CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

setup-browser-cookies

Import cookies from your real Chromium browser into the headless browse session. Opens an interactive picker UI where you select which cookie domains to import. Use before QA testing authenticated pages. Use when asked to "import cookies", "login to the site", or "authenticate the browser".

Quality

76%

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 ./skills/gstack/.agents/skills/gstack-setup-browser-cookies/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 actual cookie-import instructions are excellent — fully executable commands, clear sequencing with a stop-and-ask setup branch, and an explicit verification step. However, the body is dominated by auto-generated gstack framework boilerplate (telemetry, onboarding prompts, contributor/plan-mode protocols) that consumes most of the token budget and buries the skill content at the bottom of the file.

Suggestions

Move the shared gstack boilerplate (Preamble, Voice, Contributor Mode, Completion Status Protocol, Telemetry, Plan Status Footer) into a shared reference file or trim it drastically — it consumes ~75% of the body and competes with the actual cookie-import task for context (conciseness).

Restructure so the skill content leads: the title "# Setup Browser Cookies" currently appears after ~250 lines of boilerplate, and "## SETUP" (h2) sits inside "### 1. Find the browse binary" (h3); promote the skill sections to the top with a consistent heading hierarchy (progressive_disclosure, workflow_clarity).

Add a recovery path for the verify step: if "$B cookies" shows no imported cookies, state what to check next (e.g., re-open the picker, confirm macOS Keychain or Linux libsecret/secret-tool access) to close the validate-fix-retry loop (workflow_clarity).

DimensionReasoningScore

Conciseness

Roughly 250 of the ~340 body lines are auto-generated gstack framework boilerplate (Preamble telemetry, lake-intro/telemetry/proactive onboarding prompts, Contributor Mode, Plan Status Footer) unrelated to cookie importing, though the skill-specific sections at the end are lean. This is noticeably verbose with many padded sections; it avoids a 1 only because no space is spent explaining concepts Claude already knows.

2 / 5

Actionability

Every step provides copy-paste bash: "$B status ... | grep -q \"Mode: cdp\"", the SETUP binary check, the bun install command, "$B cookie-import-browser", "$B cookie-import-browser comet --domain github.com", and "$B cookies" for verification. The commands are fully executable and cover the common cases (CDP already connected, needs setup, picker flow, direct domain import); the only placeholders (<SKILL_DIR>, "Replace comet") are trivially resolvable.

5 / 5

Workflow Clarity

The skill workflow is clearly sequenced — CDP mode check, binary setup with a NEEDS_SETUP stop-and-wait branch and bun fallback, picker, then an explicit verify step ("$B cookies" with a domain-count summary). Not a 5 because there is no recovery path if verification shows no imported cookies, and the flow is obscured by an h2 "## SETUP" nested under h3 "### 1" plus interleaved boilerplate sections.

4 / 5

Progressive Disclosure

Section headers exist and there are no broken or nested references, but all content is inlined in one monolithic file with no bundle files or external references. The ~250 lines of template-generated framework boilerplate are exactly the content that belongs in a separate shared file; this fits 'some structure but could be better organized; content that should be separate is inline' rather than a 2, since real section structure is present.

3 / 5

Total

14

/

20

Passed

Description

78%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 clearly and explicitly states both what the skill does and when to use it, with concrete natural-language trigger phrases in third-person voice. The main gaps are limited action coverage (only two concrete actions) and slightly broad login/auth trigger phrases that could overlap with other skills.

DimensionReasoningScore

Specificity

"Import cookies from your real Chromium browser into the headless browse session" and "Opens an interactive picker UI where you select which cookie domains to import" name the domain plus exactly two concrete actions. This matches the anchor for 1-2 concrete actions without comprehensive coverage; it is not a 4 because several specific actions (direct domain import, verification, browser auto-detection) are omitted.

3 / 5

Completeness

Explicitly answers what ("Import cookies from your real Chromium browser into the headless browse session") and when with concrete trigger phrases ("Use before QA testing authenticated pages. Use when asked to 'import cookies', 'login to the site', or 'authenticate the browser'"). Clearly matches the top anchor; not a 4 because the 'when' is explicit and specific rather than merely present.

5 / 5

Trigger Term Quality

Includes natural phrases users would actually say: "import cookies", "login to the site", "authenticate the browser", plus "QA testing authenticated pages". Good keyword coverage, but not a 5 because common synonyms such as "sign in", "logged-in session", or "session cookies" are missing.

4 / 5

Distinctiveness Conflict Risk

The cookie-import-into-headless-browse niche is clear and "import cookies" is a distinct trigger. Not a 5 because "login to the site" and "authenticate the browser" are broad enough to carry minor overlap risk with generic auth/login skills, matching the 'mostly distinct; minor overlap risk' anchor.

4 / 5

Total

16

/

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

valeriibeck-star/claude-skills

Path

skills/gstack/.agents/skills/gstack-setup-browser-cookies/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.