driven Development](../spec-driven-dev/SKILL.md)

package/bundled/skills/commands/config.md

@@ -170,7 +170,6 @@ Supported tools for Commands:
 | Mode | Description | 說明 |
 |------|-------------|------|
 | `standard` | Summary + task mapping, AI knows when to read which standard (Recommended) | 摘要 + 任務映射（推薦）|
-| `full` | Embed all standards in integration files | 完整內嵌所有標準 |
 | `minimal` | Only core rules embedded | 僅內嵌核心規則 |
 
 ## Effects of Configuration Changes | 設定變更的影響

package/bundled/skills/commands/init.md

@@ -41,7 +41,7 @@ Use AskUserQuestion with multiSelect to ask which AI tools to configure:
 | **OpenCode** | `AGENTS.md` | ✅ | ✅ |
 | **Gemini CLI** | `GEMINI.md` | ✅ | ✅ |
 | **Codex** | `AGENTS.md` | ✅ | ❌ |
-| **Antigravity** | `INSTRUCTIONS.md` | ✅ | ❌ |
+| **Antigravity** | `.agents/AGENTS.md` | ✅ | ❌ |
 
 Pre-select tools detected in the environment. Note: Codex and OpenCode share `AGENTS.md`.
 
@@ -226,7 +226,6 @@ Use AskUserQuestion for integration file content:
 | Option | Description |
 |--------|-------------|
 | **Standard (Recommended)** | Summary + task mapping, AI knows when to read which standard |
-| **Full Embed** | Embed all rules, AI can use immediately but larger file |
 | **Minimal** | File references only, best with Skills |
 
 ### Step 13: Confirm and Execute | 步驟 13：確認並執行
@@ -312,7 +311,7 @@ See `uds init --help` for all options.
 9. **語言擴展** — 偵測到語言時詢問
 10. **框架擴展** — 偵測到框架時詢問
 11. **地區設定** — English / Traditional Chinese
-12. **內容模式** — Standard / Full Embed / Minimal
+12. **內容模式** — Standard / Minimal
 13. **確認並執行** — 展示摘要，確認後一次執行所有安裝
 
 **IMPORTANT**: AskUserQuestion 最多 4 個選項。3+ 工具時必須使用 Smart Grouping 兩階段策略。

package/bundled/skills/commit-standards/SKILL.md

@@ -147,6 +147,8 @@ After `/commit` completes, the AI assistant should suggest:
 
 ## Reference | 參考
 
+- [Conventional Commits Guide](./conventional-commits.md) — Read it when you need the exact type, scope and format rules.
+- [Output Language Options](./language-options.md) — Read it when deciding which language a commit message is written in.
 - Detailed guide: [guide.md](./guide.md)
 - Core standard: [commit-message-guide.md](../../core/commit-message-guide.md)
 

package/bundled/skills/contract-test-assistant/SKILL.md

@@ -111,6 +111,7 @@ After `/contract-test` completes:
 
 ## Reference | 參考
 
+- Detailed guide: [guide.md](./guide.md) — contract testing strategy and setup. Read it when configuring Pact/OpenAPI or wiring contract tests into CI.
 - Detailed guide: [contract-testing.md](../../options/testing/contract-testing.md)
 - Related: [api-design-assistant](../api-design-assistant/SKILL.md)
 

package/bundled/skills/dev-methodology/SKILL.md

@@ -101,6 +101,10 @@ After `/methodology` completes, the AI assistant should suggest based on the sel
 
 ## Reference | 參考
 
+- [Create Custom Methodology Guide](./create-methodology.md) — Read it when building a custom methodology rather than using a shipped one.
+- [Integrated Development Flow Guide](./integrated-flow.md) — Read it when combining several methodologies into one flow.
+- [Workflow Prerequisite Checking / 工作流前置步驟檢查](./prerequisite-check.md) — Read it when a workflow step needs its prerequisites checked first.
+- [Methodology Runtime Guide](./runtime.md) — Read it when you need to know how a methodology behaves while it runs.
 - Detailed guide: [guide.md](./guide.md)
 
 

package/bundled/skills/observability-assistant/SKILL.md

@@ -121,6 +121,7 @@ Before deploying a service to production:
 
