CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

test-setup

Sets up the test framework and CI: tests/ directory, engine runner, GitHub Actions workflow. Use once, before the first sprint.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/test-setup/SKILL.md
SKILL.md
Quality
Evals
Security

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.

A well-engineered orchestration skill: the body routes, guards, and sequences while all executable detail is correctly pushed one level deep into phase references that all exist and stay flat. The only real improvement is de-duplicating the per-phase compaction note and surfacing an explicit validation step in the body itself.

DimensionReasoningScore

Conciseness

The body is a lean orchestrator with no concept explanations or padding; every section carries routing or safety information. It misses anchor 5 only because the identical sentence "Read it again if the conversation was compacted or resumed during this phase" is repeated verbatim in all six phase sections when a single global note would do.

4 / 5

Actionability

Directives are concrete and executable: exact output paths ("tests/ directory structure + .github/workflows/tests.yml"), precise force-flag semantics ("create any missing files even if the directory already exists"), and a named redirect target ("stop and redirect to /setup-engine"). The executable detail itself is deliberately deferred to the reference files, which is appropriate for an orchestration skill but leaves the body one step removed from anchor 5.

4 / 5

Workflow Clarity

A clear six-phase sequence with each phase mapped to exactly one reference file, plus real checkpoints: Phase 1 detection with an early-exit gate, Phase 2 explicit approval before any file creation, and a Phase 6 post-setup summary with gate verification. Not anchor 5 because the body itself does not state an explicit validate-and-retry loop for the batch file creation (that detail lives in the references), though the never-overwrite guardrails mitigate the risk.

4 / 5

Progressive Disclosure

The body is a concise overview with six well-signaled references ("Read references/1-detect.md now and follow it"), one per phase. All six files exist in the bundle, are exactly one level deep, and contain no nested skill references — the referenced files they mention are project artifacts being created, not further skill docs. This matches the anchor-5 example structure closely.

5 / 5

Total

17

/

20

Passed

Description

75%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 that names concrete deliverables and gives an explicit (if lifecycle-based) when-to-use clause in third person. Its main gap is the absence of user-facing trigger phrases and synonyms that would push completeness and trigger-term coverage to the top anchor.

DimensionReasoningScore

Specificity

The description lists several concrete deliverables ("tests/ directory, engine runner, GitHub Actions workflow") rather than generic language. It stops short of anchor 5 because it omits outputs the skill actually produces, such as the smoke test seed and the Phase 2 plan approval.

4 / 5

Completeness

Both parts are present: a clear "what" ("Sets up the test framework and CI: tests/ directory, engine runner, GitHub Actions workflow") and an explicit "when" ("Use once, before the first sprint"). It falls short of anchor 5 because the 'when' is lifecycle timing rather than concrete user trigger phrases like "when the user mentions tests".

4 / 5

Trigger Term Quality

It uses natural terms a user would say when needing this skill ("test framework", "CI", "tests/ directory", "GitHub Actions workflow"). Not anchor 5 because common variations like "unit tests", "test suite", or "testing setup" are missing.

4 / 5

Distinctiveness Conflict Risk

"Sets up the test framework and CI" carves out a distinct scaffolding niche with a unique once-only scope. Minor overlap risk remains with closely related engine-setup or generic CI skills, keeping it below anchor 5.

4 / 5

Total

16

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository

Donchitos/Claude-Code-Game-Studios

Path

.claude/skills/test-setup/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.