code-ai-installer 3.0.0 → 4.0.1-a

package/domains/development/locales/en/.agents/skills/performance-review-baseline/SKILL.md

@@ -1,8 +1,34 @@
 ---
 name: performance-review-baseline
 description: Basic perf review — N+1, pagination, batches, redundant queries, cache by architecture, heavy operations in the request path.
+type: discretionary
+domain: development
+owners:
+  - reviewer
+gates:
+  - REV
+tech: []
+topic:
+  - review
+  - security
+  - performance
+triggers:
+  - perf review
+  - N+1 query
+  - heavy operation
+  - extra queries
+  - cache strategy
+  - pagination performance
+related:
+  - data-model
+  - observability-plan
+  - observability-review
+  - review-reference-snippets
+budget_lines: 300
+schema_version: 1
 ---
 
+
 # Skill: Performance Review Baseline
 
 Performance review without premature optimization — focus on real bottlenecks.
@@ -58,7 +84,7 @@ Performance review without premature optimization — focus on real bottlenecks.
 
 ---
 
-## 2. DO / DON'T Examples
+## 2. DO / DON'T Examples <a id="2-examples"></a>
 
 ### N+1 Query Problem
 
@@ -137,7 +163,7 @@ return <Child style={style} onClick={handleClick} />;
 
 ---
 
-## 3. Latency Targets
+## 3. Latency Targets <a id="3-latency"></a>
 
 ### API endpoints
 
@@ -161,7 +187,7 @@ return <Child style={style} onClick={handleClick} />;
 
 ---
 
-## 4. Automated Detection
+## 4. Automated Detection <a id="4-detection"></a>
 
 ### Grep patterns
 
@@ -196,7 +222,7 @@ const explain = await Model.find(query).explain('executionStats');
 
 ---
 
-## 5. Output Template
+## 5. Output Template <a id="5-output"></a>
 
 ```markdown
 # Performance Review Report
@@ -229,9 +255,6 @@ const explain = await Model.find(query).explain('executionStats');
 - ⚠️ OPTIMIZATION NEEDED — P0/P1 findings
 - ❌ BLOCKED — critical performance issue breaking SLA
 ```
-
----
-
 ## See also
 - `$observability-plan` — latency targets, metrics
 - `$observability-review` — logging/metrics compliance

package/domains/development/locales/en/.agents/skills/performance-review-baseline/agents/kimi.yaml

@@ -1,14 +1,14 @@
-name: "performance-review-baseline"
-display_name: "Performance Review Baseline"
-description: "Basic perf review — N+1, pagination, batches, redundant queries, cache by architecture, heavy operations in the request path."
-default_prompt: "Use $performance-review-baseline when the task matches the \"Performance Review Baseline\" skill."
-triggers:
-  - "performance-review-baseline"
-  - "performance review baseline"
-  - "Basic perf review — N+1, pagination, batches, redundant queries, cache by architecture, heavy operations in the request path"
-capabilities:
-  - "performance"
-  - "review"
-  - "baseline"
-tools: []
-implicit_invocation: true
+name: "performance-review-baseline"
+display_name: "Performance Review Baseline"
+description: "Basic perf review — N+1, pagination, batches, redundant queries, cache by architecture, heavy operations in the request path."
+default_prompt: "Use $performance-review-baseline when the task matches the \"Performance Review Baseline\" skill."
+triggers:
+  - "performance-review-baseline"
+  - "performance review baseline"
+  - "Basic perf review — N+1, pagination, batches, redundant queries, cache by architecture, heavy operations in the request path"
+capabilities:
+  - "performance"
+  - "review"
+  - "baseline"
+tools: []
+implicit_invocation: true

package/domains/development/locales/en/.agents/skills/pm-backlog/SKILL.md

@@ -1,20 +1,44 @@
 ---
 name: pm-backlog
 description: Decomposition of PRD into an initial backlog — epics, features, and tasks with priorities, dependencies, and iteration proposals (MVP → v1).
+type: discretionary
+domain: development
+owners:
+  - product_manager
+gates:
+  - PM
+tech: []
+topic:
+  - pm
+triggers:
+  - backlog decomposition
+  - epics and features
+  - task priorities
+  - iteration plan
+  - MVP v1
+  - task dependencies
+related:
+  - pm-prd
+  - board
+  - handoff
+budget_lines: 250
+schema_version: 1
 ---
 
+
 # Skill: Backlog (epics/features/tasks)
 
-Turning PRD into planned work.
+Turn PRD into planned work.
 
