propagate
Generate tests from Allium specifications. Use when the user wants to propagate tests, generate test files from a spec, write tests for a specification, create property-based tests, produce state machine tests, check test coverage against spec obligations, or understand what tests a specification requires.
85
81%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted skill description that clearly defines its niche (Allium specification-based test generation), lists specific concrete capabilities, and provides explicit 'Use when' triggers with natural language variations. It follows third-person voice correctly and is concise without being vague.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: generate test files from a spec, create property-based tests, produce state machine tests, check test coverage against spec obligations, and understand what tests a specification requires. | 3 / 3 |
Completeness | Clearly answers both what ('Generate tests from Allium specifications') and when ('Use when the user wants to propagate tests, generate test files from a spec, write tests for a specification...') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'propagate tests', 'generate test files', 'write tests', 'property-based tests', 'state machine tests', 'test coverage', 'spec obligations', and 'specification'. Good coverage of variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific domain of 'Allium specifications' and the particular combination of property-based tests, state machine tests, and spec obligations. Unlikely to conflict with generic testing skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive and well-structured skill that covers a complex domain (spec-to-test generation) with clear workflows, thorough taxonomies, and good decision logic for edge cases. Its main weaknesses are the length/verbosity of inline content that could be split into reference files, and the lack of concrete executable code examples showing what generated tests actually look like. The workflow clarity is strong with explicit checklists and conditional handling.
Suggestions
Add 2-3 concrete executable test output examples showing what a generated boundary test, PBT property test, and state machine test look like in at least one language (e.g., TypeScript with fast-check).
Move the detailed test category taxonomy (the long bullet list under 'Spec mode') into a separate reference file (e.g., `references/test-categories.md`) and link to it, keeping only a summary in the main skill.
Move the implementation bridge details (surface mapping, temporal test patterns, cross-module chains) into a separate reference file to reduce the main skill's token footprint.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long and includes some explanatory content that Claude wouldn't need (e.g., the metaphor about plant propagation, explaining what an implementation bridge is conceptually). However, most of the content is substantive taxonomy and procedural guidance that earns its place. Could be tightened by ~20-30%. | 2 / 3 |
Actionability | The skill provides detailed taxonomies and checklists but lacks concrete executable code examples for most scenarios. The one code snippet is a TODO placeholder. The action map construction steps are described procedurally but without executable examples. The PBT framework table is helpful but no actual test generation templates are shown. | 2 / 3 |
Workflow Clarity | The process section provides a clear 7-step sequence, the discovery checklist is explicit and thorough, and there are validation checkpoints (step 7: verify tests compile/run). Feedback loops are present for temporal tests (check for time injection seam, flag gap if missing) and cross-module tests (check for fixture, generate skeleton with TODOs if missing). The modes are clearly delineated with ordered sub-steps. | 3 / 3 |
Progressive Disclosure | The skill references `references/test-generation.md` for the taxonomy but no bundle files are provided, making it impossible to verify this reference resolves. The content is quite long and monolithic — the detailed test category taxonomies in Spec mode and the implementation bridge details could be split into separate reference files. The structure within the file is well-organized with clear headers, but the sheer volume inline hurts progressive disclosure. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- DataDog/datadog-agent
- Commit
0f36ad4
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.