@winspan/claude-forge 9.2.0 → 9.12.0

package/dist/skills/distilled/distilled-test-driven-development.md

@@ -0,0 +1,432 @@
+---
+name: distilled-test-driven-development
+version: 0.2.0-distilled
+description: 'Distilled IT-universal skill: test-driven-development (score 3.5/5)'
+keywords:
+  - test
+  - driven
+  - development
+rubric_version: 2
+distilled_from:
+  - upstream: https://github.com/obra/superpowers.git
+    license: MIT
+    commit: f2cbfbefebbfef77321e4c9abc9e949826bea9d7
+    paths:
+      - test-driven-development/SKILL.md
+  - upstream: https://github.com/anthropics/skills.git
+    license: Apache-2.0
+    commit: 690f15cac7f7b4c055c5ab109c79ed9259934081
+    paths:
+      - webapp-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - ai-regression-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - cpp-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - csharp-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - django-tdd/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - e2e-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - fsharp-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - golang-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - kotlin-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - laravel-tdd/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - perl-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - python-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - quarkus-tdd/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - rust-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - springboot-tdd/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - swift-protocol-di-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - tdd-workflow/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - golang-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - tdd-workflow/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - e2e-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - golang-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - kotlin-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - laravel-tdd/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - python-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - quarkus-tdd/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - rust-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - springboot-tdd/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - tdd-workflow/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - ai-regression-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - cpp-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - csharp-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - django-tdd/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - e2e-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - golang-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - kotlin-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - laravel-tdd/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - perl-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - python-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - rust-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - springboot-tdd/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - swift-protocol-di-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - tdd-workflow/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - golang-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - tdd-workflow/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - ai-regression-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - cpp-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - csharp-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - django-tdd/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - e2e-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - fsharp-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - golang-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - kotlin-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - laravel-tdd/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - perl-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - python-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - quarkus-tdd/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - rust-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - springboot-tdd/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - swift-protocol-di-testing/SKILL.md
+  - upstream: https://github.com/affaan-m/ECC.git
+    license: MIT
+    commit: 928076cc08cbb31e8549cea2883b4f51811de1c8
+    paths:
+      - tdd-workflow/SKILL.md
+distilled_at: '2026-06-15T00:56:21.265Z'
+distilled_by: claude-code skill-distiller agent
+it_universal_score: 3.5
+it_universal_dims:
+  d1: 0.5
+  d2: 0.5
+  d3: 0.5
+  d4: 1
+  d5: 1
+it_universal_rationale: >-
+  Red-Green-Refactor cycle, Iron Law, and anti-pattern taxonomy are fully language- and
+  tool-agnostic; only illustrative code samples and test-runner invocations are
+  TypeScript/npm-specific and trivially substitutable in any codebase.
+---
+
+# Test-Driven Development (TDD)
+
+## When to use
+- Implementing any new feature or behavior
+- Fixing a bug (write a failing test that reproduces it *before* touching production code)
+- Refactoring existing code (existing tests must stay green throughout)
+- Any behavior change where correctness needs to be verifiable and regression-safe
+
+**Exceptions (require explicit partner approval):** throwaway prototypes, generated/scaffolded code, configuration-only files.
+
+## Core idea
+Write the test first, watch it fail, then write the minimal production code to make it pass — no more, no less. If you never saw the test fail, you cannot know it tests the right thing. Tests written *after* passing code answer "what does this do?"; tests written *before* answer "what *should* this do?" and force edge-case discovery before implementation biases your thinking. The **Red → Green → Refactor** loop is the atomic unit of work: one failing test → minimal code to pass → clean up → repeat. Writing code first "just to explore" is test-after in disguise; the remedy is to delete the pre-written code and start over with a test.
+
+## Steps
+
+### 1. RED — Write One Failing Test
+Describe the exact behavior you want in a single test:
+- **One behavior per test** — if "and" appears in the name, split it into two tests
+- **Descriptive name** — the test name should state the expected outcome, not the mechanism
+- **Prefer real code over mocks** — use test doubles only when external I/O is unavoidable
+
+### 2. Verify RED — Watch It Fail *(mandatory, never skip)*
+Run this test in isolation with your project's test runner. Confirm:
+- The test **fails** (not errors on syntax/import)
+- The failure message matches what you expect ("feature missing", not "undefined is not a function")
+- It fails because the feature is absent, not due to a typo in the test itself
+
+If the test **passes immediately** → you are testing already-existing behavior; fix or delete the test.  
