winter-super-cli 2026.5.31 → 2026.6.5

package/resources/local/ecc/docs/ja-JP/skills/fsharp-testing/SKILL.md

@@ -0,0 +1,280 @@
+---
+name: fsharp-testing
+description: F#テストフレームワーク、プロパティベーステスト、および関数型アプローチ。
+origin: ECC
+---
+
+# F# Testing Patterns
+
+Comprehensive testing patterns for F# applications using xUnit, FsUnit, Unquote, FsCheck, and modern .NET testing practices.
+
+## When to Activate
+
+- Writing new tests for F# code
+- Reviewing test quality and coverage
+- Setting up test infrastructure for F# projects
+- Debugging flaky or slow tests
+
+## Test Framework Stack
+
+| Tool | Purpose |
+|---|---|
+| **xUnit** | Test framework (standard .NET ecosystem choice) |
+| **FsUnit.xUnit** | F#-friendly assertion syntax for xUnit |
+| **Unquote** | Assertion library using F# quotations for clear failure messages |
+| **FsCheck.xUnit** | Property-based testing integrated with xUnit |
+| **NSubstitute** | Mocking .NET dependencies |
+| **Testcontainers** | Real infrastructure in integration tests |
+| **WebApplicationFactory** | ASP.NET Core integration tests |
+
+## Unit Tests with xUnit + FsUnit
+
+### Basic Test Structure
+
+```fsharp
+module OrderServiceTests
+
+open Xunit
+open FsUnit.Xunit
+
+[<Fact>]
+let ``create sets status to Pending`` () =
+    let order = Order.create "cust-1" [ validItem ]
+    order.Status |> should equal Pending
+
+[<Fact>]
+let ``confirm changes status to Confirmed`` () =
+    let order = Order.create "cust-1" [ validItem ]
+    let confirmed = Order.confirm order
+    confirmed.Status |> should be (ofCase <@ Confirmed @>)
+```
+
+### Assertions with Unquote
+
+Unquote uses F# quotations so failure messages show the full expression that failed, not just "expected X got Y".
+
+```fsharp
+module OrderValidationTests
+
+open Xunit
+open Swensen.Unquote
+
+[<Fact>]
+let ``PlaceOrder returns success when request is valid`` () =
+    let request = { CustomerId = "cust-123"; Items = [ validItem ] }
+    let result = OrderService.placeOrder request
+    test <@ Result.isOk result @>
+
+[<Fact>]
+let ``order total sums item prices`` () =
+    let items = [ { Sku = "A"; Quantity = 2; Price = 10m }
+                  { Sku = "B"; Quantity = 1; Price = 5m } ]
+    let total = Order.calculateTotal items
+    test <@ total = 25m @>
+
+[<Fact>]
+let ``validated email rejects empty input`` () =
+    let result = ValidatedEmail.create ""
+    test <@ Result.isError result @>
+```
+
+### Async Tests
+
+```fsharp
+[<Fact>]
+let ``PlaceOrder returns success when request is valid`` () = task {
+    let deps = createTestDeps ()
+    let request = { CustomerId = "cust-123"; Items = [ validItem ] }
+
+    let! result = OrderService.placeOrder deps request
+
+    test <@ Result.isOk result @>
+}
+
+[<Fact>]
+let ``PlaceOrder returns error when items are empty`` () = task {
+    let deps = createTestDeps ()
+    let request = { CustomerId = "cust-123"; Items = [] }
+
+    let! result = OrderService.placeOrder deps request
+
+    test <@ Result.isError result @>
+}
+```
+
+### Parameterized Tests with Theory
+
+```fsharp
+[<Theory>]
+[<InlineData("")>]
+[<InlineData("   ")>]
+let ``PlaceOrder rejects empty customer ID`` (customerId: string) =
+    let request = { CustomerId = customerId; Items = [ validItem ] }
+    let result = OrderService.placeOrder request
+    result |> should be (ofCase <@ Error @>)
+
+[<Theory>]
+[<InlineData("", false)>]
+[<InlineData("a", false)>]
+[<InlineData("user@example.com", true)>]
+[<InlineData("user+tag@example.co.uk", true)>]
+let ``IsValidEmail returns expected result`` (email: string, expected: bool) =
+    test <@ EmailValidator.isValid email = expected @>
+```
+
+## Property-Based Testing with FsCheck
+
+### Using FsCheck.xUnit
+
+```fsharp
+open FsCheck
+open FsCheck.Xunit
+
+[<Property>]
+let ``order total is always non-negative`` (items: NonEmptyList<PositiveInt * decimal>) =
+    let orderItems =
+        items.Get
+        |> List.map (fun (qty, price) ->
+            { Sku = "SKU"; Quantity = qty.Get; Price = abs price })
+    let total = Order.calculateTotal orderItems
+    total >= 0m
+
+[<Property>]
+let ``serialization roundtrips`` (order: Order) =
+    let json = JsonSerializer.Serialize order
+    let deserialized = JsonSerializer.Deserialize<Order> json
+    deserialized = order
+```
+
+### Custom Generators
+
+```fsharp
+type OrderGenerators =
+    static member ValidEmail () =
