CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

dev-create-service

Use when adding API integration to a module - creates types, contracts, adapter, and service layer.

Quality

80%

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

Fix and improve this skill with Tessl

tessl review fix ./packs/vue/skills/dev-create-service/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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 exemplarily lean, highly actionable skill body: exact file paths, explicit naming rules, an ordered creation sequence, and a concrete validation command, with detail correctly delegated to the architecture doc. The only meaningful gaps are the absence of an error-recovery loop after `tsc --noEmit` and no example snippet of a generated artifact. Both are small additions that would make the workflow fully self-correcting.

Suggestions

Add a feedback loop after validation, e.g. "5. Validate: `npx tsc --noEmit`. If errors: fix the flagged file and re-run before proceeding."

Include one short example of a types/contracts/adapter trio for a sample resource so the snake_case↔camelCase mapping is unambiguous even if ARCHITECTURE.md is unavailable.

DimensionReasoningScore

Conciseness

The body is ~26 lines with zero padding: no concept explanations, no library tutorials, just "Read `docs/ARCHITECTURE.md` sections 4.1 (Services)...", terse file lists, bolded rules ("**NO try/catch**"), and a one-line validation command. Every token earns its place and the skill fully assumes Claude's competence.

5 / 5

Actionability

Guidance is concrete and executable: exact file paths (`types/[resource].types.ts`, `adapters/[resource]-adapter.ts`), naming conventions (snake_case vs camelCase), specific user questions, and the exact command `npx tsc --noEmit`. It stops short of the 5 anchor because no example snippets or templates of the generated files are given — the shape of each artifact is delegated entirely to the external ARCHITECTURE.md, leaving a minor gap if that doc is thin.

4 / 5

Workflow Clarity

A clear 5-step sequence with an ordered creation sub-list (a→d) and an explicit validation checkpoint ("Validate: `npx tsc --noEmit`"). It misses the 5 anchor because there is no error-recovery loop — nothing instructs what to do when tsc fails (fix and re-validate) — matching 'clear sequence with most checkpoints present; minor validation gaps'. The batch-file-creation cap does not apply since a validation step is present.

4 / 5

Progressive Disclosure

At under 50 lines with no bundle files, the skill needs no external references and is cleanly organized under a single `## Steps` section. Its one reference (`docs/ARCHITECTURE.md` §4.1-4.3) is clearly signaled, section-numbered, and one level deep, with the detailed layering rules correctly delegated there — meeting the simple-skill exception for a top score.

5 / 5

Total

18

/

20

Passed

Description

67%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 solid description with an explicit trigger clause and a concrete list of the four artifacts it creates. Its main weakness is thin trigger-term coverage — a single 'API integration' phrase with no synonyms or natural variations — which limits how reliably users' phrasing will match it. Adding a few natural trigger variants would lift both completeness and trigger quality.

Suggestions

Broaden trigger terms with natural user phrasings, e.g. "Use when adding an API integration, connecting a module to an endpoint, or creating an API client/service layer".

Mention the file types or layering vocabulary users might use (types, adapter, contracts, service) as secondary trigger words so the skill surfaces when users name only one artifact.

Consider naming the target stack (TypeScript modules) in the description so it does not trigger for non-TS API work.

DimensionReasoningScore

Specificity

The description lists several concrete deliverables — "creates types, contracts, adapter, and service layer" — naming four specific artifacts in the API-integration domain. It falls short of the 5 anchor because coverage is a single flat list with one action verb and no elaboration of what each artifact involves, matching 'several specific actions; minor gaps' rather than comprehensive coverage.

4 / 5

Completeness

Both parts are present: the what ("creates types, contracts, adapter, and service layer") and an explicit when-clause ("Use when adding API integration to a module"). It does not reach the 5 anchor because the trigger guidance is a single condition without additional concrete trigger phrases or variations, and the 'what' is a bare artifact list — consistent with 'both present; when could be more explicit or specific'.

4 / 5

Trigger Term Quality

"Use when adding API integration to a module" supplies one natural phrase a user might say, but common variations and synonyms are missing — e.g. "API client", "connect to an endpoint", "fetch data from an API", "service layer". Terms like "contracts" and "adapter" are internal artifacts users would rarely utter, so this sits at 'some relevant keywords but missing common variations' rather than the 4 anchor's good coverage.

3 / 5

Distinctiveness Conflict Risk

The combination of types/contracts/adapter/service layer for API integration carves a fairly clear niche that few generic skills would claim, though it could overlap with broader 'write API code' or scaffolding skills — matching 'mostly distinct; minor overlap risk with closely related skills'. It is clearly above anchor 3, whose examples are generic document-file phrasing with much wider overlap.

4 / 5

Total

15

/

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

fernandezbaptiste/specialist-agent

Path

packs/vue/skills/dev-create-service/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.