+If the test **errors** → fix the error and re-run until it fails cleanly for the right reason.
+
+### 3. GREEN — Write Minimal Code to Pass
+Write the simplest production code that makes the failing test pass:
+- Do not add untested features (YAGNI)
+- Do not refactor other code in the same commit
+- Do not "improve" anything beyond what the single test requires
+
+### 4. Verify GREEN — Watch It Pass *(mandatory)*
+Run your full test suite. Confirm:
+- The new test passes
+- All pre-existing tests still pass
+- Output is clean (no new warnings or errors introduced)
+
+If other tests break → fix them **now**, before proceeding.
+
+### 5. REFACTOR — Clean Up (tests still green)
+With all tests passing, improve the code's internal quality:
+- Remove duplication
+- Improve naming and readability
+- Extract helpers or shared abstractions
+
+Never add new behavior in this phase. Re-run the full suite after every refactor step.
+
+### 6. Repeat
+Write the next failing test for the next unit of behavior and cycle again.
+
+## Iron Law
+
+```
+NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST
+```
+
+Wrote code before a test? **Delete it. Start fresh.** No "keep as reference", no "adapting" it while writing the test — that is still test-after. Delete means delete.
+
+## Anti-patterns
+
+| Rationalization | Reality |
+|---|---|
+| "Too simple to test" | Simple code breaks too. A focused test takes under a minute. |
+| "I'll add tests after" | Tests that pass immediately on first run prove nothing was verified. |
+| "Already manually tested all edge cases" | Ad-hoc testing has no record and cannot be re-run; automated tests are systematic. |
+| "Deleting X hours of work is wasteful" | Sunk-cost fallacy. Unverified production code is technical debt compounding interest. |
+| "I'll keep it as reference and write tests first" | You will adapt it. That is test-after. Delete it. |
+| "TDD is dogmatic; I'm being pragmatic" | Catching bugs before commit is faster than debugging in production. Test-first *is* pragmatic. |
+| "Tests-after achieve the same goals" | They answer different questions — see Core idea. |
+| "This case is different because…" | It isn't. All of these mean: delete the code, start over. |
+
+**Red flags — stop and restart the TDD cycle from scratch:**
+- You wrote production code before any test
+- The test passed immediately without any implementation
+- You cannot articulate why the test failed
+- You find yourself composing a "just this once" justification
+
+## Verification Checklist (before marking any work complete)
+- [ ] Every new function/method has a test written before its implementation
+- [ ] Each test was observed to fail for the expected reason
+- [ ] Only minimal code was written to pass each test
+- [ ] All tests pass with a clean runner output (no new warnings)
+- [ ] Edge cases and error paths are covered by dedicated tests
+- [ ] Mocks/stubs are used only where real I/O is genuinely unavoidable
+
+## When Stuck
+
+| Problem | Solution |
+|---|---|
+| Don't know how to write the test | Write the API you *wish* existed; start with the assertion, work backwards |
+| Test is overly complicated | Your design is too complicated — simplify the interface first |
+| Must mock everything to test anything | Code is too coupled; introduce dependency injection |
+| Test setup is enormous | Extract shared helpers; if still complex, the design needs simplification |
+| Bug found in existing untested code | Write a failing test reproducing the bug, then follow the TDD cycle to fix it |
+
+## References
+- Upstream: https://github.com/obra/superpowers.git

package/dist/skills/distilled/distilled-using-superpowers.md

@@ -0,0 +1,134 @@
+---
+name: distilled-using-superpowers
+version: 0.2.0-distilled
+description: 'Distilled IT-universal skill: using-superpowers (score 4.5/5)'
+keywords:
+  - using
+  - superpowers
+rubric_version: 2
+distilled_from:
+  - upstream: https://github.com/obra/superpowers.git
+    license: MIT
+    commit: f2cbfbefebbfef77321e4c9abc9e949826bea9d7
+    paths:
+      - using-superpowers/SKILL.md
+distilled_at: '2026-06-15T00:58:31.504Z'
+distilled_by: claude-code skill-distiller agent
+it_universal_score: 4.5
+it_universal_dims:
+  d1: 1
+  d2: 0.5
+  d3: 1
+  d4: 1
+  d5: 1
+it_universal_rationale: >-
+  Language-neutral meta-methodology for AI assistant skill invocation; platform-adaptive with no
+  repo-specific paths or project terminology; strong transferable decision flowchart and heuristics.
