claude-code-pilot 3.2.0 → 3.3.0

package/src/pilot/workflows/mvp-phase.md

@@ -0,0 +1,199 @@
+<purpose>
+Guide the user through MVP-mode planning for a phase. Prompts for an "As a / I want to / So that" user story, runs SPIDR splitting check on the story, writes the result to ROADMAP.md, and delegates to `/ccp:plan-phase` (which auto-detects MVP via the roadmap mode field shipped in PRD Phase 1).
+</purpose>
+
+<required_reading>
+@~/.claude/pilot/references/user-story-template.md
+@~/.claude/pilot/references/spidr-splitting.md
+@~/.claude/pilot/references/planner-mvp-mode.md
+</required_reading>
+
+<runtime_note>
+**Copilot (VS Code):** Use `vscode_askquestions` wherever this workflow calls `AskUserQuestion`. They are equivalent.
+
+**TEXT_MODE fallback:** Set TEXT_MODE=true if `--text` is present in `$ARGUMENTS` OR `text_mode` from init JSON is true. When TEXT_MODE is active, replace every AskUserQuestion call with a plain-text numbered list and ask the user to type their choice number.
+</runtime_note>
+
+<process>
+
+## 1. Parse and validate phase argument
+
+Extract the phase number from `$ARGUMENTS` (integer or decimal like `2.1`). Optional flag: `--force` (allow operating on `in_progress` / `completed` phases).
+
+If no argument:
+```
+ERROR: Phase number required
+Usage: /ccp:mvp-phase <phase-number>
+Example: /ccp:mvp-phase 1
+Example: /ccp:mvp-phase 2.1
+```
+Exit.
+
+Normalize per `@~/.claude/pilot/references/phase-argument-parsing.md` (zero-pad integer phases to two digits).
+
+## 2. Validate phase exists and check status
+
+Read `.planning/ROADMAP.md` and extract the Phase `${PHASE}` block: locate the `### Phase ${PHASE}:` heading, then capture the `**Goal**:`, `**Mode**:` (if present), `**Depends on**:`, and `**Requirements**:` lines that follow. Record the phase name from the heading, the goal text, and the mode (empty string if no `**Mode**:` line exists).
+
+To compute disk status, list the contents of `.planning/phases/` and check whether a directory matching `${PHASE}-*` exists, and whether it contains an `XX-SUMMARY.md` summary file alongside `XX-PLAN.md` files. Apply this mapping:
+
+- If a `phase-complete` summary or all plan summaries are present, treat status as `completed`.
+- If any `XX-PLAN.md` file exists for the phase but the phase is not complete, treat status as `in_progress`.
+- Otherwise, treat status as `not_started`.
+
+If the phase was not found in ROADMAP.md: error and exit. Suggest `/ccp:add-phase` or `/ccp:insert-phase` to create the phase first.
+
+**Status guard.** If the phase is `in_progress` (has plans but not complete) or `completed`, refuse unless `--force` is in `$ARGUMENTS`:
+
+```text
+ERROR: Phase ${PHASE} is currently ${STATUS}.
+Converting an active or completed phase to MVP mode mid-flight will
+invalidate any existing plans and summaries.
+
+To proceed anyway: /ccp:mvp-phase ${PHASE} --force
+```
+
+**Already-MVP guard.** If `PHASE_MODE` is already `mvp`, surface this and ask whether to re-prompt the user story or abort:
+
+> "Phase ${PHASE} is already in MVP mode with goal: «${PHASE_GOAL}». Re-run user-story prompts and SPIDR check?"
+
+Use `AskUserQuestion` with options [Re-prompt / Abort]. On Abort, exit cleanly. On Re-prompt, proceed.
+
+## 3. User story prompts
+
+Run three sequential `AskUserQuestion` calls. Each is free-text. After all three, assemble into the canonical sentence per `@~/.claude/pilot/references/user-story-template.md`:
+
+**Prompt 1 — As a:**
+> "As a [user role]?"
+> (Examples: "new user", "admin", "signed-in customer", "API consumer")
+
+**Prompt 2 — I want to:**
+> "I want to [capability]?"
