CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

typescript-style-guide

Apply TypeScript conventions when writing, reviewing, or explaining types, discriminated unions, function APIs, variables and state, naming, source organization, React components and hooks, data flow, or tests. Do not use for styling or layout alone. Canonical typescript conventions.

Quality

83%

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

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 exemplary hub-style SKILL.md: a lean, directive overview that defers all rule detail to well-signaled, one-level-deep reference files with explicit ownership boundaries, and a clear four-step workflow with an explicit verification step. The only minor gaps are the absence of in-body example commands and an explicit error-recovery loop in the workflow.

DimensionReasoningScore

Conciseness

The ~45-line body is lean and directive throughout: "This skill owns TypeScript policy within the kit", "Do not reimplement deterministic TypeScript, ESLint, or formatting checks", with no padding and no explanation of concepts Claude already knows — every token earns its place, matching anchor 5.

5 / 5

Actionability

The guidance is concrete and executable for an instruction-only hub skill (inspect repository configuration, precedence rules, named verification loops: "focused type checks, lint, formatting, and behavioral tests as relevant"), and the absence of code is not penalized per the rubric's scoring note; the minor gap versus anchor 5 is that no example commands or snippets appear in the body itself — the concrete examples all live one level deeper in the references.

4 / 5

Workflow Clarity

Four clearly sequenced steps (Establish policy → Load rules → Apply → Verify) with an explicit verification checkpoint, escalation guidance ("Expand by impact and run repository-mandated gates at their defined stages"), and completion criteria ("Finish when each relevant rule is satisfied or a justified exception is identified") — anchor 4 rather than 5 because no explicit error-recovery/fix-retry loop is described, though this policy skill involves no destructive or batch operations, so the workflow cap does not apply.

4 / 5

Progressive Disclosure

The body is a model one-level-deep index: every one of the 10 local reference files exists and is clearly signaled with "read for…" scope statements plus ownership boundaries (e.g., "Types owns narrowing and assertion policy"), organized under Conventions and Worked comparisons, with the section-level contents claim verified in the actual files; the three cross-kit comparison links (../typescript-contracts/, ../node/) are explicitly labeled as belonging to sibling skills, so navigation remains clear — anchor 5.

5 / 5

Total

18

/

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, specific description with third-person voice, a broad but concrete topic enumeration, and useful negative boundary guidance. Its main gaps are the absence of explicit user-request-level trigger phrasing ("Use when the user mentions…"), missing natural synonyms/file extensions, and a redundant trailing fragment.

Suggestions

Replace the redundant trailing fragment "Canonical typescript conventions." with an explicit trigger clause, e.g., "Use when the user mentions TypeScript, .ts/.tsx files, type errors, or asks to write, review, or explain typed code."

Add natural synonyms and file extensions to the trigger terms, such as ".ts", ".tsx", and "type safety", so the description matches how users actually phrase requests.

Clarify distinctiveness from adjacent skills by naming what this skill does not own (e.g., runtime contract validation or linting configuration) in the negative boundary clause.

DimensionReasoningScore

Specificity

The description enumerates a comprehensive set of concrete activities and topics ("writing, reviewing, or explaining types, discriminated unions, function APIs, variables and state, naming, source organization, React components and hooks, data flow, or tests") but the governing action is a single "apply conventions" and the trailing "Canonical typescript conventions" fragment is redundant — fitting anchor 4 (several specific actions, minor gaps) rather than anchor 5's multiple distinct action verbs.

4 / 5

Completeness

Both what ("Apply TypeScript conventions…") and when ("when writing, reviewing, or explaining…") are present, plus an explicit negative boundary ("Do not use for styling or layout alone"), but there is no user-request-level trigger phrase like "Use when the user mentions TypeScript" — anchor 4 (both present, 'when' could be more explicit) rather than anchor 5's concrete trigger phrases.

4 / 5

Trigger Term Quality

Good keyword coverage of natural terms users would say ("TypeScript", "types", "function APIs", "React components and hooks", "naming", "tests"), but common synonyms and file extensions (.ts, .tsx, "TS") are missing, matching anchor 4 ("Good keyword coverage; a few natural terms missing") rather than anchor 5's comprehensive synonym/extension coverage.

4 / 5

Distinctiveness Conflict Risk

The explicit exclusion clause ("Do not use for styling or layout alone") distinguishes it from styling/layout skills, and the enumerated sub-domains carve a clear niche, but there is minor overlap risk with closely related TypeScript skills (e.g., contract or linting convention skills) — anchor 4 ("Mostly distinct; minor overlap risk with closely related skills") rather than anchor 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

slurpyb/pi-taskfile

Path

.agents/references/agent/ref.bYWQ9U5K/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.