 **Sections:**
 1. [Workflow](#1-workflow)
 2. [Hierarchy](#2-hierarchy)
-3. [Task Card Template](#3-task-card)
+3. [Task Card](#3-task-card)
 4. [Decomposition Rules](#4-rules)
 5. [Iteration Planning](#5-iterations)
-6. [Example](#6-example)
-7. [Output Template](#7-output)
+6. [Spike Workflow](#6-spike)
+7. [Example](#7-example)
+8. [Output Template](#8-output)
 
 ---
 
@@ -22,13 +46,11 @@ Turning PRD into planned work.
 
 ```
 1. Input: PRD (from $pm-prd) — user stories + AC
-2. Group stories into Epics (business domain areas)
-3. Break each story into Features (deliverable chunks)
-4. Break each feature into Tasks (implementable units)
-5. Assign priorities (P0/P1/P2)
-6. Map dependencies
-7. Propose iterations (section 5)
-8. Submit for review → $board
+2. Group stories → Epics → Features → Tasks (1–4h each)
+3. Assign priorities (P0/P1/P2 — definition in $pm-prd §3)
+4. Map dependencies (including external blockers and cyclic-check)
+5. Propose iterations (§5)
+6. Submit → $board, then $handoff → DEV + Conductor
 ```
 
 ---
@@ -36,64 +58,39 @@ Turning PRD into planned work.
 ## 2. Hierarchy
 
 ```
-Epic (E-xx) — business domain area
-├── Feature (F-xx) — deliverable user-facing chunk
-│   ├── Task (T-xx) — implementable unit (1-4h of work)
-│   ├── Task (T-xx)
+Epic (E-xx)    — business domain area (1–3 weeks)
+├── Feature (F-xx) — user-facing deliverable (2–5 days)
+│   ├── Task (T-xx)    — implementable unit (1–4h)
 │   └── Task (T-xx)
 ├── Feature (F-xx)
-│   └── ...
-└── Spike (SP-xx) — research / time-boxed exploration
+└── Spike (SP-xx) — time-boxed exploration (2–8h, see §6)
 ```
 
-### Level definitions
-
-| Level | What | Size | Example |
-|-------|------|------|---------|
-| **Epic** | Business domain area | 1-3 weeks | E-01: Settings Management |
-| **Feature** | User-facing deliverable | 2-5 days | F-01: Settings CRUD API |
-| **Task** | Implementable unit | 1-4 hours | T-01: Create settings schema |
-| **Spike** | Research / exploration | Time-boxed (2-8h) | SP-01: Evaluate external API integration |
-
 ---
 