+---
+
+# Skill-First Workflow: Invoke Relevant Skills Before Any Action
+
+## When to use
+- At the start of **any** conversation or task in an AI assistant (Claude Code, Copilot CLI, Gemini CLI, etc.)
+- Before exploring a codebase, answering a question, or asking a clarifying question
+- Whenever you are about to enter plan mode or take any substantive action
+- When multiple skills might apply and you need to pick the right order
+
+## Core idea
+
+The fundamental discipline is: **check for and invoke relevant skills *before* taking any action — including before asking clarifying questions**. Even a 1% probability that a skill applies is enough to trigger an invocation. Skills describe *how* to approach a task; without checking them first, you may gather information, explore, or plan in a suboptimal or incorrect way. User instructions (project config files, direct requests) always take the highest precedence over skills, which in turn override default system behavior. When you invoke a skill and it turns out to be inapplicable to the situation, you are free to disregard it — but you must check first.
+
+## Steps
+
+1. **Receive user message or prepare to enter plan mode.**
+
+2. **Ask: "Might any skill apply — even with 1% probability?"**
+   - Yes → proceed to step 3.
+   - Definitely not → respond directly.
+
+3. **Invoke the Skill tool** (platform-specific name varies; see Platform notes below).
+   - Announce: *"Using [skill name] to [brief purpose]."*
+
+4. **Apply skill priority order** when multiple skills could apply:
+   - **Process skills first** (brainstorming, debugging, planning) — they determine *how* to approach the task.
+   - **Implementation skills second** (patterns, code generation, domain-specific guides) — they guide execution.
+   - Example: "Let's build X" → brainstorming skill first, then implementation skill.
+   - Example: "Fix this bug" → debugging skill first, then domain-specific skill.
+
+5. **If the invoked skill contains a checklist**, create a to-do item per checklist entry before proceeding.
+
+6. **Follow the skill exactly** (rigid skills) or adapt its principles to context (flexible skills). The skill itself declares which type it is.
+
+7. **Proceed with the task**, informed by the skill's guidance.
+
+## Skill types
+
+| Type | Examples | How to follow |
+|---|---|---|
+| **Rigid** | TDD, debugging protocols | Follow exactly; do not adapt away the discipline |
+| **Flexible** | Design patterns, code style | Adapt principles to context |
+
+The skill document itself tells you which type it is.
+
+## Platform notes
+
+| Platform | Tool name to invoke |
+|---|---|
+| Claude Code | `Skill` tool |
+| Copilot CLI | `skill` tool |
+| Gemini CLI | `activate_skill` tool |
+
+Never use a file-read tool to load skill content — always use the platform's designated skill tool so that the correct version is loaded.
+
+## Instruction precedence
+
+1. **User's explicit instructions** (CLAUDE.md, AGENTS.md, GEMINI.md, direct requests) — highest priority
+2. **Invoked skills** — override default system behavior
+3. **Default system prompt** — lowest priority
+
+If a user config file says "don't do X" and a skill says "always do X," follow the user's config.
+
+## Anti-patterns
+
+- **"This is just a simple question."** → Questions are tasks. Check for skills before answering.
+- **"I need more context first."** → Skill check comes *before* clarifying questions.
+- **"Let me explore the codebase first."** → Skills tell you *how* to explore. Check first.
+- **"I remember this skill from before."** → Skills evolve. Always read the current version via the tool.
+- **"This skill seems like overkill."** → Simple tasks become complex. Invoke and decide afterward.
+- **"I'll just do this one quick thing first."** → Check *before* doing anything.
+- **"I know what that skill says."** → Knowing the concept ≠ using the skill. Invoke it.
+- **"This doesn't count as a real task."** → Any action = task. Check for skills.
+
+## Decision flowchart (text form)
+
+```
+User message received
+        │
+        ▼
+Might any skill apply? (even 1%)
+   │              │
+  Yes             No
+   │              └──► Respond directly
+   ▼
+Invoke Skill tool
+        │
+        ▼
+Announce: "Using [skill] to [purpose]"
+        │
+        ▼
+Skill has a checklist?
+   │              │
+  Yes             No
+   │              └──► Follow skill exactly
+   ▼
+Create one todo per checklist item
+        │
+        ▼
+Follow skill exactly
+        │
+        ▼
+Respond / act
+```
+
+## References
+- Upstream: https://github.com/obra/superpowers.git