CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

agentlas-browser

Use the Agentlas browser hardpoint for browser-required work.

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./kimi/skills/agentlas-browser/SKILL.md
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.

The body is an exemplarily lean delegation alias: it gives a precise, unambiguous instruction with an exact reference path and effective anti-drift guardrails ("do not summarize `hep-browser/SKILL.md` from memory"). Its only weakness is total dependence on the sibling skill with no fallback if it is missing.

DimensionReasoningScore

Conciseness

The ~10-line body is lean and efficient: "Locate the sibling skill directory `hep-browser` ... read its `SKILL.md`, and follow its instructions exactly" with no padding and no explanation of concepts Claude already knows. Every token earns its place.

5 / 5

Actionability

The guidance is concrete and executable — an exact relative path ("`../hep-browser/SKILL.md` relative to this file"), an explicit read-and-follow instruction, and a precise argument-passing rule ("treating everything typed after `/skill:agentlas-browser` as that command's request"). It falls short of 5 only because the skill's actual behavior is entirely defined in an external file with no fallback or error handling if the sibling skill cannot be located.

4 / 5

Workflow Clarity

This is a simple single-task skill (delegate to hep-browser) whose single action is unambiguous: locate the sibling skill, read its SKILL.md, follow it exactly. No destructive or batch operations are involved, so no validation checkpoints are required, and the simple-skill exception applies.

5 / 5

Progressive Disclosure

The body is a concise overview that delegates all detail to a single, clearly signaled, one-level-deep reference with its exact path ("`../hep-browser/SKILL.md` relative to this file, under the same `kimi/skills/` root"). No bundle files exist to reorganize, and navigation is trivial.

5 / 5

Total

19

/

20

Passed

Description

53%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.

The description names a distinctive, niche tool but does little else. It lacks an explicit "Use when..." trigger clause, natural trigger phrases, and any statement of concrete capabilities, leaving the what and when only weakly specified.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to open web pages, click through a browser flow, or run /agentlas browser commands."

Include natural terms and synonyms users would actually say (web page, navigate, screenshot a site, browser automation) alongside "browser-required work".

State concretely what the hardpoint does (e.g. "drives a real browser session to complete the request") so the what is more than a bare directive.

DimensionReasoningScore

Specificity

"Use the Agentlas browser hardpoint" names one concrete action tied to a specific tool, matching the anchor for domain plus 1-2 concrete actions. It is above score 2 because the action is specific rather than generic, but below score 4 because no coverage of what the hardpoint actually does is provided.

3 / 5

Completeness

"Use the Agentlas browser hardpoint" states a directive-level what, and "for browser-required work" only weakly implies when, with no explicit "Use when..." trigger guidance — per the judging guidelines this caps completeness at 3. It is not score 4 because the when clause lacks any concrete trigger phrase and the what is a bare directive.

3 / 5

Trigger Term Quality

"browser" and "browser-required work" are relevant domain keywords, but common natural variations (web page, navigate, scrape, browser automation) are missing. Not score 2 because "browser" is domain-relevant rather than generic; not score 4 because almost no natural user phrasing is present.

3 / 5

Distinctiveness Conflict Risk

"Agentlas browser hardpoint" is a uniquely named tool giving a clear niche, so it is mostly distinct with only minor overlap risk. It is not score 5 because "browser-required work" is broad enough to overlap with other browser-automation skills, and not score 3 because the named hardpoint is far more specific than generic phrasing like "Works with document files".

4 / 5

Total

13

/

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

agentlas-ai/Agentlas-OS

Path

kimi/skills/agentlas-browser/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.