+> (Examples: "register and log in", "upload a CSV", "see my dashboard")
+
+**Prompt 3 — So that:**
+> "So that [outcome]?"
+> (Examples: "I can access my account", "I can bulk-import contacts", "I can see at a glance what needs attention")
+
+Assemble:
+
+```
+USER_STORY="As a ${ROLE}, I want to ${CAPABILITY}, so that ${OUTCOME}."
+```
+
+If any of the three answers is empty or whitespace-only, error and re-prompt that single field. Do NOT proceed with a partial story.
+
+**Validate the assembled story against the canonical regex** `/^As a .+, I want to .+, so that .+\.$/`. The verb owns this regex and surfaces per-error guidance:
+
+- If the story does not match, identify which clause is missing or malformed (`As a ...`, `I want to ...`, `so that ...`, trailing period) and re-prompt only the offending field(s).
+- Rebuild `USER_STORY` and re-validate before continuing.
+- Do not abort the workflow on first invalid draft.
+
+This guarantees the goal stored in ROADMAP.md will satisfy the same guard the verifier applies later.
+
+## 4. SPIDR splitting check
+
+Run the SPIDR rules from `@~/.claude/pilot/references/spidr-splitting.md`. Briefly:
+
+**Trigger evaluation.** Check the assembled `USER_STORY` against the four size signals from the reference (compound capabilities, multi-actor, length > 120 chars, vague capability). If none fire, **skip SPIDR** entirely — go to step 5.
+
+**If SPIDR triggers.**
+
+a) Restate the story to the user:
+
+> "Your story: «${USER_STORY}»
+>
+> This story has [signal description, e.g., 'two compound capabilities joined by and']. Splitting it into multiple phases will produce a cleaner Walking Skeleton and reduce the risk of mid-phase scope creep.
+>
+> Want to walk through SPIDR splitting?"
+
+Use `AskUserQuestion` with options [Yes, walk through SPIDR / No, proceed with the story as-is].
+
+If "No": skip SPIDR, go to step 5.
+
+If "Yes": continue to (b).
+
+b) Ask which SPIDR axis fits best:
+
+> "Which axis best fits how to split this story?"
+
+Use `AskUserQuestion` with the five options from `spidr-splitting.md` (Spike / Paths / Interfaces / Data / Rules). Each option includes its targeted question as the description so the user can pick by understanding what each axis means.
+
+c) Walk through the chosen axis with **one** targeted question (not all five). For example, if the user picked "Paths":
+
+> "Does this feature have a happy path and one or more error/edge paths?"
+
+Free-text response. Workflow parses to identify the split.
+
+d) Produce a split proposal. Example:
+
+> "Proposed split (Paths axis):
+> - **Phase ${PHASE} (this one):** Happy path — ${HAPPY_STORY}
+> - **Phase ${PHASE+1} (new):** Edge case — ${EDGE_STORY}
+>
+> Accept this split?"
+
+Use `AskUserQuestion` [Accept / Modify / Reject].
+
+- **Accept**: `USER_STORY` becomes the first split's story (`${HAPPY_STORY}` in the example). Surface the remaining splits as a list of `/ccp:add-phase` invocations the user can run after this command completes — do NOT auto-create the new phases (preserve user control over numbering).
+- **Modify**: re-prompt the splits one more time, then accept or reject.
+- **Reject**: revert `USER_STORY` to the original, proceed without splitting.
+
+## 5. Update ROADMAP.md
+
+Read `ROADMAP.md`. Find the section for `Phase ${PHASE}`. Apply two edits:
+
+**Edit 1 — Update Goal line.**
+
+Find: `**Goal:** ${OLD_GOAL_TEXT}`
+Replace with: `**Goal:** ${USER_STORY}`
+
+**Edit 2 — Insert Mode line.**
+
+If `**Mode:**` already exists in the section (replacing or re-running), update it to `**Mode:** mvp`.
+If `**Mode:**` does not exist, insert `**Mode:** mvp` on the line immediately after `**Goal:**`.
+
+Show the user a unified diff (lines being changed) and ask:
+
+> "Apply these changes to ROADMAP.md?"
