CtrlK
BlogDocsLog inGet started
Tessl Logo

using-lynx-api-docs

Provides authoritative guidance for Lynx development involving pages, templates, components, CSS, layouts, elements, web migration, rendering or styling bugs, and code review. Applies to *.ttml, Lynx *.tsx, and all Lynx-specific files, and requires searching the installed API docs before acting.

63

Quality

79%

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 ./ai/skills/lynx-api-docs/skills/using-lynx-api-docs/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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.

A well-structured navigation skill: clear core rule, a task-to-doc lookup table, and mistake-triggered doc pointers that make the workflow easy to follow. The main weaknesses are redundancy across the Overview/Core Rule/Red Flags sections and a slightly under-specified fallback search step.

Suggestions

Consolidate the repeated core rule: keep the single bolded 'MUST ALWAYS read the relevant API docs BEFORE writing or editing Lynx code' statement in one section and cut the near-duplicate sentences in 'Overview' and 'Red Flags'.

Merge 'Why Web Knowledge Fails' and 'Red Flags — Stop and Read Docs' into one section; each currently restates the same facts (div/span vs view/text, box-sizing auto, no margin collapsing) with the same doc pointers.

Replace 'If uncertain, search the elements/ or css/ directories' with a concrete search step (e.g., the specific grep/Glob pattern to run against the installed docs directory), and drop the four inlined 'Core Rules' bullets in favor of the pointer to quick-reference.md.

DimensionReasoningScore

Conciseness

The body is mostly efficient and does not teach concepts Claude already knows (Lynx platform differences are legitimately unfamiliar), but the same facts are repeated across sections — the core rule appears in 'Overview' ('Always retrieve from the installed API docs before writing or modifying Lynx page code'), 'Core Rule' ('MUST ALWAYS read the relevant API docs BEFORE writing or editing any Lynx code'), and again in 'Red Flags'; box-sizing ('auto, normally with border-box sizing') and margin collapsing each appear twice. This is more than the 'minor instances that could be trimmed' of the level-4 anchor, but well short of heavily padded.

3 / 5

Actionability

The Quick Reference table maps each task to concrete, specific doc paths ('css/supported-properties.md', 'layout/linear-layout.md') and the Red Flags pair each mistake with the exact doc to read, which is concrete executable guidance for an instruction-only skill. The gap keeping it from 5: the fallback 'If uncertain, search the elements/ or css/ directories' gives no concrete search mechanism (e.g., a grep/Glob invocation), and the referenced paths cannot be verified as real files since no bundle directory exists alongside SKILL.md.

4 / 5

Workflow Clarity

'How to Use the Docs' gives a clear 5-step sequence (identify task, look up file, read before editing, apply, fallback search) with an explicit ordering checkpoint ('Read the doc BEFORE writing or editing code'). This is a read-then-apply documentation skill, not a destructive or batch operation, so the missing-validate cap does not apply; the only minor gap is that there is no verification step after applying doc rules (e.g., re-checking the doc when output looks wrong), which fits the level-4 anchor rather than the explicit-feedback-loops of level 5.

4 / 5

Progressive Disclosure

The body is a genuine overview that points to one-level-deep, well-signaled references via the Quick Reference table, and the Red Flags section routes to specific docs — good structure matching level 4. It falls short of level 5 because the 'Core Rules' section inlines four rules ('Text must use <text> component', 'No margin collapsing', 'Use rem + vw') that duplicate the very content it says lives in 'quick-reference.md', a minor organization gap; also, no bundle files are present to verify the referenced paths resolve.

4 / 5

Total

15

/

20

Passed

Description

81%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 excellent trigger-term coverage (platform name, natural task keywords, synonyms, and file extensions) and a clearly distinct Lynx-specific niche. Its main limitation is that the 'what' leans on a generic 'provides authoritative guidance' verb plus a topic list rather than concrete actions, and its 'when' clause is file-scope-based rather than task-based.

Suggestions

Replace 'Provides authoritative guidance for Lynx development involving...' with a concrete-action verb list, e.g. 'Look up Lynx element, CSS, and layout behavior in the installed API docs before writing or editing Lynx code; check migration guidance when porting web code.'

Add a task-oriented trigger phrase alongside the file-scope clause, e.g. 'Use when writing or modifying *.ttml or Lynx *.tsx pages, debugging Lynx rendering/styling issues, migrating web UIs to Lynx, or reviewing Lynx code.'

DimensionReasoningScore

Specificity

The description names the domain precisely ('Lynx development involving pages, templates, components, CSS, layouts, elements, web migration, rendering or styling bugs, and code review') and one concrete action ('requires searching the installed API docs before acting'), but the opening verb 'Provides authoritative guidance' is generic — it enumerates topic areas rather than listing several concrete actions (cf. 'Extract text and tables from PDF files, fill forms, merge documents'). It matches the level-3 anchor (domain plus 1-2 concrete actions, not comprehensive) better than level 4, which expects several specific actions.

3 / 5

Completeness

Both parts are present: 'what' ('Provides authoritative guidance for Lynx development involving [scope]' plus 'requires searching the installed API docs before acting') and an explicit 'when' ('Applies to *.ttml, Lynx *.tsx, and all Lynx-specific files'). It is not level 5 because the trigger guidance is file-pattern-based only — there is no task-oriented 'Use when writing or editing Lynx pages' phrasing, so the 'when' could be more explicit, matching the level-4 anchor.

4 / 5

Trigger Term Quality

Coverage is comprehensive: platform name ('Lynx'), natural task terms users would actually say ('CSS', 'layouts', 'components', 'templates', 'styling', 'rendering... bugs', 'code review', 'web migration'), synonyms for the same intent (styling/rendering), and file extensions ('*.ttml', 'Lynx *.tsx') — matching the level-5 anchor 'comprehensive coverage of natural terms including synonyms and file extensions'.

5 / 5

Distinctiveness Conflict Risk

It occupies a clear niche: the platform name 'Lynx' plus Lynx-specific extensions (*.ttml, Lynx *.tsx) give it distinct triggers and minimal conflict risk — the only conceivable overlap is generic CSS conversations, but the description explicitly scopes to 'Lynx-specific files', matching the level-5 anchor.

5 / 5

Total

17

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
lynx-family/lynx
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.