CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

browse

Drive a real stealth browser from your shell — act on websites (order food, file an expense, pull data behind a login), with per-person persistent sign-ins kept in the person's browser profile (Kernel, Anchor, Browserbase, or Browser Use — picked by which API key you have). Use for ACTING on a site; to just read a page, use curl/wget first. Requires managed model access and a keychain grant for the browser provider key; follow the missing-key steps below.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills-seed/browse/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

66%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 workflow itself is excellently engineered — clear sequencing, typed outcomes, error-recovery loops, and a genuine consent gate for spending — and the shared runner is copy-paste ready. The bundle is broken as shipped, though: every provider-specific step delegates to provider docs that are missing from the bundle, and heavy operational detail is inlined in SKILL.md rather than split into reference files.

Suggestions

Ship the referenced bundle files (providers/kernel.md, providers/anchor.md, providers/browserbase.md, providers/browser-use.md, and install-runtime.sh) or inline minimal create/cleanup commands — as delivered, steps 1 and 3 of the workflow point to files that do not exist.

Move the keychain credential-check/bootstrap procedures and the full runner script into a reference file, keeping SKILL.md as a concise overview of the provider-selection, run, and cleanup flow.

Trim duplicated guidance (the acting-vs-reading rule appears in both the description and the intro) and tighten the wordy profile-security prose into short imperative rules.

DimensionReasoningScore

Conciseness

The content is almost entirely non-obvious operational detail (keychain flows, provider selection, security rules) with no explanation of concepts Claude already knows, but several passages could be tightened: the intro paragraph repeats the description's acting-vs-reading guidance nearly verbatim, the "BROWSE_LAB_* names are historical" aside, and multi-clause security prose that takes 40 words per 15-word rule. This fits anchor 3 (some unnecessary explanation, could be tightened) better than 4's "minor instances".

3 / 5

Actionability

The shared flow is fully executable and copy-paste ready: the complete runner script, installer invocation, exact keychain curl commands with JSON payloads, wall-URL extraction one-liner, nav script, and a concrete authorized-spend task example ("checkout authorized up to $25 total"). Not 5 because the browser-create and cleanup steps — the entry and exit of the whole workflow — contain no executable command in the bundle, delegating entirely to provider docs that are not present.

4 / 5

Workflow Clarity

The sequence (pick provider → prerequisites → create → run → clean up → report) is explicit with strong validation checkpoints and feedback loops: typed outcome JSON with distinct done/signin_needed handling, wall-URL sanity-check against the task domain (prompt-injection defense), dead-key 401/403 fallback to the next provider, retry-once guidance for the auth race, installer-failure reporting, and a pre-launch consent gate with spending ceiling for money-spending tasks.

5 / 5

Progressive Disclosure

The body's reference design is well-signaled and one level deep ("Read `providers/kernel.md`" per provider), but the referenced files — providers/kernel.md, anchor.md, browserbase.md, browser-use.md, and install-runtime.sh — do not exist in the bundle (no references/, scripts/, or assets/ directories), so navigation dead-ends at every provider-shaped step. Additionally, content that clearly belongs in separate files (the ~50-line runner script, keychain ask/drop procedures) is inlined in SKILL.md, matching anchor 2 (inlined content that belongs in separate files) rather than anchor 3, whose "references present but not clearly signaled" does not describe this case — here references are clearly signaled but absent.

2 / 5

Total

14

/

20

Passed

Description

82%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 that explicitly answers both what and when (including when NOT to use it) with natural trigger phrases and a sharp boundary against plain fetching. Its only defect is second-person phrasing ("your shell", "you have"), which costs it specificity under the rubric's voice rule.

DimensionReasoningScore

Specificity

Concrete actions are present ("act on websites (order food, file an expense, pull data behind a login)", "per-person persistent sign-ins"), which would rate 4, but the description uses second-person voice ("from your shell", "picked by which API key you have"), which the rubric penalizes by reducing specificity by 1. It stays at 3 rather than 2 because multiple concrete capabilities are named, not just a domain.

3 / 5

Completeness

Both what ("Drive a real stealth browser from your shell — act on websites… with per-person persistent sign-ins") and when ("Use for ACTING on a site; to just read a page, use curl/wget first") are explicit, with a concrete negative trigger boundary. Not 4 because the when-clause is fully explicit rather than merely present.

5 / 5

Trigger Term Quality

Natural phrases users would say appear directly: "order food", "file an expense", "pull data behind a login", "sign-ins", "read a page". Not 5 because common synonyms like "scrape", "book", "fill out a form", "log in", or "checkout" are missing.

4 / 5

Distinctiveness Conflict Risk

The acting-vs-reading boundary ("Use for ACTING on a site; to just read a page, use curl/wget first") sharply separates it from generic fetch/web skills, and named providers (Kernel, Anchor, Browserbase, Browser Use) plus CDP-driven stealth browsing define a clear niche with minimal conflict risk.

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

yc-software/qm

Path

skills-seed/browse/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.