+
+Use `AskUserQuestion` [Apply / Cancel]. On Cancel, exit without writing.
+
+On Apply, write the updated `ROADMAP.md` atomically (read-edit-write).
+
+## 6. Verify the write
+
+Re-read `.planning/ROADMAP.md` and re-extract the Phase `${PHASE}` block: locate the `### Phase ${PHASE}:` heading and capture the `**Goal**:` and `**Mode**:` lines that follow.
+
+Assert:
+- The new `**Mode**:` value equals `mvp`
+- The new `**Goal**:` value equals the assembled user story
+
+If either assertion fails, surface the discrepancy to the user and exit. Do not proceed to plan-phase delegation with a half-applied write.
+
+## 7. Delegate to /ccp:plan-phase
+
+Invoke `/ccp:plan-phase ${PHASE}` (no flags). Phase 1's MVP_MODE resolution chain (CLI flag → roadmap mode → config → false) will detect the new `**Mode:** mvp` line and run plan-phase in vertical-slice mode automatically.
+
+The Walking Skeleton gate (also from Phase 1) will fire automatically if `${PHASE} == "01"` and there are zero prior phase summaries.
+
+## 8. Surface deferred phase splits (if any)
+
+If SPIDR produced a split in step 4, append a final user-facing message:
+
+> "**SPIDR split deferred phases.**
+>
+> Your original story was split. The first slice is now planned via plan-phase.
+> To create the remaining slice(s) as new phases, run:
+>
+> - `/ccp:add-phase` — for the next slice: «${SPLIT_2_STORY}»
+> - `/ccp:add-phase` — for the next slice: «${SPLIT_3_STORY}»
+>
+> Each will be added to the end of the current milestone. You can then run
+> `/ccp:mvp-phase <new-phase-number>` on each to plan them as MVP slices."
+
+## 9. Exit
+
+Workflow ends. The phase is now in MVP mode with a planned PLAN.md, optionally with deferred follow-up phases surfaced for the user.
+
+</process>

package/src/skills/agent-architecture-audit/SKILL.md

@@ -0,0 +1,256 @@
+---
+name: agent-architecture-audit
+description: Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature.
+origin: oh-my-agent-check
+tools: Read, Write, Edit, Bash, Grep, Glob
+---
+
+# Agent Architecture Audit
+
+A diagnostic workflow for agent systems that hide failures behind wrapper layers, stale memory, retry loops, or transport/rendering mutations.
+
+## When to Activate
+
+**MANDATORY for:**
+- Releasing any agent or LLM-powered application to production
+- Shipping features with tool calling, memory, or multi-step workflows
+- Agent behavior degrades after adding wrapper layers
+- User reports "the agent is getting worse" or "tools are flaky"
+- Same model works in playground but breaks inside your wrapper
+- Debugging agent behavior for more than 15 minutes without finding root cause
+
+**Especially critical when:**
+- You've added new prompt layers, tool definitions, or memory systems
+- Different agents in your system behave inconsistently
+- The model was fine yesterday but is hallucinating today
+- You suspect hidden repair/retry loops silently mutating responses
+
+**Do not use for:**
+- General code debugging — use `agent-introspection-debugging`
+- Code review — use language-specific reviewer agents
+- Security scanning — use `security-review` or `security-review/scan`
+- Agent performance benchmarking — use `agent-eval`
+- Writing new features — use the appropriate workflow skill
+
+## The 12-Layer Stack
+
+Every agent system has these layers. Any of them can corrupt the answer:
+
+| # | Layer | What Goes Wrong |
+|---|-------|----------------|
+| 1 | System prompt | Conflicting instructions, instruction bloat |
+| 2 | Session history | Stale context injection from previous turns |
+| 3 | Long-term memory | Pollution across sessions, old topics in new conversations |
+| 4 | Distillation | Compressed artifacts re-entering as pseudo-facts |
+| 5 | Active recall | Redundant re-summary layers wasting context |
+| 6 | Tool selection | Wrong tool routing, model skips required tools |
+| 7 | Tool execution | Hallucinated execution — claims to call but doesn't |
+| 8 | Tool interpretation | Misread or ignored tool output |
+| 9 | Answer shaping | Format corruption in final response |
+| 10 | Platform rendering | Transport-layer mutation (UI, API, CLI mutates valid answers) |
+| 11 | Hidden repair loops | Silent fallback/retry agents running second LLM pass |
+| 12 | Persistence | Expired state or cached artifacts reused as live evidence |
+
+## Common Failure Patterns
+
+### 1. Wrapper Regression
+
+The base model produces correct answers, but the wrapper layers make it worse.