+        gen {
+            let! user = Gen.elements [ "alice"; "bob"; "carol" ]
+            let! domain = Gen.elements [ "example.com"; "test.org" ]
+            return $"{user}@{domain}"
+        }
+        |> Arb.fromGen
+
+[<Property(Arbitrary = [| typeof<OrderGenerators> |])>]
+let ``valid emails pass validation`` (email: string) =
+    EmailValidator.isValid email
+```
+
+## Mocking Dependencies
+
+### Function Stubs (Preferred)
+
+```fsharp
+let createTestDeps () =
+    let mutable savedOrders = []
+    { FindOrder = fun id -> task { return Map.tryFind id testData }
+      SaveOrder = fun order -> task { savedOrders <- order :: savedOrders }
+      SendNotification = fun _ -> Task.CompletedTask }
+
+[<Fact>]
+let ``PlaceOrder saves the confirmed order`` () = task {
+    let mutable saved = []
+    let deps =
+        { createTestDeps () with
+            SaveOrder = fun order -> task { saved <- order :: saved } }
+
+    let! _ = OrderService.placeOrder deps validRequest
+
+    test <@ saved.Length = 1 @>
+}
+```
+
+### NSubstitute for .NET Interfaces
+
+```fsharp
+open NSubstitute
+
+[<Fact>]
+let ``calls repository with correct ID`` () = task {
+    let repo = Substitute.For<IOrderRepository>()
+    repo.FindByIdAsync(Arg.Any<Guid>(), Arg.Any<CancellationToken>())
+        .Returns(Task.FromResult(Some testOrder))
+
+    let service = OrderService(repo)
+    let! _ = service.GetOrder(testOrder.Id, CancellationToken.None)
+
+    do! repo.Received(1).FindByIdAsync(testOrder.Id, Arg.Any<CancellationToken>())
+}
+```
+
+## ASP.NET Core Integration Tests
+
+```fsharp
+type OrderApiTests (factory: WebApplicationFactory<Program>) =
+    interface IClassFixture<WebApplicationFactory<Program>>
+
+    let client =
+        factory.WithWebHostBuilder(fun builder ->
+            builder.ConfigureServices(fun services ->
+                services.RemoveAll<DbContextOptions<AppDbContext>>() |> ignore
+                services.AddDbContext<AppDbContext>(fun options ->
+                    options.UseInMemoryDatabase("TestDb") |> ignore) |> ignore))
+            .CreateClient()
+
+    [<Fact>]
+    member _.``GET order returns 404 when not found`` () = task {
+        let! response = client.GetAsync($"/api/orders/{Guid.NewGuid()}")
+        test <@ response.StatusCode = HttpStatusCode.NotFound @>
+    }
+```
+
+## Test Organization
+
+```
+tests/
+  MyApp.Tests/
+    Unit/
+      OrderServiceTests.fs
+      PaymentServiceTests.fs
+    Integration/
+      OrderApiTests.fs
+      OrderRepositoryTests.fs
+    Properties/
+      OrderPropertyTests.fs
+    Helpers/
+      TestData.fs
+      TestDeps.fs
+```
+
+## Common Anti-Patterns
+
+| Anti-Pattern | Fix |
+|---|---|
+| Testing implementation details | Test behavior and outcomes |
+| Mutable shared test state | Fresh state per test |
+| `Thread.Sleep` in async tests | Use `Task.Delay` with timeout, or polling helpers |
+| Asserting on `sprintf` output | Assert on typed values and pattern matches |
+| Ignoring `CancellationToken` | Always pass and verify cancellation |
+| Skipping property-based tests | Use FsCheck for any function with clear invariants |
+
+## Related Skills
+
+- `dotnet-patterns` - Idiomatic .NET patterns, dependency injection, and architecture
+- `csharp-testing` - C# testing patterns (shared infrastructure like WebApplicationFactory and Testcontainers applies to F# too)
+
+## Running Tests
+
+```bash
+# Run all tests
+dotnet test
+
+# Run with coverage
+dotnet test --collect:"XPlat Code Coverage"
+
+# Run specific project
+dotnet test tests/MyApp.Tests/
+
+# Filter by test name
+dotnet test --filter "FullyQualifiedName~OrderService"
+
+# Watch mode during development
+dotnet watch test --project tests/MyApp.Tests/
+```

package/resources/local/ecc/docs/ja-JP/skills/gan-style-harness/SKILL.md

@@ -0,0 +1,278 @@
+---
+name: gan-style-harness
+description: GAN（生成的敵対ネットワーク）スタイルの評価ハーネス、画像生成パターン、および品質メトリクス。
+origin: ECC-community
+tools: Read, Write, Edit, Bash, Grep, Glob, Task
+---
+
+# GAN-Style Harness Skill
+
+> Inspired by [Anthropic's Harness Design for Long-Running Application Development](https://www.anthropic.com/engineering/harness-design-long-running-apps) (March 24, 2026)
+
+A multi-agent harness that separates **generation** from **evaluation**, creating an adversarial feedback loop that drives quality far beyond what a single agent can achieve.
