CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

typescript-testing

Select and run TypeScript SDK verification for packages, examples, type checks, linting, builds, Vitest suites, Effect v4 CLI tests, and runtime E2E tests. Use when adding tests, diagnosing TypeScript CI, choosing a focused test command, validating TypeScript package changes, or writing/porting CLI tests against effect@4.0.3 and @effect/vitest. Do not use for Python-only checks.

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

An exemplary router-style SKILL.md: lean, unambiguous conditional routing to two real, well-scoped, one-level-deep references. The only soft spot is that the body holds no inline command at all, so even the most common action (e.g., a quick typecheck) requires opening a reference first.

Suggestions

Inline one zero-hop quick-start command (e.g., `pnpm typecheck` or `pnpm --filter @composio/core test`) in the body for the most frequent single-check case, keeping the full command matrix in `references/test-commands.md`.

Trim the duplicated CLI Effect v4 routing paragraph in `references/test-commands.md` (lines 40-47), which restates the SKILL.md body's third paragraph nearly verbatim — link to `effect-v4-cli.md` in one sentence instead.

DimensionReasoningScore

Conciseness

The ~10-line body contains only a purpose statement and two condition-gated reading directives ("Read `references/test-commands.md` before running broad checks or adding new test coverage"); it explains nothing Claude already knows, and every token earns its place. The brief summary of what `effect-v4-cli.md` covers is navigation signaling, not padding, so it does not fall to the level-4 anchor with trimmable over-explanation.

5 / 5

Actionability

The directives are fully concrete and executable — exact file paths with explicit trigger conditions ("before writing or modifying tests under `ts/packages/cli/test/`") — but the body itself contains no commands or code; the copy-paste-ready `pnpm` commands live one hop away in `test-commands.md`. This is mostly-executable guidance with a minor gap rather than the fully self-contained level-5 anchor, and it is clearly above the pseudocode/missing-details level-3 anchor.

4 / 5

Workflow Clarity

This is a simple single-purpose skill (routing verification choices) under 50 lines, and the single action — pick the right verification by conditionally reading the right reference — is unambiguous, with each read tied to a distinct, non-overlapping trigger. No destructive or batch operations are involved, so the validation cap does not apply and the simple-skill exception holds.

5 / 5

Progressive Disclosure

Verified against the actual bundle: both referenced paths (`references/test-commands.md`, `references/effect-v4-cli.md`) exist, are one level deep, clearly signaled, and condition-gated, with the body acting as a clean overview and all detail appropriately split. The same-level cross-link from `test-commands.md` to `effect-v4-cli.md` aids navigation rather than nesting deeper, matching the clear-overview anchor rather than the level-4 anchor with organization gaps.

5 / 5

Total

19

/

20

Passed

Description

92%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.

A strong description: concrete capabilities, explicit use-when triggers in natural phrasing, third-person voice, and a negative boundary. The only improvement area is trigger-term breadth — a few common synonyms and file extensions are missing.

Suggestions

Add one or two common user phrasings as triggers, e.g. "running the tests" or "typechecking a package", to broaden natural-term coverage.

Mention the .ts/.tsx file extension in the when-clause (e.g., "Use when changing .ts/.tsx files under ts/packages/...") to match how users often scope TypeScript work.

DimensionReasoningScore

Specificity

"Select and run TypeScript SDK verification for packages, examples, type checks, linting, builds, Vitest suites, Effect v4 CLI tests, and runtime E2E tests" lists multiple specific concrete actions with comprehensive coverage of the domain, matching the level-5 anchor exactly. It is well above the level-4 anchor (several specific actions with minor coverage gaps) since nothing in the verification domain is omitted, and the third-person voice incurs no penalty.

5 / 5

Completeness

The description explicitly answers both questions: what ("Select and run TypeScript SDK verification for...") and when ("Use when adding tests, diagnosing TypeScript CI, choosing a focused test command...") with concrete trigger phrases, and adds a when-not clause ("Do not use for Python-only checks"). This is a direct match for the level-5 anchor and clearly above level 4, where the when-clause is present but less explicit.

5 / 5

Trigger Term Quality

"Use when adding tests, diagnosing TypeScript CI, choosing a focused test command, validating TypeScript package changes, or writing/porting CLI tests" provides strong natural trigger phrases, plus concrete tool names (Vitest, Effect v4, @effect/vitest). It falls short of the level-5 anchor's comprehensive synonym/extension coverage — no file extensions (.ts/.tsx), and common phrasings like "run the tests" or "unit tests" are absent — while clearly exceeding the level-3 anchor with missing common variations.

4 / 5

Distinctiveness Conflict Risk

A clear niche (TypeScript SDK verification with pinned versions effect@4.0.3 and @effect/vitest) with distinct triggers, and the explicit negative boundary "Do not use for Python-only checks" further reduces wrong-skill triggering. Minor overlap with a generic TypeScript tooling skill exists, but not enough to drop to the level-4 anchor given the version-pinned, tool-specific scope.

5 / 5

Total

19

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

ComposioHQ/composio

Path

.agents/skills/typescript-testing/SKILL.md

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.