+
+**Symptoms:**
+- Model works fine in playground or direct API call, breaks in your agent
+- Added a new prompt layer, existing behavior degraded
+- Agent sounds confident but is confidently wrong
+- "It was working before the last update"
+
+### 2. Memory Contamination
+
+Old topics leak into new conversations through history, memory retrieval, or distillation.
+
+**Symptoms:**
+- Agent brings up unrelated past topics
+- User corrections don't stick (old memory overwrites new)
+- Same-session artifacts re-enter as pseudo-facts
+- Memory grows without bound, degrading response quality over time
+
+### 3. Tool Discipline Failure
+
+Tools are declared in the prompt but not enforced in code. The model skips them or hallucinates execution.
+
+**Symptoms:**
+- "Must use tool X" in prompt, but model answers without calling it
+- Tool results look correct but were never actually executed
+- Different tools fight over the same responsibility
+- Model uses tool when it shouldn't, or skips it when it must
+
+### 4. Rendering/Transport Corruption
+
+The agent's internal answer is correct, but the platform layer mutates it during delivery.
+
+**Symptoms:**
+- Logs show correct answer, user sees broken output
+- Markdown rendering, JSON parsing, or streaming fragments corrupt valid responses
+- Hidden fallback agent quietly replaces the answer before delivery
+- Output differs between terminal and UI
+
+### 5. Hidden Agent Layers
+
+Silent repair, retry, summarization, or recall agents run without explicit contracts.
+
+**Symptoms:**
+- Output changes between internal generation and user delivery
+- "Auto-fix" loops run a second LLM pass the user doesn't know about
+- Multiple agents modify the same output without coordination
+- Answers get "smoothed" or "corrected" by invisible layers
+
+## Audit Workflow
+
+### Phase 1: Scope
+
+Define what you're auditing:
+
+- **Target system** — what agent application?
+- **Entrypoints** — how do users interact with it?
+- **Model stack** — which LLM(s) and providers?
+- **Symptoms** — what does the user report?
+- **Time window** — when did it start?
+- **Layers to audit** — which of the 12 layers apply?
+
+### Phase 2: Evidence Collection
+
+Gather evidence from the codebase:
+
+- **Source code** — agent loop, tool router, memory admission, prompt assembly
+- **Logs** — historical session traces, tool call records
+- **Config** — prompt templates, tool schemas, provider settings
+- **Memory files** — SOPs, knowledge bases, session archives
+
+Use `rg` to search for anti-patterns:
+
+```bash
+# Tool requirements expressed only in prompt text (not code)
+rg "must.*tool|必须.*工具|required.*call" --type md
+
+# Tool execution without validation
+rg "tool_call|toolCall|tool_use" --type py --type ts
+
+# Hidden LLM calls outside main agent loop
+rg "completion|chat\.create|messages\.create|llm\.invoke"
+
+# Memory admission without user-correction priority
+rg "memory.*admit|long.*term.*update|persist.*memory" --type py --type ts
+
+# Fallback loops that run additional LLM calls
+rg "fallback|retry.*llm|repair.*prompt|re-?prompt" --type py --type ts
+
+# Silent output mutation
+rg "mutate|rewrite.*response|transform.*output|shap" --type py --type ts
+```
+
+### Phase 3: Failure Mapping
+
+For each finding, document:
+
+- **Symptom** — what the user sees
+- **Mechanism** — how the wrapper causes it
+- **Source layer** — which of the 12 layers
+- **Root cause** — the deepest cause
+- **Evidence** — file:line or log:row reference
+- **Confidence** — 0.0 to 1.0
+
+### Phase 4: Fix Strategy
+
+Default fix order (code-first, not prompt-first):
+
+1. **Code-gate tool requirements** — enforce in code, not just prompt text
+2. **Remove or narrow hidden repair agents** — make fallback explicit with contracts
