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

89%

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

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 dispatch-style SKILL.md: lean, non-redundant, with a well-sequenced workflow that includes an explicit verification stage, and a reference index that is accurately signposted and verified against the bundle. The only reservations are the absence of any concrete command or code snippet in the Verify step and the implicit (rather than explicit) fix-and-retry loop when a check fails.

DimensionReasoningScore

Conciseness

The ~45-line body is all payload with zero concept padding: "Use the repository's existing tools for enforceable rules. Do not reimplement deterministic TypeScript, ESLint, or formatting checks" and each workflow step carry operational instruction only, with nothing explaining what Claude already knows. This matches the 5 anchor 'every token earns its place'; the 4 anchor requires over-explanation that could be trimmed, and none is present.

5 / 5

Actionability

Guidance is concrete and executable for an instruction-only dispatch skill: "Inspect the consuming repository's instructions and configuration", verify with "focused type checks, lint, formatting, and behavioral tests", and per-file routing like "read for inference, readonly data, constants, template literal types". It sits between anchors: more complete and specific than the 3 anchor (no pseudocode, no missing key details), but short of the 5 anchor because no sample command or snippet is given (e.g., a scoped `tsc --noEmit` invocation) and step 3 delegates detail to the references.

4 / 5

Workflow Clarity

A clear four-step sequence ("Establish policy" → "Load the applicable rules" → "Apply the rules" → "Verify") with an explicit verification step, named check types, and completion criteria ("Finish when each relevant rule is satisfied or a justified exception is identified"). It fits the 4 anchor: the sequence and checkpoints are explicit, but the 5 anchor's error-recovery loop is only implicit ("Expand by impact") rather than an explicit what-to-do-when-a-check-fails path.

4 / 5

Progressive Disclosure

The body is a clean dispatch hub: a short overview, a workflow, and a grouped reference index ("Conventions" / "Worked comparisons") where every entry has a 'read for...' trigger and ownership disambiguation (e.g., "Owns narrowing and assertion policy, including runtime null checks"). All 10 local paths (references/types.md through references/state-examples.md) exist and — verified — do provide the claimed "section-level contents"; the three sibling-skill links (../typescript-contracts, ../node) are one level deep and clearly signaled, so navigation is easy and content is appropriately split, matching the 5 anchor.

5 / 5

Total

18

/

20

Passed

Description

88%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: it states a concrete capability set, an explicit multi-context 'when' clause, and a negative boundary, all in third-person/imperative voice without padding. The trailing fragment "Canonical typescript conventions." adds little, and a few natural trigger terms (file extensions, 'interfaces', 'generics') are absent.

DimensionReasoningScore

Specificity

"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" names three concrete actions and comprehensively enumerates the domain's sub-areas with no material gaps. This matches the anchor 'Lists multiple specific concrete actions; comprehensive coverage' rather than 4, whose only distinction is minor coverage gaps that this description does not have.

5 / 5

Completeness

The 'what' is explicit ("Apply TypeScript conventions...") and the 'when' is an explicit trigger clause enumerating contexts ("when writing, reviewing, or explaining types, discriminated unions, function APIs...") plus a negative boundary ("Do not use for styling or layout alone"). Both what and when are clearly and explicitly stated with concrete triggers, matching the 5 anchor; the 4 anchor ('when' could be more explicit) does not apply since no trigger is merely implied.

5 / 5

Trigger Term Quality

Natural trigger terms are well covered: "TypeScript", "types", "discriminated unions", "React components and hooks", "naming", "tests". It falls short of the 5 anchor because common variations users would actually say are missing — no ".ts"/".tsx", "TS", "interfaces", or "generics" — but coverage is too broad and on-topic for the 3 anchor's 'missing common variations' to be the better fit.

4 / 5

Distinctiveness Conflict Risk

The exclusion "Do not use for styling or layout alone" explicitly disambiguates from UI/styling skills, but the sweeping claim "Canonical typescript conventions" and broad terms like "tests", "naming", and "data flow" leave minor overlap risk with closely related skills (e.g., sibling contracts or node-conventions skills in the same kit). This fits the 4 anchor 'Mostly distinct; minor overlap risk with closely related skills'; it is not 5 because residual overlap with adjacent TS-adjacent skills remains, and not 3 because the triggers are anchored specifically to TypeScript.

4 / 5

Total

18

/

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.rQayoeky/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.