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.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/test-all/SKILL.md

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable and clearly sequenced into 7 phases with concrete commands and a copy-paste sub-agent template. Its weaknesses are progressive disclosure (everything inlined into a single monolithic file with no referenced bundle materials) and minor verbosity in the rationale sections.

Suggestions

Move the large static blocks (the 9-row test map, the sub-agent prompt template, and the design-decisions/troubleshooting sections) into reference files under references/ and link to them one level deep, e.g. 'See references/test-map.md' and 'See references/subagent-prompt.md'.

Tighten the 'Key Design Decisions' section to bullet conclusions, since much of it restates phases already covered.

Add an explicit inline validate-then-proceed checkpoint after Phase 3 server start (verify all 9 URLs present before launching agents) to strengthen the batch-operation feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and action-oriented with numbered phases and direct bash commands, assuming Claude's competence; a few explanatory passages (e.g. repeated rationale in 'Key Design Decisions') could be trimmed, but padding is minor.	4 / 5
Actionability	Guidance is fully executable: exact commands like 'node scripts/test-servers.mjs start', 'pnpm build:tgz', a concrete sub-agent prompt template with substitution placeholders, and a result-aggregation table format are all copy-paste ready and cover the common cases.	5 / 5
Workflow Clarity	The 7-phase sequence is explicit with validation checkpoints ('Stop on failure', 60-second server readiness check, 20-minute hard timeout, retry limits), but for a batch/destructive operation it relies on script-level validation rather than an inline validate-fix-retry loop, leaving a minor checkpoint gap.	4 / 5
Progressive Disclosure	No bundle files (references/, scripts/, assets/) are present and the body inlines all detail in one monolithic file; section headers provide structure, but the test-map, prompt template, and design-decisions content that could live in separate references is all inline with no one-level-deep navigation.	3 / 5
	Total	16 / 20 Passed

Description

58%Weight 40%Scale 1-5

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 is specific and distinct, clearly conveying a parallel test-orchestration workflow, but it omits any explicit 'Use when...' trigger guidance and leans on technical jargon over natural user language. Completeness and trigger-term quality are the main weaknesses.

Suggestions

Append an explicit 'Use when...' clause, e.g. 'Use when the user wants to run the full IWSDK test suite, run all test suites at once, or verify the SDK across all example projects.'

Add natural user-language keywords and synonyms (e.g. 'run tests', 'full test suite', 'run all tests', 'IWSDK tests') so the description triggers on phrases a user would actually say.

Consider third-person-voicing the opening clause consistently and trimming 'Handles' in favor of action verbs to keep the what-it-does list tight.

Dimension	Reasoning	Score
Specificity	Names the domain (parallel test orchestration) and several concrete actions ('build, example setup, dev servers, agent launch, polling, retries, and result aggregation'), giving broad action coverage, though a few are slightly generic ('setup', 'handling').	4 / 5
Completeness	It clearly answers 'what does this do' with concrete lifecycle steps, but there is no 'Use when...' clause or equivalent explicit trigger guidance telling Claude when to invoke the skill, which caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant terms like 'test suites', 'sub-agents', and 'iwsdk CLI' are present, but the phrasing is technical-orchestration jargon rather than the natural phrases a user would say when needing the skill, and synonyms/user-language variants are largely missing.	3 / 5
Distinctiveness Conflict Risk	The narrow niche (running all 9 IWSDK test suites concurrently via Task sub-agents) is distinct from generic test or build skills, with only minor overlap risk against other test-runner skills.	4 / 5
	Total	14 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 10 missing	Warning

	Total	14 / 16 Passed

Repository: facebook/immersive-web-sdk
Path: .claude/skills/test-all/SKILL.md
Commit: 13f42e7

Reviewed: 8 days ago

Table of Contents

Discovery Implementation Validation

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.