+3. **Reduce context duplication** — same info through prompt + history + memory + distillation
+4. **Tighten memory admission** — user corrections > agent assertions
+5. **Tighten distillation triggers** — don't compress what shouldn't be compressed
+6. **Reduce rendering mutation** — pass-through, don't transform
+7. **Convert to typed JSON envelopes** — structured internal flow, not freeform prose
+
+## Severity Model
+
+| Level | Meaning | Action |
+|-------|---------|--------|
+| `critical` | Agent can confidently produce wrong operational behavior | Fix before next release |
+| `high` | Agent frequently degrades correctness or stability | Fix this sprint |
+| `medium` | Correctness usually survives but output is fragile or wasteful | Plan for next cycle |
+| `low` | Mostly cosmetic or maintainability issues | Backlog |
+
+## Output Format
+
+Present findings to the user in this order:
+
+1. **Severity-ranked findings** (most critical first)
+2. **Architecture diagnosis** (which layer corrupted what, and why)
+3. **Ordered fix plan** (code-first, not prompt-first)
+
+Do not lead with compliments or summaries. If the system is broken, say so directly.
+
+## Quick Diagnostic Questions
+
+When auditing an agent system, answer these:
+
+| # | Question | If Yes → |
+|---|----------|----------|
+| 1 | Can the model skip a required tool and still answer? | Tool not code-gated |
+| 2 | Does old conversation content appear in new turns? | Memory contamination |
+| 3 | Is the same info in system prompt AND memory AND history? | Context duplication |
+| 4 | Does the platform run a second LLM pass before delivery? | Hidden repair loop |
+| 5 | Does the output differ between internal generation and user delivery? | Rendering corruption |
+| 6 | Are "must use tool X" rules only in prompt text? | Tool discipline failure |
+| 7 | Can the agent's own monologue become persistent memory? | Memory poisoning |
+
+## Anti-Patterns to Avoid
+
+- Avoid blaming the model before falsifying wrapper-layer regressions.
+- Avoid blaming memory without showing the contamination path.
+- Do not let a clean current state erase a dirty historical incident.
+- Do not treat markdown prose as a trustworthy internal protocol.
+- Do not accept "must use tool" in prompt text when code never enforces it.
+- Keep findings direct, evidence-backed, and severity-ranked.
+
+## Report Schema
+
+Audits should produce structured reports following this shape:
+
+```json
+{
+  "schema_version": "ecc.agent-architecture-audit.report.v1",
+  "executive_verdict": {
+    "overall_health": "high_risk",
+    "primary_failure_mode": "string",
+    "most_urgent_fix": "string"
+  },
+  "scope": {
+    "target_name": "string",
+    "model_stack": ["string"],
+    "layers_to_audit": ["string"]
+  },
+  "findings": [
+    {
+      "severity": "critical|high|medium|low",
+      "title": "string",
+      "mechanism": "string",
+      "source_layer": "string",
+      "root_cause": "string",
+      "evidence_refs": ["file:line"],
+      "confidence": 0.0,
+      "recommended_fix": "string"
+    }
+  ],
+  "ordered_fix_plan": [
+    { "order": 1, "goal": "string", "why_now": "string", "expected_effect": "string" }
+  ]
+}
+```
+
+## Related Skills
+
+- `agent-introspection-debugging` — Debug agent runtime failures (loops, timeouts, state errors)
+- `agent-eval` — Benchmark agent performance head-to-head
+- `security-review` — Security audit for code and configuration
+- `autonomous-agent-harness` — Set up autonomous agent operations
+- `agent-harness-construction` — Build agent harnesses from scratch

package/src/skills/agent-harness-design/SKILL.md

@@ -0,0 +1,73 @@
+---
+name: agent-harness-design
+description: Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.
