core-agent-browser

Internal support skill for agent-browser CLI workflows used by rust-learner, docs-researcher, and crate-researcher. Use only when browser automation is explicitly required.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/core-agent-browser/SKILL.md

Quality

Content

82%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 lean, highly actionable command reference with clear sequencing and good organization; the main gaps are minor Quick-start/Commands redundancy and the absence of an explicit validate-retry feedback loop and any one-level-deep reference file.

Suggestions

Add an explicit verify/feedback step to the Core workflow (e.g. 'after interaction, re-snapshot and confirm the expected element changed; if not, retry'), to push workflow clarity toward 5.

Either collapse the duplicated Quick-start commands into a pointer to the Commands section, or move the full command catalog into a REFERENCES.md and keep Quick start inline, to tighten conciseness and improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean command reference with inline comments and no padding about browser concepts, but the Quick start block repeats several commands (open/snapshot/click/fill/close) that reappear in the Commands section, a minor redundancy that keeps it at anchor 4 rather than 5.	4 / 5
Actionability	Commands are fully executable and copy-paste ready, with concrete @ref usage and a complete form-submission example covering the common case, matching anchor 5.	5 / 5
Workflow Clarity	The Core workflow lists a clear sequenced process (Navigate -> Snapshot -> Interact -> Re-snapshot) with the re-snapshot-after-DOM-change checkpoint, but lacks an explicit validate/fix/retry feedback loop beyond that, fitting anchor 4 rather than 5.	4 / 5
Progressive Disclosure	Content is well organized into clearly headed sections (Quick start, Core workflow, Commands, Example) with no nested references, but no bundle files exist and the full command catalog is inlined rather than split into a one-level-deep reference, so it sits at anchor 4 rather than 5.	4 / 5
	Total	17 / 20 Passed

Description

61%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 well-scoped, distinct description with explicit when-to-use guidance, but it stays at the tool/domain level and omits concrete capabilities and natural trigger synonyms that would improve specificity and trigger-term coverage.

Suggestions

Add 1-2 concrete capabilities to raise specificity, e.g. '...browser automation — navigate, snapshot, click/fill elements, and screenshot'.

Include natural trigger synonyms users actually say, such as 'fill forms', 'take screenshots', or 'scrape page', alongside 'browser automation'.

Dimension	Reasoning	Score
Specificity	The description names the domain ('agent-browser CLI workflows', 'browser automation') and the consuming skills, but lists no concrete actions (e.g. click, fill, snapshot); actions are minimal/generic, matching anchor 2 rather than 3 which requires 1-2 concrete actions.	2 / 5
Completeness	It answers both 'what' (agent-browser CLI workflows) and 'when' ('Use only when browser automation is explicitly required'); the 'when' is explicit but the 'what' stays tool-level rather than capability-level, so it sits at anchor 4 rather than 5 which demands concrete trigger phrases.	4 / 5
Trigger Term Quality	It includes relevant keywords ('browser automation', 'agent-browser') but misses common natural variations and synonyms a user would say ('fill form', 'screenshot', 'scrape', 'click'), fitting anchor 3 (some relevant keywords but missing common variations).	3 / 5
Distinctiveness Conflict Risk	It carves a clear niche scoped to specific consumer skills (rust-learner, docs-researcher, crate-researcher) with an explicit usage restriction, giving distinct triggers and minimal conflict risk per anchor 5.	5 / 5
	Total	14 / 20 Passed

Validation

100%

Warnings & errors only

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: actionbook/rust-skills
Path: skills/core-agent-browser/SKILL.md
Commit: 5c40d3a

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

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.