-## 3. Task Card Template
+## 3. Task Card
 
 ```markdown
 ### T-XX: <Title>
 
 **Feature:** F-XX
 **Owner:** DEV / UX / ARCH / TEST
-**Priority:** P0 / P1 / P2
-**Estimate:** XS (1h) / S (2h) / M (4h) / L (8h) / XL (16h)
+**Priority:** P0 / P1 / P2  <!-- definition in $pm-prd §3 -->
+**Estimate:** XS (1h) / S (2h) / M (4h) / L (8h) / XL (16h) — L/XL see §4
 
-**Description:**
-<What needs to be done, concretely>
+**Description:** <What needs to be done, concretely>
 
 **Acceptance Criteria:**
-- [ ] <Measurable, checkable criterion>
-- [ ] <Measurable, checkable criterion>
+- [ ] <Measurable criterion>
+- [ ] <Measurable criterion>
 
 **Dependencies:**
-- Requires: T-XX (schema), F-XX (API)
-- Blocks: T-XX (UI integration)
-
-**DoD (Definition of Done):**
-- [ ] Code complete
-- [ ] Unit tests pass
-- [ ] Code review passed
-- [ ] No P0 bugs
-```
-
-### Estimation guide
+- Requires: T-XX, F-XX
+- Blocks: T-XX
+- External blocker (if any): <system + ETA>
 
-| Size | Hours | Complexity | Example |
-|------|:-----:|-----------|---------|
-| **XS** | ~1h | Trivial change | Add field to schema |
-| **S** | ~2h | Simple, well-understood | CRUD endpoint |
-| **M** | ~4h | Moderate, some decisions | Form with validation |
-| **L** | ~8h | Complex, multiple parts | Full settings page |
-| **XL** | ~16h | Large, risky → split if possible | Template system |
+**DoD:** Code complete | Unit tests pass | Review passed | No P0 bugs
+```
 
 ---
 
@@ -101,149 +98,113 @@ Epic (E-xx) — business domain area
 
 | Rule | Explanation |
 |------|------------|
-| **Vertical slices** | End-to-end features (API + UI + tests), not layer-by-layer |
-| **MVP first** | P0 = product doesn't work without it |
+| **Vertical slices** | End-to-end (API + UI + tests), not layer-by-layer |
+| **MVP first** | P0 = product doesn't work without it (definition — `$pm-prd` §3) |
 | **One task = one result** | Each task produces a checkable artifact |
-| **Max 4h per task** | If larger → split into subtasks |
-| **Spike for unknowns** | Uncertainty → create time-boxed Spike task |
-| **Dependencies explicit** | State what's required before and what this blocks |
-| **Cross-cutting last** | Polish, a11y, perf → P1/P2 after core works |
+| **Split rule** | Tasks > M (4h): split if it doesn't break the vertical slice. XL is kept only as a risk signal and requires a Spike (§6) or explicit rationale in the card |
+| **Spike for unknowns** | Any uncertainty → time-boxed Spike (§6) |
+| **Dependencies explicit** | State requires/blocks; external blockers — with system and ETA |
+| **No cyclic deps** | A↔B → break via Spike or renegotiate scope |
+| **Cross-cutting last** | Polish, a11y, perf → P1/P2 after core |
 
-### Priority rules
-
-| Priority | Criteria | % of MVP |
-|----------|---------|:--------:|
-| 🔴 **P0** | Core functionality, must ship | 60-70% |
-| 🟠 **P1** | Important UX, error handling, polish | 20-30% |
-| 🟡 **P2** | Nice-to-have, future iteration | 5-10% |
+> **Priority criteria (P0/P1/P2)** — single definition in `$pm-prd` §3 Story categories. This skill uses the same set, does not redefine.
 
 ---
 
 ## 5. Iteration Planning
 
-### Iteration format
-
 ```markdown
 ### Iteration N: <Name> (<duration>)
 
 **Goal:** <One-sentence goal>
-**Scope:** <Features/tasks included>
 **Entry criteria:** <What must be ready>
 **Exit criteria:** <What must be done>
 
 | Task | Priority | Estimate | Owner | Status |
 |------|:--------:|:--------:|:-----:|:------:|
 | T-01 | P0 | S | DEV | ☐ |
-| T-02 | P0 | M | DEV | ☐ |
 ```
 
-### Typical MVP breakdown
+Typical MVP breakdown: **Iter 1** Foundation (schema/API/CRUD) → **Iter 2** Core UI → **Iter 3** Integration → **Iter 4** Hardening (errors/edge cases/tests).
+
+---
+
+## 6. Spike Workflow
+
+A Spike is a time-boxed investigation to resolve uncertainty before estimation/decomposition.
 
-| Iteration | Focus | Content |
-|-----------|-------|---------|
-| **Iter 1** | Foundation | Schema, API, basic CRUD, install flow |
-| **Iter 2** | Core UI | Dashboard, settings, config panel |
-| **Iter 3** | Integration | Widget, live preview, templates |
-| **Iter 4** | Hardening | Error handling, edge cases, testing |
+**When to create:**
+- Cannot give an estimate (unknown complexity)
+- Multiple architectural options without a clear choice
+- Dependency on an external system with unclear constraints
+- A cycle in dependencies that needs to be broken
+
+**Lifecycle:** `TRIGGER` (unknown identified) → `TIME-BOX` (typically 2–8h, max 16h) → `SCOPE` (one research question) → `EXECUTE` (if you hit the limit — STOP, record partial result) → `OUTPUT` (ADR for architectural choice, or note in backlog) → `CLOSE` (produces new tasks with estimates, or updates existing ones, or escalation if the question is not resolved).
+
+**Spike card:**
+```markdown
+### SP-XX: <Question to answer>
+**Priority:** P0/P1  **Time-box:** Xh (hard limit)  **Owner:** <role>
+**Output:** ADR / note / new task list
+**Status:** ☐ Open / ⏳ In-progress / ✅ Closed / ⚠ Escalated
+```
 
 ---
 
-## 6. Example
+## 7. Example
 