+origin: ECC
+---
+
+# Agent Harness Construction
+
+Use this skill when you are improving how an agent plans, calls tools, recovers from errors, and converges on completion.
+
+## Core Model
+
+Agent output quality is constrained by:
+1. Action space quality
+2. Observation quality
+3. Recovery quality
+4. Context budget quality
+
+## Action Space Design
+
+1. Use stable, explicit tool names.
+2. Keep inputs schema-first and narrow.
+3. Return deterministic output shapes.
+4. Avoid catch-all tools unless isolation is impossible.
+
+## Granularity Rules
+
+- Use micro-tools for high-risk operations (deploy, migration, permissions).
+- Use medium tools for common edit/read/search loops.
+- Use macro-tools only when round-trip overhead is the dominant cost.
+
+## Observation Design
+
+Every tool response should include:
+- `status`: success|warning|error
+- `summary`: one-line result
+- `next_actions`: actionable follow-ups
+- `artifacts`: file paths / IDs
+
+## Error Recovery Contract
+
+For every error path, include:
+- root cause hint
+- safe retry instruction
+- explicit stop condition
+
+## Context Budgeting
+
+1. Keep system prompt minimal and invariant.
+2. Move large guidance into skills loaded on demand.
+3. Prefer references to files over inlining long documents.
+4. Compact at phase boundaries, not arbitrary token thresholds.
+
+## Architecture Pattern Guidance
+
+- ReAct: best for exploratory tasks with uncertain path.
+- Function-calling: best for structured deterministic flows.
+- Hybrid (recommended): ReAct planning + typed tool execution.
+
+## Benchmarking
+
+Track:
+- completion rate
+- retries per task
+- pass@1 and pass@3
+- cost per successful task
+
+## Anti-Patterns
+
+- Too many tools with overlapping semantics.
+- Opaque tool output with no recovery hints.
+- Error-only output without next steps.
+- Context overloading with irrelevant references.

package/src/skills/angular-developer/SKILL.md

@@ -0,0 +1,154 @@
+---
+name: angular-developer
+description: Generates Angular code and provides architectural guidance. Trigger when creating projects, components, or services, or for best practices on reactivity (signals, linkedSignal, resource), forms, dependency injection, routing, SSR, accessibility (ARIA), animations, styling (component styles, Tailwind CSS), testing, or CLI tooling.
+origin: ECC
+---
+
+# Angular Developer Guidelines
+
+## When to Activate
+
+- Working in any Angular project or codebase
+- Creating or scaffolding a new Angular project, application, or library
+- Generating components, services, directives, pipes, guards, or resolvers
+- Implementing reactivity with Angular Signals, `linkedSignal`, or `resource`
+- Working with Angular forms (signal forms, reactive forms, or template-driven)
+- Setting up dependency injection, routing, lazy loading, or route guards
+- Adding accessibility (ARIA), animations, or component styling
+- Writing or debugging Angular-specific tests (unit, component harness, E2E)
+- Configuring Angular CLI tooling or the Angular MCP server
+
+1. Always analyze the project's Angular version before providing guidance, as best practices and available features can vary significantly between versions. If creating a new project with Angular CLI, do not specify a version unless prompted by the user.
+
+2. When generating code, follow Angular's style guide and best practices for maintainability and performance. Use the Angular CLI for scaffolding components, services, directives, pipes, and routes to ensure consistency.
+
+3. Once you finish generating code, run `ng build` to ensure there are no build errors. If there are errors, analyze the error messages and fix them before proceeding. Do not skip this step, as it is critical for ensuring the generated code is correct and functional.
+
+## Creating New Projects
+
+If no guidelines are provided by the user, use these defaults when creating a new Angular project:
+
+1. Use the latest stable version of Angular unless the user specifies otherwise.
+2. Prefer Signal Forms for new projects only when the target Angular version supports them. [Find out more](references/signal-forms.md).
+
+**Execution Rules for `ng new`:**
+When asked to create a new Angular project, you must determine the correct execution command by following these strict steps:
+
+**Step 1: Check for an explicit user version.**
+
+- **IF** the user requests a specific version (e.g., Angular 15), bypass local installations and strictly use `npx`.