 ## Reference | 參考
 
+- Detailed guide: [guide.md](./guide.md) — the three pillars (logs, metrics, traces) in depth. Read it when setting up monitoring, choosing metric types, implementing tracing, or assessing maturity.
 - Core standard: [observability-standards.md](../../core/observability-standards.md)
 - Core standard: [alerting-standards.md](../../core/alerting-standards.md)
 - Core standard: [slo-standards.md](../../core/slo-standards.md)

package/bundled/skills/project-discovery/SKILL.md

@@ -147,6 +147,7 @@ After `/discover` completes, the AI assistant should suggest based on the assess
 
 ## Reference | 參考
 
+- Step-by-step workflow: [workflow.md](./workflow.md) — the discovery steps in order (code health, architecture, documentation inventory, review snapshot, dependency and security). Read it when actually running a discovery rather than deciding whether to.
 - Detailed guide: [guide.md](./guide.md)
 
 

package/bundled/skills/project-structure-guide/SKILL.md

@@ -168,6 +168,7 @@ After `/project-structure` completes, the AI assistant should suggest:
 
 ## Related Standards
 
+- [Language-specific patterns](./language-patterns.md) — concrete directory layouts per language (Node.js/TypeScript, Python, Go, and others). Read it when laying out a project in a specific language.
 - [Core: Project Structure](../../core/project-structure.md)
 - [Core: Documentation Structure](../../core/documentation-structure.md)
 - [Guide: File Placement Decision Guide](../../core/guides/file-placement-guide.md)

package/bundled/skills/release-standards/SKILL.md

@@ -132,6 +132,9 @@ After `/release` completes, the AI assistant should suggest:
 
 ## Reference | 參考
 
+- [Changelog Format Guide](./changelog-format.md) — Read it when writing or reviewing a changelog entry.
+- [Release Workflow Guide](./release-workflow.md) — Read it when actually cutting a release, step by step.
+- [Semantic Versioning Guide](./semantic-versioning.md) — Read it when deciding whether a change is major, minor or patch.
 - Detailed guide: [guide.md](./guide.md)
 - Core standard: [versioning.md](../../core/versioning.md)
 

package/bundled/skills/requirement-assistant/SKILL.md

@@ -75,6 +75,8 @@ After `/requirement` completes, the AI assistant should suggest:
 
 ## Reference | 參考
 
+- [Requirement Completeness Checklist](./requirement-checklist.md) — Read it when checking a requirement is complete before it is accepted.
+- [Requirement Writing Guide](./requirement-writing.md) — Read it when writing a requirement from scratch.
 - Detailed guide: [guide.md](./guide.md)
 - Core standard: [requirement-engineering.md](../../core/requirement-engineering.md)
 

package/bundled/skills/reverse-engineer/SKILL.md

@@ -147,6 +147,9 @@ After `/reverse` (full or `spec`) completes, the AI assistant should suggest:
 
 ## Reference | 參考
 
+- [BDD Extraction Workflow Guide](./bdd-extraction.md) — Read it when extracting BDD scenarios out of an existing spec.
+- [TDD Analysis Workflow Guide](./tdd-analysis.md) — Read it when analysing test coverage against scenarios and finding the gaps.
+- Step-by-step workflow: [workflow.md](./workflow.md) — the reverse-engineering phases in order (code scanning, data models, configuration, test analysis, coverage). Read it when actually running the process rather than deciding whether to.
 - Detailed guide: [guide.md](./guide.md)
 - Core standard: [reverse-engineering-standards.md](../../core/reverse-engineering-standards.md)
 

package/bundled/skills/reverse-engineer/tdd-analysis.md

@@ -597,9 +597,22 @@ Mark both scenarios as [Inferred] with shared test reference
 
