CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

modern-web-guidance

Search tool for modern web development best practices. MANDATORY: Execute FIRST for all HTML/CSS and clientside JS tasks. Do NOT skip — web APIs evolve rapidly and training weights contain obsolete patterns. Trigger immediately for: modals/dialogs/popovers, tables, dark mode, anchor positioning, container queries, view transitions, scroll-driven animations, parallax/reveals, forms, validation, autofill, accessibility, custom selects, scrollbars, CWV (LCP, INP, CLS), content-visibility, fetch priority, image optimization, security, passkeys, HTML sanitization, web components, dates/timezones, built-in AI, WebAssembly, standard HTML/CSS/DOM in frameworks, etc. DO NOT trigger for: backend (SQL, ORMs, API routes), infra/scripts (CI/CD, Docker, Actions, Python/Go, Git), or tooling/trivial (Vite, tsconfig, ESLint, tests, copy/renames, 3P docs), etc.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Failed to scan

The risk profile of this skill

SKILL.md
Quality
Evals
Security

Quality

Content

88%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-engineered instruction skill: executable commands, explicit decision branches, validation checkpoints, and feedback loops throughout, with no filler explanations. The only weaknesses are mild verbosity in the disclosure-format and browser-support-policy sections.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious operational guidance (query phrasing rules, npx/pnpx permissions, SSR spread/cast idioms, per-instance anchor-name generation) and explains nothing Claude already knows, matching the efficient anchor 4. It misses 5 because Step 4's disclosure-format spec and the browser-support policy example list carry minor padding that could be trimmed.

4 / 5

Actionability

Commands are copy-paste ready ('npx -y modern-web-guidance@latest search "<query>" --skill-version ...', 'retrieve "<id>"', 'legacy-scan <path> --json') with concrete good/bad query examples and edge-case handling (rephrase weak searches once, read >9.5 KB temp output in full, offline retry). This matches the fully-executable anchor covering common cases.

5 / 5

Workflow Clarity

The 4-step primary workflow has explicit decision branches (match → retrieve; weak → rephrase once then list; not covered → proceed) and a verification checkpoint (Step 3 cross-check against the retrieved guide before concluding), while the modernization flow includes keepWhen/dropWhen verification and a re-run of legacy-scan on modified files to confirm resolution — explicit validation with feedback loops.

5 / 5

Progressive Disclosure

No bundle files exist, and the body is well-sectioned, delegating bulk detail to the external tool's retrieved guides so SKILL.md functions as an overview — good structure, anchor 4. It misses 5 because at ~90 lines, inline sections like 'Interpreting Browser Support & Fallbacks' and the Step 4 disclosure spec are detail that could be split out or tightened.

4 / 5

Total

18

/

20

Passed

Description

86%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 explicit what/when structure, an unusually thorough natural-keyword trigger list, and a well-scoped exclusion list. The main gap is that only the search action is described, while the retrieve and legacy-scan capabilities the skill actually provides go unmentioned.

Suggestions

Mention the retrieve (fetch full guides by id) and legacy-scan (detect legacy patterns for modernization) actions alongside 'Search tool' so the capability list is comprehensive, not just the single search action.

Soften or narrow the 'Execute FIRST for all HTML/CSS and clientside JS tasks' claim to reduce collision risk with other frontend-specific skills the user may have installed.

DimensionReasoningScore

Specificity

The description names the domain ('modern web development best practices') and a single concrete action ('Search tool'), but capabilities exercised in the body such as retrieve and legacy-scan modernization scanning are not mentioned, leaving action coverage incomplete. It sits at anchor 3 ('names domain and 1-2 concrete actions, but not comprehensive') rather than 4 because only one action is listed.

3 / 5

Completeness

It explicitly answers both what ('Search tool for modern web development best practices') and when ('Trigger immediately for: ...' plus an explicit 'DO NOT trigger for: ...' exclusion list) with concrete trigger phrases. This is the anchor-5 pattern of clearly and explicitly answering both what AND when.

5 / 5

Trigger Term Quality

Trigger terms are comprehensive and natural — 'modals/dialogs/popovers, tables, dark mode, anchor positioning, container queries, view transitions... forms, validation, autofill, accessibility, custom selects, scrollbars, CWV (LCP, INP, CLS)... passkeys, HTML sanitization, web components, dates/timezones' — including synonyms and expanded abbreviations. This matches the anchor for comprehensive coverage of natural terms including synonyms.

5 / 5

Distinctiveness Conflict Risk

The frontend niche is clear and the explicit negative triggers ('backend (SQL, ORMs, API routes), infra/scripts (CI/CD, Docker, Actions...), or tooling/trivial') sharply reduce overlap risk, earning mostly-distinct anchor 4. It falls short of 5 because 'Execute FIRST for all HTML/CSS and clientside JS tasks' claims an sweeping scope that could overlap with other frontend-oriented skills.

4 / 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

englishstreetventures/osn

Path

.agents/skills/modern-web-guidance/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.