+
+## Core Insight
+
+> When asked to evaluate their own work, agents are pathological optimists — they praise mediocre output and talk themselves out of legitimate issues. But engineering a **separate evaluator** to be ruthlessly strict is far more tractable than teaching a generator to self-critique.
+
+This is the same dynamic as GANs (Generative Adversarial Networks): the Generator produces, the Evaluator critiques, and that feedback drives the next iteration.
+
+## When to Use
+
+- Building complete applications from a one-line prompt
+- Frontend design tasks requiring high visual quality
+- Full-stack projects that need working features, not just code
+- Any task where "AI slop" aesthetics are unacceptable
+- Projects where you want to invest $50-200 for production-quality output
+
+## When NOT to Use
+
+- Quick single-file fixes (use standard `claude -p`)
+- Tasks with tight budget constraints (<$10)
+- Simple refactoring (use de-sloppify pattern instead)
+- Tasks that are already well-specified with tests (use TDD workflow)
+
+## Architecture
+
+```
+                    ┌─────────────┐
+                    │   PLANNER   │
+                    │  (Opus 4.6) │
+                    └──────┬──────┘
+                           │ Product Spec
+                           │ (features, sprints, design direction)
+                           ▼
+              ┌────────────────────────┐
+              │                        │
+              │   GENERATOR-EVALUATOR  │
+              │      FEEDBACK LOOP     │
+              │                        │
+              │  ┌──────────┐          │
+              │  │GENERATOR │--build-->│──┐
+              │  │(Opus 4.6)│          │  │
+              │  └────▲─────┘          │  │
+              │       │                │  │ live app
+              │    feedback             │  │
+              │       │                │  │
+              │  ┌────┴─────┐          │  │
+              │  │EVALUATOR │<-test----│──┘
+              │  │(Opus 4.6)│          │
+              │  │+Playwright│         │
+              │  └──────────┘          │
+              │                        │
+              │   5-15 iterations      │
+              └────────────────────────┘
+```
+
+## The Three Agents
+
+### 1. Planner Agent
+
+**Role:** Product manager — expands a brief prompt into a full product specification.
+
+**Key behaviors:**
+- Takes a one-line prompt and produces a 16-feature, multi-sprint specification
+- Defines user stories, technical requirements, and visual design direction
+- Is deliberately **ambitious** — conservative planning leads to underwhelming results
+- Produces evaluation criteria that the Evaluator will use later
+
+**Model:** Opus 4.6 (needs deep reasoning for spec expansion)
+
+### 2. Generator Agent
+
+**Role:** Developer — implements features according to the spec.
+
+**Key behaviors:**
+- Works in structured sprints (or continuous mode with newer models)
+- Negotiates a "sprint contract" with the Evaluator before writing code
+- Uses full-stack tooling: React, FastAPI/Express, databases, CSS
+- Manages git for version control between iterations
+- Reads Evaluator feedback and incorporates it in next iteration
+
+**Model:** Opus 4.6 (needs strong coding capability)
+
+### 3. Evaluator Agent
+
+**Role:** QA engineer — tests the live running application, not just code.