 ## CI/CD Integration
 
-### GitHub Actions Example
+### GitHub Actions — not currently scriptable
+
+There is no `uds reverse-tdd` CLI command. Coverage-gap analysis is delivered
+as the **`reverse-tdd`** AI agent (`uds agent install reverse-tdd`) — an
+interactive, LLM-driven analysis run from your AI tool, not a deterministic
+script that emits a `coverage.json` file. A prior version of this doc showed
+a GitHub Actions step invoking a CLI command that never existed (XSPEC-383
+R4, 2026-08-19).
+
+The sketch below is **illustrative only** — it shows the shape a scriptable
+CI integration would need if one is built, not something you can paste into
+a workflow today:
 
 ```yaml
+# ASPIRATIONAL — no scriptable equivalent exists yet.
+# Today: run the reverse-tdd agent interactively from your AI tool instead.
 name: BDD Coverage Check
 
 on: [pull_request]
@@ -610,29 +623,9 @@ jobs:
     steps:
       - uses: actions/checkout@v4
 
-      - name: Run BDD Coverage Analysis
-        run: |
-          uds reverse-tdd features/ --output coverage.json
-
-      - name: Check Coverage Threshold
+      - name: Run BDD Coverage Analysis (not yet implemented)
         run: |
-          COVERAGE=$(jq '.summary.effectiveCoverage' coverage.json)
-          if (( $(echo "$COVERAGE < 0.80" | bc -l) )); then
-            echo "Coverage $COVERAGE below 80% threshold"
-            exit 1
-          fi
-
-      - name: Comment on PR
-        uses: actions/github-script@v6
-        with:
-          script: |
-            const coverage = require('./coverage.json');
-            github.rest.issues.createComment({
-              issue_number: context.issue.number,
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              body: `## BDD Coverage Report\n\nCoverage: ${(coverage.summary.effectiveCoverage * 100).toFixed(1)}%`
-            });
+          echo "No CLI equivalent yet — see reverse-tdd agent for interactive use"
 ```
 
 ---

package/bundled/skills/runbook-assistant/SKILL.md

@@ -52,6 +52,7 @@ Any deploy runbook that includes a destructive-update pattern (stop → swap →
 
 ## Reference | 參考
 
+- Detailed guide: [guide.md](./guide.md) — runbook creation, organization and validation. Read it when writing runbooks, reviewing operational procedures, planning drills, or assessing coverage.
 - Core standard: [runbook-standards.md](../../core/runbook-standards.md)
 - Related: [alerting-standards.md](../../core/alerting-standards.md)
 - Related: [postmortem-standards.md](../../core/postmortem-standards.md)

package/bundled/skills/slo-assistant/SKILL.md

@@ -46,6 +46,7 @@ Guide SLI selection, SLO setting methodology, and Error Budget management.
 
 ## Reference | 參考
 
+- Detailed guide: [guide.md](./guide.md) — SLI/SLO/error-budget definition and management. Read it when defining SLOs, selecting SLIs, calculating error budgets, or setting reliability targets.
 - Core standard: [slo-standards.md](../../core/slo-standards.md)
 - Related: [observability-standards.md](../../core/observability-standards.md)
 - Related: [alerting-standards.md](../../core/alerting-standards.md)

package/bundled/skills/tdd-assistant/SKILL.md

@@ -87,6 +87,8 @@ After `/tdd` completes, the AI assistant should suggest:
 
 ## Reference | 參考
 
+- [TDD Language Examples](./language-examples.md) — Read it when you need a concrete example in a specific language.
+- [TDD Workflow Guide](./tdd-workflow.md) — Read it when running the red-green-refactor cycle end to end.
 - Detailed guide: [guide.md](./guide.md)
 - Core standard: [test-driven-development.md](../../core/test-driven-development.md)
 

package/bundled/skills/workflows/README.md

@@ -157,18 +157,9 @@ steps:
 
 ## Usage
 
-### CLI Installation
+### Getting Workflows
 
-```bash
-# List available workflows
-uds workflow list
-
-# Install specific workflow
-uds workflow install integrated-flow
-
-# Install all workflows
-uds workflow install --all
-```
+`uds workflow` was removed in v6.0.0 (process orchestration moved to the adoption layer — DEC-049; see [MIGRATION-v6.md §3](../../docs/MIGRATION-v6.md#3-removed-4-deprecated-cli-commands)). There is no CLI install step: workflow definitions live directly under `skills/workflows/*.workflow.yaml` in this repo (see the table above), so reference them by path or copy them into your project's `.claude/workflows/`.
 