 ```markdown
 ## E-01: Settings Management
 ### F-01: Settings CRUD API (P0)
-- T-01: Create Settings schema — S — DEV
-- T-02: POST /settings endpoint (create) — S — DEV
-- T-03: PUT /settings/:id endpoint (update) — S — DEV
-- T-04: GET /settings/:id endpoint (read) — XS — DEV
-- T-05: Settings validation (Zod schema) — S — DEV
-
-### F-02: Settings Dashboard UI (P0)
-- T-06: Settings page layout (2-column: config + preview) — M — DEV
-- T-07: General tab (title, subtitle, CTA fields) — M — DEV
-- T-08: Appearance tab (color pickers, font select) — L — DEV
-- T-09: Notifications tab (enable switch, config inputs) — S — DEV
-- T-10: Save flow (button → API → toast) — S — DEV
-
-## E-02: Product Management
-### F-03: Product CRUD API (P0)
-- T-11: Product schema — S — DEV
-- T-12: POST /products endpoint — S — DEV
-- T-13: GET /products (list) endpoint — S — DEV
-- T-14: DELETE /products/:id endpoint — XS — DEV
-
-### F-04: Product Dashboard UI (P0)
-- T-15: Products list (table + empty state) — M — DEV
-- T-16: Create product form (modal) — M — DEV
-- T-17: Delete product (confirm → delete → toast) — S — DEV
-
-## E-03: Public Content
-### F-05: Content Rendering (P0)
-- T-18: Public content endpoint (GET /content/:id) — S — DEV
-- T-19: Content template renderer — L — DEV
-- T-20: Token replacement engine (title, subtitle, colors) — M — DEV
-
-### SP-01: Evaluate External API Integration (P0, time-box: 4h)
-- Research: How to handle external webhook events
-- Output: ADR with chosen approach
+- T-01: Settings schema (Zod) — S — DEV
+- T-02: POST /settings + PUT /settings/:id — M — DEV — requires T-01
+- T-03: GET /settings/:id — XS — DEV — requires T-01
+
+### SP-01: External webhook handling approach (P0, time-box: 4h)
+- **Question:** push-based webhook vs polling vs hybrid?
+- **Output:** ADR with chosen approach
+- **Triggers:** new tasks under F-02 once closed
 ```
 
 ---
 
-## 7. Output Template
+## 8. Output Template
 
 ```markdown
-# Product Backlog: <Project Name>
+# Product Backlog: <Project>
 
-**PRD:** <reference>
-**Date:** YYYY-MM-DD
-**Author:** Product Manager Agent
+**PRD:** <reference>  **Date:** YYYY-MM-DD  **Author:** Product Manager Agent
 
 ## Summary
-| Metric | Count |
-|--------|:-----:|
-| Epics | X |
-| Features | Y |
-| Tasks | Z |
-| Spikes | W |
-| P0 tasks | A |
-| P1 tasks | B |
-| P2 tasks | C |
+| Epics | Features | Tasks | Spikes | P0 | P1 | P2 |
+|:-----:|:--------:|:-----:|:------:|:--:|:--:|:--:|
+| X | Y | Z | W | A | B | C |
 
 ## Backlog
-
-### E-01: <Epic Name>
-#### F-01: <Feature Name> (P0)
+### E-01: <Epic>
+#### F-01: <Feature> (P0)
 | Task | Priority | Estimate | Owner | Deps | Status |
 |------|:--------:|:--------:|:-----:|------|:------:|
-| T-01: ... | P0 | S | DEV | — | ☐ |
-| T-02: ... | P0 | M | DEV | T-01 | ☐ |
-
-#### F-02: <Feature Name> (P0)
-...
+| T-01 | P0 | S | DEV | — | ☐ |
 