+
+**Key behaviors:**
+- Uses **Playwright MCP** to interact with the live application
+- Clicks through features, fills forms, tests API endpoints
+- Scores against four criteria (configurable):
+  1. **Design Quality** — Does it feel like a coherent whole?
+  2. **Originality** — Custom decisions vs. template/AI patterns?
+  3. **Craft** — Typography, spacing, animations, micro-interactions?
+  4. **Functionality** — Do all features actually work?
+- Returns structured feedback with scores and specific issues
+- Is engineered to be **ruthlessly strict** — never praises mediocre work
+
+**Model:** Opus 4.6 (needs strong judgment + tool use)
+
+## Evaluation Criteria
+
+The default four criteria, each scored 1-10:
+
+```markdown
+## Evaluation Rubric
+
+### Design Quality (weight: 0.3)
+- 1-3: Generic, template-like, "AI slop" aesthetics
+- 4-6: Competent but unremarkable, follows conventions
+- 7-8: Distinctive, cohesive visual identity
+- 9-10: Could pass for a professional designer's work
+
+### Originality (weight: 0.2)
+- 1-3: Default colors, stock layouts, no personality
+- 4-6: Some custom choices, mostly standard patterns
+- 7-8: Clear creative vision, unique approach
+- 9-10: Surprising, delightful, genuinely novel
+
+### Craft (weight: 0.3)
+- 1-3: Broken layouts, missing states, no animations
+- 4-6: Works but feels rough, inconsistent spacing
+- 7-8: Polished, smooth transitions, responsive
+- 9-10: Pixel-perfect, delightful micro-interactions
+
+### Functionality (weight: 0.2)
+- 1-3: Core features broken or missing
+- 4-6: Happy path works, edge cases fail
+- 7-8: All features work, good error handling
+- 9-10: Bulletproof, handles every edge case
+```
+
+### Scoring
+
+- **Weighted score** = sum of (criterion_score * weight)
+- **Pass threshold** = 7.0 (configurable)
+- **Max iterations** = 15 (configurable, typically 5-15 sufficient)
+
+## Usage
+
+### Via Command
+
+```bash
+# Full three-agent harness
+/project:gan-build "Build a project management app with Kanban boards, team collaboration, and dark mode"
+
+# With custom config
+/project:gan-build "Build a recipe sharing platform" --max-iterations 10 --pass-threshold 7.5
+
+# Frontend design mode (generator + evaluator only, no planner)
+/project:gan-design "Create a landing page for a crypto portfolio tracker"
+```
+
+### Via Shell Script
+
+```bash
+# Basic usage
+./scripts/gan-harness.sh "Build a music streaming dashboard"
+
+# With options
+GAN_MAX_ITERATIONS=10 \
+GAN_PASS_THRESHOLD=7.5 \
+GAN_EVAL_CRITERIA="functionality,performance,security" \
+./scripts/gan-harness.sh "Build a REST API for task management"
+```
+
+### Via Claude Code (Manual)
+
+```bash
+# Step 1: Plan
+claude -p --model opus "You are a Product Planner. Read PLANNER_PROMPT.md. Expand this brief into a full product spec: 'Build a Kanban board app'. Write spec to spec.md"
+
+# Step 2: Generate (iteration 1)
+claude -p --model opus "You are a Generator. Read spec.md. Implement Sprint 1. Start the dev server on port 3000."
+
+# Step 3: Evaluate (iteration 1)
+claude -p --model opus --allowedTools "Read,Bash,mcp__playwright__*" "You are an Evaluator. Read EVALUATOR_PROMPT.md. Test the live app at http://localhost:3000. Score against the rubric. Write feedback to feedback-001.md"
+
+# Step 4: Generate (iteration 2 — reads feedback)
+claude -p --model opus "You are a Generator. Read spec.md and feedback-001.md. Address all issues. Improve the scores."
+
+# Repeat steps 3-4 until pass threshold met
+```
+
+## Evolution Across Model Capabilities
+
+The harness should simplify as models improve. Following Anthropic's evolution:
+
+### Stage 1 — Weaker Models (Sonnet-class)
+- Full sprint decomposition required
+- Context resets between sprints (avoid context anxiety)
+- 2-agent minimum: Initializer + Coding Agent
+- Heavy scaffolding compensates for model limitations
+
+### Stage 2 — Capable Models (Opus 4.5-class)
+- Full 3-agent harness: Planner + Generator + Evaluator
+- Sprint contracts before each implementation phase
+- 10-sprint decomposition for complex apps
+- Context resets still useful but less critical
+
+### Stage 3 — Frontier Models (Opus 4.6-class)
+- Simplified harness: single planning pass, continuous generation
+- Evaluation reduced to single end-pass (model is smarter)
+- No sprint structure needed
+- Automatic compaction handles context growth
+
+> **Key principle:** Every harness component encodes an assumption about what the model can't do alone. When models improve, re-test those assumptions. Strip away what's no longer needed.