 ### Execution
 

package/bundled/templates/.ai-context.yaml.template

@@ -0,0 +1,194 @@
+# ============================================================
+# .ai-context.yaml - AI Context Configuration Template
+# ============================================================
+#
+# This file helps AI assistants understand your project structure
+# and optimize their analysis and code generation.
+#
+# Usage:
+# 1. Copy this file to your project root as `.ai-context.yaml`
+# 2. Customize the values for your project
+# 3. AI tools will use this for better context management
+#
+# Reference: core/ai-friendly-architecture.md
+# ============================================================
+
+version: 1.0.0
+
+# ============================================================
+# PROJECT INFORMATION
+# ============================================================
+project:
+  # Project name (should match package.json or pyproject.toml)
+  name: my-project
+
+  # Project type affects analysis strategy
+  # Options: web-app | library | cli | api | monorepo | mobile
+  type: web-app
+
+  # Primary programming language
+  # Options: typescript | javascript | python | go | rust | java | other
+  primary-language: typescript
+
+  # Brief description for AI context
+  description: |
+    A brief description of what this project does.
+    Include key features and architectural decisions.
+
+# ============================================================
+# MODULE DEFINITIONS
+# ============================================================
+# Define logical modules in your codebase for structured analysis.
+# AI will use these boundaries to chunk large codebases efficiently.
+
+modules:
+  # Example: Authentication module
+  - name: auth
+    path: src/auth/
+    entry: index.ts
+    description: User authentication and session management
+    dependencies:
+      - database
+      - crypto
+    # Priority affects analysis order (high | medium | low)
+    priority: high
+
+  # Example: API module
+  - name: api
+    path: src/api/
+    entry: routes.ts
+    description: REST API endpoints and handlers
+    dependencies:
+      - auth
+      - database
+    priority: high
+
+  # Example: Database module
+  - name: database
+    path: src/db/
+    entry: index.ts
+    description: Database connection and models
+    dependencies: []
+    priority: high
+
+  # Example: Utilities module
+  - name: utils
+    path: src/utils/
+    entry: index.ts
+    description: Shared utility functions
+    dependencies: []
+    priority: low
+
+# ============================================================
+# ANALYSIS HINTS
+# ============================================================
+# Guide AI tools on how to analyze this project
+
+analysis-hints:
+  # Main entry points - AI starts analysis here
+  entry-points:
+    - src/main.ts
+    - src/index.ts
+
+  # Patterns to ignore during analysis
+  ignore-patterns:
+    - node_modules
+    - dist
+    - build
+    - coverage
+    - "*.test.ts"
+    - "*.spec.ts"
+    - __pycache__
+    - .venv
+
+  # Architecture type affects analysis approach
+  # Options: layered | microservices | modular | monolith | event-driven
+  architecture-type: layered
+
+  # Key configuration files to understand project setup
+  config-files:
+    - package.json
+    - tsconfig.json
+    - .env.example
+
+# ============================================================
+# DOCUMENTATION REFERENCES
+# ============================================================
+# Point AI to different documentation layers
+
+documentation:
+  # Level 1: Quick reference (< 500 tokens)
+  quick-ref: docs/QUICK-REF.md
+
+  # Level 2: Detailed architecture (< 5000 tokens)
+  detailed: docs/ARCHITECTURE.md
+
+  # Level 3: Full examples
+  examples: docs/examples/
+
+  # API documentation
+  api-docs: docs/api/
+
+  # Changelog for understanding recent changes
+  changelog: CHANGELOG.md
+
+# ============================================================
+# RLM CONTEXT STRATEGY
+# ============================================================
+# Configuration for handling large codebases with AI
+
+context-strategy:
+  # Maximum tokens per analysis chunk
+  max-chunk-size: 50000
+
+  # Token overlap between chunks for context continuity
+  overlap: 500
+
+  # Analysis pattern
+  # Options: hierarchical | parallel | sequential
+  analysis-pattern: hierarchical
+
+  # Enable RLM-aware processing
+  enable-rlm: true
+
+# ============================================================
+# CUSTOM ANNOTATIONS
+# ============================================================
+# Define project-specific code annotation patterns
+
+annotations:
+  # Security-related code markers
+  security:
+    - "@ai-security"
+    - "@security-critical"
+
+  # Performance-critical code markers
+  performance:
+    - "@ai-performance"
+    - "@perf-critical"
+
+  # Complexity hints
+  complexity:
+    - "@ai-complexity"
+
+# ============================================================
+# TEAM CONVENTIONS
+# ============================================================
+# Help AI understand your team's conventions
+
+conventions:
+  # Naming conventions
+  naming:
+    files: kebab-case        # kebab-case | camelCase | snake_case | PascalCase
+    functions: camelCase
+    classes: PascalCase
+    constants: UPPER_SNAKE
+
+  # Code style
+  style:
+    indent: 2
+    quotes: single
+    semicolons: true
+
+  # Commit message format
+  commits: conventional      # conventional | angular | custom