test-all
Parallel test orchestrator. Runs all 9 test suites concurrently via Task sub-agents and the iwsdk CLI. Handles build, example setup, dev servers, agent launch, polling, retries, and result aggregation.
61
72%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/test-all/SKILL.mdQuality
Discovery
67%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description excels at specificity and distinctiveness, clearly listing concrete actions and a unique tooling niche. However, it lacks an explicit 'Use when...' clause, which is critical for Claude to know when to select this skill. The trigger terms lean heavily on internal jargon rather than natural user language.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to run the full test suite, execute all tests, or check CI status.'
Include more natural trigger terms users might say, such as 'run tests', 'test runner', 'execute test suite', or 'CI pipeline'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: runs 9 test suites concurrently, uses Task sub-agents and iwsdk CLI, handles build, example setup, dev servers, agent launch, polling, retries, and result aggregation. | 3 / 3 |
Completeness | Clearly answers 'what does this do' with detailed actions, but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which caps this dimension at 2 per the rubric guidelines. | 2 / 3 |
Trigger Term Quality | Includes some relevant terms like 'test suites', 'retries', 'build', but uses domain-specific jargon ('iwsdk CLI', 'Task sub-agents', 'polling') that users are unlikely to naturally say. Missing common variations like 'run tests', 'test runner', 'CI'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly specific niche: parallel test orchestration using iwsdk CLI with 9 specific test suites and Task sub-agents. Very unlikely to conflict with other skills due to the precise tooling and workflow described. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong orchestration skill with excellent workflow clarity and actionability — every phase has concrete commands, clear sequencing, and explicit validation/failure handling. The main weaknesses are moderate verbosity in the 'Key Design Decisions' section (which explains rationale rather than providing instructions) and the monolithic structure that could benefit from splitting reference material into separate files.
Suggestions
Move the 'Key Design Decisions' section to a separate DESIGN.md or remove it entirely — most of these rationale explanations don't help Claude execute the workflow.
Consider moving the Troubleshooting section to a separate TROUBLESHOOTING.md referenced from the main skill to reduce the token footprint of the primary instruction set.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary sections like 'Key Design Decisions' that explain rationale Claude doesn't need (why ports aren't pre-assigned, why sub-agents read skill files). The troubleshooting section is useful but some entries are obvious. The test map table and phase structure are well-organized and earn their tokens. | 2 / 3 |
Actionability | Every phase has concrete, executable bash commands. The sub-agent prompt template is copy-paste ready with clear substitution variables. The tracking data structure, retry logic, and output format are all specific and actionable. | 3 / 3 |
Workflow Clarity | The 7-phase workflow is clearly sequenced with explicit stop-on-failure checkpoints in Phase 1, timeout handling in Phase 5, retry limits and conditions in Phase 6, and a cleanup + aggregation phase. The feedback loop for retries (transient vs assertion failures) is well-defined, and the constraint against improvised bash commands adds safety. | 3 / 3 |
Progressive Disclosure | The skill references 9 sub-skill files (e.g., test-interactions/SKILL.md) which is good delegation, but no bundle files were provided to verify these exist. The 'Key Design Decisions' section and some troubleshooting content could be split into a separate reference file to keep the main skill leaner. The content is well-structured with clear sections but is somewhat monolithic at ~180 lines. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- facebook/immersive-web-sdk
- Commit
b3d1162
- 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.