+
+## Configuration
+
+### Environment Variables
+
+| Variable | Default | Description |
+|----------|---------|-------------|
+| `GAN_MAX_ITERATIONS` | `15` | Maximum generator-evaluator cycles |
+| `GAN_PASS_THRESHOLD` | `7.0` | Weighted score to pass (1-10) |
+| `GAN_PLANNER_MODEL` | `opus` | Model for planning agent |
+| `GAN_GENERATOR_MODEL` | `opus` | Model for generator agent |
+| `GAN_EVALUATOR_MODEL` | `opus` | Model for evaluator agent |
+| `GAN_EVAL_CRITERIA` | `design,originality,craft,functionality` | Comma-separated criteria |
+| `GAN_DEV_SERVER_PORT` | `3000` | Port for the live app |
+| `GAN_DEV_SERVER_CMD` | `npm run dev` | Command to start dev server |
+| `GAN_PROJECT_DIR` | `.` | Project working directory |
+| `GAN_SKIP_PLANNER` | `false` | Skip planner, use spec directly |
+| `GAN_EVAL_MODE` | `playwright` | `playwright`, `screenshot`, or `code-only` |
+
+### Evaluation Modes
+
+| Mode | Tools | Best For |
+|------|-------|----------|
+| `playwright` | Browser MCP + live interaction | Full-stack apps with UI |
+| `screenshot` | Screenshot + visual analysis | Static sites, design-only |
+| `code-only` | Tests + linting + build | APIs, libraries, CLI tools |
+
+## Anti-Patterns
+
+1. **Evaluator too lenient** — If the evaluator passes everything on iteration 1, your rubric is too generous. Tighten scoring criteria and add explicit penalties for common AI patterns.
+
+2. **Generator ignoring feedback** — Ensure feedback is passed as a file, not inline. The generator should read `feedback-NNN.md` at the start of each iteration.
+
+3. **Infinite loops** — Always set `GAN_MAX_ITERATIONS`. If the generator can't improve past a score plateau after 3 iterations, stop and flag for human review.
+
+4. **Evaluator testing superficially** — The evaluator must use Playwright to **interact** with the live app, not just screenshot it. Click buttons, fill forms, test error states.
+
+5. **Evaluator praising its own fixes** — Never let the evaluator suggest fixes and then evaluate those fixes. The evaluator only critiques; the generator fixes.
+
+6. **Context exhaustion** — For long sessions, use Claude Agent SDK's automatic compaction or reset context between major phases.
+
+## Results: What to Expect
+
+Based on Anthropic's published results:
+
+| Metric | Solo Agent | GAN Harness | Improvement |
+|--------|-----------|-------------|-------------|
+| Time | 20 min | 4-6 hours | 12-18x longer |
+| Cost | $9 | $125-200 | 14-22x more |
+| Quality | Barely functional | Production-ready | Phase change |
+| Core features | Broken | All working | N/A |
+| Design | Generic AI slop | Distinctive, polished | N/A |
+
+**The tradeoff is clear:** ~20x more time and cost for a qualitative leap in output quality. This is for projects where quality matters.
+
+## References
+
+- [Anthropic: Harness Design for Long-Running Apps](https://www.anthropic.com/engineering/harness-design-long-running-apps) — Original paper by Prithvi Rajasekaran
+- [Epsilla: The GAN-Style Agent Loop](https://www.epsilla.com/blogs/anthropic-harness-engineering-multi-agent-gan-architecture) — Architecture deconstruction
+- [Martin Fowler: Harness Engineering](https://martinfowler.com/articles/exploring-gen-ai/harness-engineering.html) — Broader industry context
+- [OpenAI: Harness Engineering](https://openai.com/index/harness-engineering/) — OpenAI's parallel work

package/resources/local/ecc/docs/ja-JP/skills/gateguard/SKILL.md

@@ -0,0 +1,125 @@
+---
+name: gateguard
+description: API、エージェント、およびLLMエンドポイントのアクセス制御と認可パターン。
+origin: community
+---
+
+# GateGuard — Fact-Forcing Pre-Action Gate
+
+A PreToolUse hook that forces Claude to investigate before editing. Instead of self-evaluation ("are you sure?"), it demands concrete facts. The act of investigation creates awareness that self-evaluation never did.