+- **Command:** `npx @angular/cli@<requested_version> new <project-name>`
+
+**Step 2: Check for an existing Angular installation.**
+
+- **IF** no specific version is requested, run `ng version` in the terminal to check if the Angular CLI is already installed on the system.
+- **IF** the command succeeds and returns an installed version, use the local/global installation directly.
+- **Command:** `ng new <project-name>`
+
+**Step 3: Fallback to Latest.**
+
+- **IF** no specific version is requested AND the `ng version` command fails (indicating no Angular installation exists), you must use `npx` to fetch the latest version.
+- **Command:** `npx @angular/cli@latest new <project-name>`
+
+## Components
+
+When working with Angular components, consult the following references based on the task:
+
+- **Fundamentals**: Anatomy, metadata, core concepts, and template control flow (@if, @for, @switch). Read [components.md](references/components.md)
+- **Inputs**: Signal-based inputs, transforms, and model inputs. Read [inputs.md](references/inputs.md)
+- **Outputs**: Signal-based outputs and custom event best practices. Read [outputs.md](references/outputs.md)
+- **Host Elements**: Host bindings and attribute injection. Read [host-elements.md](references/host-elements.md)
+
+If you require deeper documentation not found in the references above, read the documentation at `https://angular.dev/guide/components`.
+
+## Reactivity and Data Management
+
+When managing state and data reactivity, use Angular Signals and consult the following references:
+
+- **Signals Overview**: Core signal concepts (`signal`, `computed`), reactive contexts, and `untracked`. Read [signals-overview.md](references/signals-overview.md)
+- **Dependent State (`linkedSignal`)**: Creating writable state linked to source signals. Read [linked-signal.md](references/linked-signal.md)
+- **Async Reactivity (`resource`)**: Fetching asynchronous data directly into signal state. Read [resource.md](references/resource.md)
+- **Side Effects (`effect`)**: Logging, third-party DOM manipulation (`afterRenderEffect`), and when NOT to use effects. Read [effects.md](references/effects.md)
+
+## Forms
+
+In most cases for new apps, **prefer signal forms**. When making a forms decision, analyze the project and consider the following guidelines:
+
+- If the application version supports Signal Forms and this is a new form, **prefer signal forms**.
+- For older applications or existing forms, match the application's current form strategy.
+
+- **Signal Forms**: Use signals for form state management. Read [signal-forms.md](references/signal-forms.md)
+- **Template-driven forms**: Use for simple forms. Read [template-driven-forms.md](references/template-driven-forms.md)
+- **Reactive forms**: Use for complex forms. Read [reactive-forms.md](references/reactive-forms.md)
+
+## Dependency Injection
+
+When implementing dependency injection in Angular, follow these guidelines:
+
+- **Fundamentals**: Overview of Dependency Injection, services, and the `inject()` function. Read [di-fundamentals.md](references/di-fundamentals.md)
+- **Creating and Using Services**: Creating services, the `providedIn: 'root'` option, and injecting into components or other services. Read [creating-services.md](references/creating-services.md)
+- **Defining Dependency Providers**: Automatic vs manual provision, `InjectionToken`, `useClass`, `useValue`, `useFactory`, and scopes. Read [defining-providers.md](references/defining-providers.md)
+- **Injection Context**: Where `inject()` is allowed, `runInInjectionContext`, and `assertInInjectionContext`. Read [injection-context.md](references/injection-context.md)
+- **Hierarchical Injectors**: The `EnvironmentInjector` vs `ElementInjector`, resolution rules, modifiers (`optional`, `skipSelf`), and `providers` vs `viewProviders`. Read [hierarchical-injectors.md](references/hierarchical-injectors.md)
+
+## Angular Aria
+
+When building accessible custom components for any of the following patterns: Accordion, Listbox, Combobox, Menu, Tabs, Toolbar, Tree, Grid, consult the following reference:
+
+- **Angular Aria Components**: Building headless, accessible components (Accordion, Listbox, Combobox, Menu, Tabs, Toolbar, Tree, Grid) and styling ARIA attributes. Read [angular-aria.md](references/angular-aria.md)