-### E-02: <Epic Name>
-...
+## Spikes
+| ID | Question | Time-box | Output | Status |
+|----|----------|:--------:|--------|:------:|
+| SP-01 | ... | 4h | ADR | ☐ |
 
 ## Iterations
-<section 5 format>
+<§5 format per iteration>
 
 ## Dependencies Graph
-<list critical path dependencies>
-
-## Spikes
-| ID | Question | Time box | Output | Status |
-|----|---------|:--------:|--------|:------:|
-| SP-01 | ... | 4h | ADR | ☐ |
+<critical path; external blockers with system and ETA>
 
 ## Next Step
-→ Transfer to $board for tracking
+→ Transfer to $board for tracking; then $handoff → DEV + Conductor
 ```
 
 ---
 
 ## See also
-- `$pm-prd` — PRD (input)
+- `$pm-prd` — PRD (input) + single P0/P1/P2 definition
 - `$board` — project board (tracks execution)
-- `$handoff` — gate transitions
+- `$handoff` — gate transitions (PM → DEV/Conductor)

package/domains/development/locales/en/.agents/skills/pm-backlog/agents/kimi.yaml

@@ -1,13 +1,13 @@
-name: "pm-backlog"
-display_name: "PM Backlog"
-description: "Decomposition of PRD into an initial backlog — epics, features, and tasks with priorities, dependencies, and iteration proposals (MVP → v1)."
-default_prompt: "Use $pm-backlog when the task matches the \"PM Backlog\" skill."
-triggers:
-  - "pm-backlog"
-  - "pm backlog"
-  - "Decomposition of PRD into an initial backlog — epics, features, and tasks with priorities, dependencies, and iteration proposals (MVP → v1)"
-capabilities:
-  - "pm"
-  - "backlog"
-tools: []
-implicit_invocation: true
+name: "pm-backlog"
+display_name: "PM Backlog"
+description: "Decomposition of PRD into an initial backlog — epics, features, and tasks with priorities, dependencies, and iteration proposals (MVP → v1)."
+default_prompt: "Use $pm-backlog when the task matches the \"PM Backlog\" skill."
+triggers:
+  - "pm-backlog"
+  - "pm backlog"
+  - "Decomposition of PRD into an initial backlog — epics, features, and tasks with priorities, dependencies, and iteration proposals (MVP → v1)"
+capabilities:
+  - "pm"
+  - "backlog"
+tools: []
+implicit_invocation: true

package/domains/development/locales/en/.agents/skills/pm-interview/SKILL.md

@@ -1,8 +1,31 @@
 ---
 name: pm-interview
 description: Structured interview/documentation review — gather goals, audience, MVP, constraints, integrations, and success criteria to write a PRD.
+type: discretionary
+domain: development
+owners:
+  - product_manager
+gates:
+  - PM
+tech: []
+topic:
+  - pm
+triggers:
+  - PM interview
+  - documentation review
+  - goals and audience
+  - success criteria
+  - integrations and constraints
+  - requirements gathering
+related:
+  - pm-prd
+  - pm-backlog
+  - ux-discovery
+budget_lines: 200
+schema_version: 1
 ---
 
+
 # Skill: PM Interview / Discovery
 
 Gather the minimum sufficient information for a PRD.
@@ -11,35 +34,27 @@ Gather the minimum sufficient information for a PRD.
 1. [Workflow](#1-workflow)
 2. [Question Bank](#2-questions)
 3. [Priority & Assumptions](#3-priority)
-4. [Output Template](#5-output)
+4. [Output Template](#4-output)
 
 ---
 
 ## 1. Workflow
 