+
+## When to Activate
+
+- Working on any codebase where file edits affect multiple modules
+- Projects with data files that have specific schemas or date formats
+- Teams where AI-generated code must match existing patterns
+- Any workflow where Claude tends to guess instead of investigating
+
+## Core Concept
+
+LLM self-evaluation doesn't work. Ask "did you violate any policies?" and the answer is always "no." This is verified experimentally.
+
+But asking "list every file that imports this module" forces the LLM to run Grep and Read. The investigation itself creates context that changes the output.
+
+**Three-stage gate:**
+
+```
+1. DENY  — block the first Edit/Write/Bash attempt
+2. FORCE — tell the model exactly which facts to gather
+3. ALLOW — permit retry after facts are presented
+```
+
+No competitor does all three. Most stop at deny.
+
+## Evidence
+
+Two independent A/B tests, identical agents, same task:
+
+| Task | Gated | Ungated | Gap |
+| --- | --- | --- | --- |
+| Analytics module | 8.0/10 | 6.5/10 | +1.5 |
+| Webhook validator | 10.0/10 | 7.0/10 | +3.0 |
+| **Average** | **9.0** | **6.75** | **+2.25** |
+
+Both agents produce code that runs and passes tests. The difference is design depth.
+
+## Gate Types
+
+### Edit / MultiEdit Gate (first edit per file)
+
+MultiEdit is handled identically — each file in the batch is gated individually.
+
+```
+Before editing {file_path}, present these facts:
+
+1. List ALL files that import/require this file (use Grep)
+2. List the public functions/classes affected by this change
+3. If this file reads/writes data files, show field names, structure,
+   and date format (use redacted or synthetic values, not raw production data)
+4. Quote the user's current instruction verbatim
+```
+
+### Write Gate (first new file creation)
+
+```
+Before creating {file_path}, present these facts:
+
+1. Name the file(s) and line(s) that will call this new file
+2. Confirm no existing file serves the same purpose (use Glob)
+3. If this file reads/writes data files, show field names, structure,
+   and date format (use redacted or synthetic values, not raw production data)
+4. Quote the user's current instruction verbatim
+```
+
+### Destructive Bash Gate (every destructive command)
+
+Triggers on: `rm -rf`, `git reset --hard`, `git push --force`, `drop table`, etc.
+
+```
+1. List all files/data this command will modify or delete
+2. Write a one-line rollback procedure
+3. Quote the user's current instruction verbatim
+```
+
+### Routine Bash Gate (once per session)
+
+```
+1. The current user request in one sentence
+2. What this specific command verifies or produces
+```
+
+## Quick Start
+
+### Option A: Use the ECC hook (zero install)
+
+The hook at `scripts/hooks/gateguard-fact-force.js` is included in this plugin. Enable it via hooks.json.
+
+If GateGuard blocks setup or repair work, start the session with
+`ECC_GATEGUARD=off`. For hook-level control, keep using
+`ECC_DISABLED_HOOKS` with the GateGuard hook ID.
+
+### Option B: Full package with config
+
+```bash
+pip install gateguard-ai
+gateguard init
+```
+
+This adds `.gateguard.yml` for per-project configuration (custom messages, ignore paths, gate toggles).
+
+## Anti-Patterns
+
+- **Don't use self-evaluation instead.** "Are you sure?" always gets "yes." This is experimentally verified.
+- **Don't skip the data schema check.** Both A/B test agents assumed ISO-8601 dates when real data used `%Y/%m/%d %H:%M`. Checking data structure (with redacted values) prevents this entire class of bugs.
+- **Don't gate every single Bash command.** Routine bash gates once per session. Destructive bash gates every time. This balance avoids slowdown while catching real risks.
+
+## Best Practices
+
+- Let the gate fire naturally. Don't try to pre-answer the gate questions — the investigation itself is what improves quality.
+- Customize gate messages for your domain. If your project has specific conventions, add them to the gate prompts.
+- Use `.gateguard.yml` to ignore paths like `.venv/`, `node_modules/`, `.git/`.
+
+## Related Skills
+
+- `safety-guard` — Runtime safety checks (complementary, not overlapping)
+- `code-reviewer` — Post-edit review (GateGuard is pre-edit investigation)