+
+## Routing
+
+When implementing navigation in Angular, consult the following references:
+
+- **Define Routes**: URL paths, static vs dynamic segments, wildcards, and redirects. Read [define-routes.md](references/define-routes.md)
+- **Route Loading Strategies**: Eager vs lazy loading, and context-aware loading. Read [loading-strategies.md](references/loading-strategies.md)
+- **Show Routes with Outlets**: Using `<router-outlet>`, nested outlets, and named outlets. Read [show-routes-with-outlets.md](references/show-routes-with-outlets.md)
+- **Navigate to Routes**: Declarative navigation with `RouterLink` and programmatic navigation with `Router`. Read [navigate-to-routes.md](references/navigate-to-routes.md)
+- **Control Route Access with Guards**: Implementing `CanActivate`, `CanMatch`, and other guards for security. Read [route-guards.md](references/route-guards.md)
+- **Data Resolvers**: Pre-fetching data before route activation with `ResolveFn`. Read [data-resolvers.md](references/data-resolvers.md)
+- **Router Lifecycle and Events**: Chronological order of navigation events and debugging. Read [router-lifecycle.md](references/router-lifecycle.md)
+- **Rendering Strategies**: CSR, SSG (Prerendering), and SSR with hydration. Read [rendering-strategies.md](references/rendering-strategies.md)
+- **Route Transition Animations**: Enabling and customizing the View Transitions API. Read [route-animations.md](references/route-animations.md)
+
+If you require deeper documentation or more context, visit the [official Angular Routing guide](https://angular.dev/guide/routing).
+
+## Styling and Animations
+
+When implementing styling and animations in Angular, consult the following references:
+
+- **Using Tailwind CSS with Angular**: Integrating Tailwind CSS into Angular projects. Read [tailwind-css.md](references/tailwind-css.md)
+- **Angular Animations**: Using native CSS (recommended) or the legacy DSL for dynamic effects. Read [angular-animations.md](references/angular-animations.md)
+- **Styling components**: Best practices for component styles and encapsulation. Read [component-styling.md](references/component-styling.md)
+
+## Testing
+
+When writing or updating tests, consult the following references based on the task:
+
+- **Fundamentals**: Best practices for unit testing, async patterns, and `TestBed`. Read [testing-fundamentals.md](references/testing-fundamentals.md)
+- **Component Harnesses**: Standard patterns for robust component interaction. Read [component-harnesses.md](references/component-harnesses.md)
+- **Router Testing**: Using `RouterTestingHarness` for reliable navigation tests. Read [router-testing.md](references/router-testing.md)
+- **End-to-End (E2E) Testing**: Best practices for E2E tests with Cypress or Playwright. Read [e2e-testing.md](references/e2e-testing.md)
+
+## Tooling
+
+When working with Angular tooling, consult the following references:
+
+- **Angular CLI**: Creating applications, generating code (components, routes, services), serving, and building. Read [cli.md](references/cli.md)
+- **Angular MCP Server**: Available tools, configuration, and experimental features. Read [mcp.md](references/mcp.md)
+
+## Anti-Patterns
+
+- Using `null` or `undefined` as initial signal form field values — use `''`, `0`, or `[]` instead
+- Accessing form field state flags without calling the field first: `form.field.valid()` — use `form.field().valid()`
+- Starting new forms with older form APIs when the target Angular version supports Signal Forms
+- Setting `min`, `max`, `value`, `disabled`, or `readonly` HTML attributes on `[formField]` inputs — define these as schema rules instead
+- Calling `inject()` outside an injection context — use `runInInjectionContext` when needed
+- Using `effect()` for derived state that should use `computed()`
+- Referencing `$parent.$index` in nested `@for` loops — Angular does not support `$parent`; use `let outerIdx = $index` instead
+
+## Related Skills
+
+- `tdd-workflow` — test-driven development workflow applicable to Angular components and services
+- `security-review` — security checklist for web applications including Angular-specific concerns
+- `frontend-patterns` — general frontend patterns for context on React/Next.js approaches