Skip to content

sickn33/agentic-awesome-skills / plugins/agentic-awesome-skills-claude/skills/agents-generator

agents-generator

Verified

Generate project-specific AGENTS.md and companion rules by analyzing a codebase. Supports full, minimal, update, and dry-run modes with package-manager detection, monorepos, backups, managed blocks, confidence scoring, and command validation.

FileKindSize
SKILL.mdskill md9.7 KB
assets/agents-full.mdmarkdown11.8 KB
assets/agents-minimal.mdmarkdown1.8 KB
assets/agents-nested.mdmarkdown1.8 KB
assets/architecture.mdmarkdown1.6 KB
assets/backend.mdmarkdown1.5 KB
assets/claude.mdmarkdown1.1 KB
assets/database.mdmarkdown1.4 KB
assets/forms.mdmarkdown1.7 KB
assets/frontend-patterns.mdmarkdown1.3 KB
assets/git-workflow.mdmarkdown1.8 KB
assets/i18n.mdmarkdown1.5 KB
assets/platform.mdmarkdown2.8 KB
assets/sdd-workflow.mdmarkdown1.7 KB
assets/server-actions.mdmarkdown1.0 KB
assets/styling.mdmarkdown1.9 KB
assets/testing.mdmarkdown1.9 KB
references/decision-matrix.mdmarkdown18.5 KB
references/example-output/README.mdmarkdown6.0 KB
references/template-filling-guide.mdmarkdown5.3 KB

assets/testing.md

View on GitHub
# Testing Strategy

## Runner

{{TEST_RUNNER_INFO}}

| Command           | Purpose |
| ----------------- | ------- |
| {{TEST_COMMANDS}} |

## Test Files

```text
{{TEST_FILE_STRUCTURE}}
```

{{TEST_COUNT}}

## Running Specific Tests

{{SPECIFIC_TEST_COMMANDS}}

## Patterns

{{TEST_PATTERNS}}

## When Writing New Tests

{{NEW_TEST_RULES}}

## Verification

After changes to {{TESTED_AREA}}:

```
{{VERIFICATION_CYCLE}}
```

## Generation Rules

- **TEST_RUNNER_INFO**: "Vitest X.Y.Z" or "Jest X.Y.Z". If both exist, document which is used for what.
- **TEST_COMMANDS**: Extract from package.json scripts. Include watch mode, single-run, coverage.
- **TEST_FILE_STRUCTURE**: Directory tree with found test files.
- **TEST_COUNT**: "Total: N tests" counting all test cases. If uncountable, report "N test files".
- **SPECIFIC_TEST_COMMANDS**: Generate commands to run specific test files. Format:
  ```
  # Run all tests
  {{PM}} {{TEST_RUN_SCRIPT}}

  # Run a specific test file
  {{PM}} {{TEST_RUNNER}} {{TEST_FILE_PATH}}

  # Run tests matching a pattern
  {{PM}} {{TEST_RUNNER}} -t "test name pattern"
  ```
  - For vitest: `bun run test path/to/file.test.ts` or `bun vitest run -t "pattern"`
  - For jest: `npm test -- path/to/file.spec.ts` or `npx jest -t "pattern"`
  - For playwright: `npx playwright test path/to/file.spec.ts`
  - Read the actual test runner config to determine the correct invocation pattern.
  - List 2-3 real test file paths as examples.
- **TEST_PATTERNS**:
  - If using mocks (vi.mock, jest.mock): document what is mocked and how.
  - If using global fixtures: document where they are.
  - If using inline factories/builders: document the pattern.
  - If there are type narrowing tests (type guards): document it.
- **NEW_TEST_RULES**: Project-specific rules for new tests (where to create, naming, what to cover).
- **TESTED_AREA**: "lib/" or "src/" — the main tested directory.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall