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

85%

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

The canonical home for this skill is typescript-style-guide in slurpyb/pi-taskfile

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 meta-skill body: lean, non-duplicative, with a clear sequenced workflow and explicit validation guidance. The only structural weakness is the worked-comparison links that reference sibling skill bundles not present in this kit's directory structure.

Suggestions

Fix or inline the three broken cross-skill links (boundary-examples.md, inference-examples.md, concurrency-examples.md) so navigation works within the shipped bundle.

Make the verify step's error-recovery loop explicit (e.g., 'if a check fails, fix and re-run the shortest loop before proceeding') to reach the top workflow-clarity anchor.

DimensionReasoningScore

Conciseness

The ~45-line body is lean and assumes Claude's competence: no explanation of what TypeScript is, no padding, and every sentence carries policy or navigation ('Use the repository's existing tools for enforceable rules. Do not reimplement deterministic TypeScript, ESLint, or formatting checks.').

5 / 5

Actionability

The workflow is directive and concrete (inspect repository configuration, load rules per decision, adapt examples, verify with 'focused type checks, lint, formatting, and behavioral tests') with explicit termination criteria ('Finish when each relevant decision has a rule source'), but all executable detail is delegated to the references and the repository's own tools, leaving minor gaps in the body itself.

4 / 5

Workflow Clarity

A clear four-step sequence (Establish policy → Load rules → Apply → Verify) with an explicit validation step ('Use the shortest feedback loop that exercises the affected behaviour... run repository-mandated gates at their defined stages') and an exception rule; however, error-recovery feedback loops are only implied ('Expand by impact') rather than explicit, so it sits at 4 rather than 5.

4 / 5

Progressive Disclosure

The body is a pure overview with well-signaled, one-level-deep references each carrying 'read for...' descriptions and ownership notes, and all 8 local reference files exist in references/. However, 3 of the 13 links ('../typescript-contracts/references/boundary-examples.md', '../typescript-contracts/references/inference-examples.md', '../node/references/concurrency-examples.md') point to sibling skill directories that do not resolve in the actual bundle, leaving minor navigation gaps.

4 / 5

Total

17

/

20

Passed

Description

83%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 explicitly covers what and when with concrete trigger phrases and a useful negative boundary. Its main weakness is that the action verbs are generic (apply/write/review/explain) and a few natural synonyms (TS, generics, interfaces) are absent.

Suggestions

Replace the generic action verbs with more distinct concrete capabilities (e.g., 'enforce, refactor, and review type definitions') to raise specificity.

Add common synonyms such as 'TS', 'generics', 'interfaces', or '.ts/.tsx files' to the trigger terms.

DimensionReasoningScore

Specificity

The description enumerates many concrete topic areas ('types, discriminated unions, function APIs, variables and state, naming, source organization, React components and hooks, data flow, or tests') but the actions themselves are only three generic verbs ('writing, reviewing, or explaining'), so it lists several specific capabilities with minor coverage gaps rather than the multiple distinct concrete actions of a 5.

4 / 5

Completeness

Clearly answers both: the what ('Apply TypeScript conventions') and an explicit, specific when ('when writing, reviewing, or explaining types, discriminated unions, function APIs...') with concrete trigger phrases, plus a negative boundary ('Do not use for styling or layout alone'). The 'when' is explicit and enumerated, not merely present or weakly implied, matching the anchor-5 example structure.

5 / 5

Trigger Term Quality

Includes natural terms users would say such as 'TypeScript', 'types', 'discriminated unions', 'React components and hooks', 'data flow', and 'tests', but misses common synonyms and variations like 'TS', 'interfaces', 'generics', or '.ts', so a few natural terms are missing.

4 / 5

Distinctiveness Conflict Risk

The TypeScript policy niche is distinct with TS-specific triggers, but somewhat generic trigger words like 'naming', 'tests', and 'data flow' could overlap with testing, React, or general style-guide skills; the negative boundary mitigates but does not fully eliminate that minor overlap risk.

4 / 5

Total

17

/

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.lcafO307/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.