CtrlK
BlogDocsLog inGet started
Tessl Logo

method-shorthand-jsdoc

Method shorthand in return objects for JSDoc preservation. Use when factory functions have internal helpers that should expose docs, or hovering over returned methods shows no JSDoc.

58

Quality

73%

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 ./.agents/skills/method-shorthand-jsdoc/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

56%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 body teaches the pattern well with complete code and an explicit decision rule, but it is noticeably padded: the same example is repeated four times and basic `this`-binding semantics are explained. Its references section points at paths outside the skill that won't resolve when the skill is installed.

Suggestions

Cut the duplicated getEpoch example to a single Problem/Solution pair and drop the 'Real Example' or 'The Pattern' section — one full worked example plus the decision table conveys the same transformation in roughly half the tokens.

Remove the 'Arrow Functions Don't Work' explanation of why arrows lack `this` (Claude already knows this); keep only the one-line rule 'use method shorthand, not arrows, so `this` binds to the object'.

Fix the References section: either move the two articles into a `references/` directory inside the skill and link them one level deep, or delete the broken `../../../docs/articles/...` links, since they won't resolve in an installed skill bundle.

DimensionReasoningScore

Conciseness

The same getEpoch example with full JSDoc appears three times ("The Problem", "The Solution", "Real Example"), and "The Pattern" repeats the bad/good pair a fourth time; "Why This Works" restates what the examples already showed. "Arrow Functions Don't Work" explains that arrows lack their own `this` — a concept Claude already knows — placing this firmly at the score-2 anchor (several padded/unnecessary sections) rather than score 3's "mostly efficient".

2 / 5

Actionability

The core transformation is shown with complete, executable TypeScript in both directions, backed by a decision rule, a zone-selection table, and a summary table. It stops short of score 5 because several snippets are elided pseudocode ("fetchUser(id: string) { ... }", the arrow-function blocks) rather than copy-paste-ready code.

4 / 5

Workflow Clarity

As a single-action pattern skill, the instruction is unambiguous and the "Decision Rule" section supplies explicit move-it-in vs keep-it-out criteria plus a zone table, acting as the checkpoint. It misses score 5 because that guidance is scattered across redundant sections (Decision Rule, the anatomy table, and the summary table restate each other), slightly muddying the canonical decision path.

4 / 5

Progressive Disclosure

Sections are clearly headed and content stays on-topic, but the skill is a single ~240-line monolith with no bundle files, and its only references point outside the skill directory ("../../../docs/articles/...") to files that do not exist in the bundle, so they are effectively broken. This matches the score-3 anchor (structure present, references not clearly signaled/usable) rather than score 4's well-signaled one-level-deep references.

3 / 5

Total

13

/

20

Passed

Description

78%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 with an explicit what and a well-crafted, symptom-based Use-when clause. Its main limits are modest action coverage (one technique rather than several) and minor trigger overlap with the factory-function skill family.

DimensionReasoningScore

Specificity

"Method shorthand in return objects for JSDoc preservation" names the domain and one concrete action (use method shorthand so JSDoc survives), but does not enumerate several distinct capabilities. It is more concrete than the score-2 anchor ("Processes PDF files") yet does not reach the score-4 "lists several specific actions" bar.

3 / 5

Completeness

Both halves are explicit: the what ("Method shorthand in return objects for JSDoc preservation") and a concrete "Use when..." clause with two specific triggers, including a symptom-based one ("hovering over returned methods shows no JSDoc"). This matches the score-5 anchor of clearly answering what AND when with concrete trigger phrases, exceeding score 4's "when could be more explicit".

5 / 5

Trigger Term Quality

Natural phrases a developer would say are present: "factory functions have internal helpers", "hovering over returned methods shows no JSDoc", "JSDoc". It falls short of score 5 because common synonyms like "intellisense", "tooltip", "doc comments", or "TypeScript" are missing, but coverage is clearly better than the score-3 "some relevant keywords" anchor.

4 / 5

Distinctiveness Conflict Risk

The niche is distinct — the hover-symptom trigger ("hovering over returned methods shows no JSDoc") is unlikely to fire for any other skill. However "factory functions have internal helpers" overlaps with the closely related `factory-function-composition` skill referenced in the body, matching the score-4 anchor (minor overlap risk) rather than score 5's minimal conflict risk.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 3 suspicious

Warning

Total

15

/

16

Passed

Repository
EpicenterHQ/epicenter
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.