Add unique identifier for test_phase3c_walk_recovery.gd

.backup/skills/bugfix/SKILL.md

@@ -0,0 +1,27 @@
+---
+name: bugfix
+description: "Executes a bugfix pipeline on one or more gitea issues: Developer -> Tester -> Reviewer"
+---
+
+## What I do
+
+I orchestrate a sequential bugfix and verification pipeline - I will retrieve issues(s) from Gitea (title, body, images, comments, etc...). I will then forward information from the issues to the respective subagents.
+
+Use gitea-mcp-server to interact with Gitea. Verify that the server is running and accessible.
+
+If an issue is not provided, ask the user for the issue number(s).
+
+1. **Developer**: Provides a code fix for each issue.
+2. **Reviewer**: Audits the code and architectural soundness.
+3. **Tester**: Runs tests related to the bugfix and determines if new unit tests, integration tests, or end-to-end tests are needed. If so, implement. Verify by running the test suite.
+
+## Execution Rules
+
+- Stop and ask the user for clarification if a step fails or is ambiguous.
+- Use the `@` mention to trigger the respective subagents sequentially.
+- Pass the context from the previous stage to the next stage to ensure consistency.
+- Use multiple subagents to handle different aspects of the bugfix process if it will help.
+
+## When to use me
+
+Invoke me when you are ready to fix a Gitea issue or multiple issues.

.backup/skills/e2e-repair/SKILL.md

@@ -0,0 +1,22 @@
+---
+name: e2e-repair
+description: "Runs playwright tests, captures errors, and triggers auto-repair."
+---
+
+## Logic
+
+1. Execute: `npx playwright test [test_file]`
+2. If Success:
+   - Report success.
+   - Exit.
+3. If Failure:
+   - Capture output.
+   - Pass logs to @tester agent.
+   - @tester analyzes error and edits file.
+   - Repeat until success or max_retries reached.
+
+## Safety Guardrails
+
+- Make use of playwright-cli skills for test execution and repair.
+- Max Retries: 3 per file.
+- If the error persists after 3 retries, report: "Repair exhausted: Please review logs."

.backup/skills/feature-pipeline/SKILL.md

@@ -0,0 +1,23 @@
+---
+name: feature-pipeline
+description: "Executes the full dev-to-docs pipeline: Developer -> Tester -> Reviewer -> Writer."
+---
+
+## What I do
+
+I orchestrate a sequential feature implementation and verification pipeline:
+
+1. **Developer**: Implements the feature based on the spec.
+2. **Reviewer**: Audits the code and architectural soundness.
+3. **Tester**: Runs full unit/E2E test suites; repairs failures if found.
+4. **Writer**: Updates README and API docs based on verified code.
+
+## Execution Rules
+
+- Stop and ask the user for clarification if a step fails or is ambiguous.
+- Use the `@` mention to trigger the respective subagents sequentially.
+- Pass the context from the previous stage to the next stage to ensure consistency.
+
+## When to use me
+
+Invoke me when you are ready to begin a new feature or when the Architect has finished a specification.

.backup/skills/fix-pipeline/SKILL.md

@@ -0,0 +1,22 @@
+---
+name: fix-pipeline
+description: "Diagnoses, fixes, and verifies bugs across Architect, Developer, Tester, and Writer."
+---
+
+## What I do
+
+I resolve bugs by triaging ownership, applying code fixes, and running regression tests:
+
+1. **Architect (Triage)**: Compares the bug report against existing `specs/` and codebase architecture.
+   - **Spec / Design Defect**: Updates `specs/` and `decisions.md`, then forwards to `@developer`.
+   - **Implementation Defect**: Forwards directly to `@developer` without updating specs.
+2. **Developer**: Applies surgical code fixes adhering to Godot performance and typing rules.
+3. **Tester**: Writes a GUT regression test, executes test suites, and verifies the fix (max 2 repair attempts).
+4. **Writer** (Conditional): Updates README or API docs if external interfaces or setup instructions changed.
+
+## Execution Rules
+
+- Default to starting at Step 1 (`@architect`) for triage unless explicitly told `--dev-only`.
+- Allow `@tester` a maximum of 2 auto-repair attempts for failing test suites before passing back to `@developer`.
+- Stop and ask the user for clarification if any step fails or is ambiguous.
+- Pass context from each completed stage to the next stage.

.backup/skills/spec-pipeline/SKILL.md

@@ -0,0 +1,25 @@
+---
+name: spec-pipeline
+description: "Executes the full dev-to-docs pipeline: Developer -> Tester -> Writer."
+---
+
+## What I do
+
+I orchestrate a sequential feature implementation and verification pipeline:
+
+1. **Architect**: Explores codebase, asks clarifying questions, and drafts the spec. *Waits for user approval before handoff.*
+2. **Developer**: Implements the feature based on the spec.
+3. **Tester**: Runs full unit test suites; repairs failures if found.
+4. **Writer**: After updating README and API docs, review `docs/tech_debt_and_optimizations.md` for formatting consistency and ensure no duplicate entries exist.
+
+## Execution Rules
+
+- **Architect Gate**: Stop after Phase 3 and wait for user approval on the spec before calling `@developer`.
+- **Tester Repair Limit**: Allow `@tester` a maximum of 2 auto-repair attempts for failing test suites. If tests still fail after 2 attempts, hand the error context back to `@developer` to fix the underlying implementation.
+- Stop and ask the user for clarification if any step fails or is ambiguous.
+- Use `@` mentions to trigger subagents sequentially.
+- Pass context from each completed stage to the next stage.
+
+## When to use me
+
+Invoke me when you are ready to begin a new feature/fix or when the Architect has finished a specification.