 ```
-1. Read what is already available:
-   ├── User brief / idea description
-   ├── Existing code / README
-   └── Previous documents (if any)
-
+1. Read: user brief + code/README + previous docs
 2. Extract facts (what is already known)
-
-3. Identify gaps (what needs clarification)
-   └── Use Question Bank (section 2)
-
-4. Prioritize questions:
-   ├── 🔴 Blocking — cannot write PRD without an answer
-   ├── 🟠 Important — affects PRD, but can be assumed
-   └── 🟡 Nice-to-know — can be deferred
-
-5. Ask questions (only blocking + important)
-   └── For the rest → make assumptions marked ASSUMPTION
-
-6. Generate Interview Summary (section 5)
-   └── Pass to → $pm-prd
+3. Identify gaps → Use Question Bank (§2)
+4. Prioritize: 🔴 Blocking / 🟠 Important / 🟡 Nice-to-know
+5. Ask blocking + important (rest → ASSUMPTION)
+6. Generate Interview Summary (§4) → $pm-prd
 ```
 
+### Interview technique
+- **Open > closed**: "Tell me how you solve X today?" > "Do you use Excel?"
+- **Active listening**: rephrase the answer ("Got it right: ...?") before the next question
+- **Max 7–10 questions/round**: more degrades answer quality; split into several short rounds
+- **Defensive answers** ("it's obvious", "we'll figure it out later"): don't push, log as gap + agree to revisit later
+
 ### When an interview is NOT needed
 
 | Situation | Action |
@@ -47,6 +62,8 @@ Gather the minimum sufficient information for a PRD.
 | User provided a detailed brief with answers to everything | Skip → go straight to $pm-prd |
 | Iteration on an existing PRD | Minimal interview (only new questions) |
 | Bugfix / patch | Not needed |
+| Feature addition to existing product | Only delta questions (scope/UX of what changes) |
+| Re-pitch of an old idea to new stakeholders | Brief interview about their context/expectations |
 
 ---
 
@@ -100,6 +117,8 @@ Gather the minimum sufficient information for a PRD.
 | Q-17 | Where do we deploy? | Infrastructure | 🟠 |
 | Q-18 | Is an admin panel needed? | Additional scope | 🟡 |
 
+> **Adaptation:** Question Bank is a starter set. For a given domain (B2B SaaS / mobile-consumer / internal tooling) add 3–5 domain-specific questions or drop irrelevant ones.
+
 ---
 
 ## 3. Priority & Assumptions
@@ -112,6 +131,13 @@ Gather the minimum sufficient information for a PRD.
 | Can proceed with a safe assumption | 🟠 Assume + mark ASSUMPTION |
 | Can be deferred to PRD review | 🟡 Add to Open Questions |
 
+### "I don't know" on a 🔴 question
+
+| Risk | Action |
+|------|---------|
+| Low/Medium | Convert to ASSUMPTION-XX with risk=High, explicit `confirm-by: <milestone>`, log in Open Questions |
+| Catastrophic (security / data integrity / regulatory) | **Block PRD** — escalate to the user (or their proxy); do not proceed without an answer |
+
 ### Assumption format
 
 ```markdown
@@ -123,10 +149,7 @@ Gather the minimum sufficient information for a PRD.
 
 ---
 
-
----
-
-## 5. Output Template
+## 4. Output Template
 
 ```markdown
 # PM Interview Summary

package/domains/development/locales/en/.agents/skills/pm-interview/agents/kimi.yaml

@@ -1,14 +1,14 @@
-name: "pm-interview"
-display_name: "PM Interview / Discovery"
-description: "Structured interview/documentation review — gather goals, audience, MVP, constraints, integrations, and success criteria to write a PRD."
-default_prompt: "Use $pm-interview when the task matches the \"PM Interview / Discovery\" skill."
-triggers:
-  - "pm-interview"
-  - "pm interview"
-  - "PM Interview / Discovery"
-  - "Structured interview/documentation review — gather goals, audience, MVP, constraints, integrations, and success criteria to write a PRD"
-capabilities:
-  - "pm"
-  - "interview"
-tools: []
-implicit_invocation: true
+name: "pm-interview"
+display_name: "PM Interview / Discovery"
+description: "Structured interview/documentation review — gather goals, audience, MVP, constraints, integrations, and success criteria to write a PRD."
+default_prompt: "Use $pm-interview when the task matches the \"PM Interview / Discovery\" skill."
+triggers:
+  - "pm-interview"
+  - "pm interview"
+  - "PM Interview / Discovery"
+  - "Structured interview/documentation review — gather goals, audience, MVP, constraints, integrations, and success criteria to write a PRD"
+capabilities:
+  - "pm"
+  - "interview"
+tools: []
+implicit_invocation: true