CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

browser-ops-skill

Triggered when the user asks for page-level interaction with a specific webpage: login, form filling, button clicks, pagination scraping, screenshots, downloading page images, handling CAPTCHAs or anti-bot measures, accessing SPA dynamic content; also used as a fallback when WebFetch returns an empty shell or gets blocked. Typical phrasing: "log me into X then scrape Y", "take a screenshot". **Not for**: factual questions or "what is xx" (→ `WebSearch`), or simply reading static webpage text (try `WebFetch` first).

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

Excellent operational content: concrete executable tool invocations, three well-sequenced workflows with explicit verification checkpoints, decision trees for error recovery, and a clear security/anti-bot policy. The only weakness is minor redundancy between the Iron Rules recap and earlier sections, which costs a few tokens without adding new information.

Suggestions

Trim the Iron Rules section to rules not already stated verbatim earlier, or fold them into the relevant sections, to remove repetition.

Replace the motivational framing ("Screenshots are a debugging superpower", "the single most common failure mode") with terse imperatives to save tokens.

DimensionReasoningScore

Conciseness

The body is efficient and assumes Claude's competence (no explanations of what a browser or iframe is), but the "Iron Rules" section recapitulates six rules already stated in earlier sections, and the Core Mental Model loop is restated in the workflows. These minor repetitions could be trimmed.

4 / 5

Actionability

Guidance is copy-paste ready throughout: concrete parameterized calls such as `BrowserAct { action: "click-css", selector: "button[type=submit]" }`, `BrowserWait { type: "urlIncludes", url: "/success" }`, `BrowserDownloadImage { selector: ".product-image" }`, and the `ToolSearch(names: …)` activation call, with common cases covered.

5 / 5

Workflow Clarity

The three workflows are clearly sequenced with explicit validation checkpoints (snapshot after every action, `BrowserWait { type: "urlIncludes" }` to confirm login success, snapshot on every pagination page), the Error Diagnosis section provides feedback loops for recovery, and the Iron Rules act as a checklist. Pagination scraping includes per-page verification, so batch operations are not left unvalidated.

5 / 5

Progressive Disclosure

The skill is a single self-contained file with no bundle references; all content (tool inventory, modes, workflows, error handling) is core operational guidance that appropriately lives in SKILL.md. Sections are well-organized with clear headers, making navigation easy, and nothing that belongs in a separate file is inlined.

5 / 5

Total

19

/

20

Passed

Description

92%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 names concrete capabilities, gives explicit trigger conditions with quoted example phrasing, defines a fallback use case, and cleanly delineates what it is not for. The only gap is a handful of missing natural trigger synonyms, which keeps trigger term coverage just short of comprehensive.

Suggestions

Add a few more natural user phrasings such as "scrape a website", "click this button", or "automate a webpage" to make trigger term coverage fully comprehensive.

Consider mentioning "web scraping" or "crawling" explicitly as synonyms of pagination scraping to catch users who phrase it that way.

DimensionReasoningScore

Specificity

The description enumerates many concrete actions — "login, form filling, button clicks, pagination scraping, screenshots, downloading page images, handling CAPTCHAs or anti-bot measures, accessing SPA dynamic content" — giving comprehensive coverage of the skill's capabilities, matching the anchor for multiple specific concrete actions.

5 / 5

Completeness

Both what ("page-level interaction with a specific webpage: login, form filling, …") and when ("Triggered when the user asks…", "Typical phrasing…", plus a fallback condition and a **Not for** exclusion list) are explicitly and concretely answered with trigger phrases.

5 / 5

Trigger Term Quality

Natural phrases users would say are present and even quoted ("log me into X then scrape Y", "take a screenshot") alongside terms like login, form filling, screenshots, and CAPTCHA. A few common phrasings (e.g., "scrape a website", "click a button", "automate a page") are absent, so coverage is good but not fully comprehensive.

4 / 5

Distinctiveness Conflict Risk

It carves out a clear niche (page-level browser interaction) and explicitly routes away overlapping cases — factual questions (→ WebSearch) and static text reading (→ WebFetch first) — minimizing conflict risk with related skills.

5 / 5

Total

19

/

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

itsablabla/openloaf-web

Path

apps/server/src/ai/builtin-skills/browser-ops/en/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.