CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

browser-to-code

Gather context from Chrome browser tabs (Jira, Figma, docs) and hand off to a workflow skill (brainstorming, planning, debugging, code review)

Quality

80%

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 ./browser-to-code/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%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 tight, executable orchestrator skill: concrete commands with explicit failure handling, user confirmation checkpoints, and a feedback loop. The only weaknesses are a redundant sentence pair in the handoff phase and an undefined '<target>' placeholder in the extraction commands.

DimensionReasoningScore

Conciseness

The body is operational throughout — concrete commands, exact failure messages, and a compact summary template — assuming Claude's competence with no concept-teaching padding. Minor trimming is possible, mainly the redundant restatement in Phase 3 that the context is 'already in the conversation' and the downstream skill 'will see them' / 'will have full visibility'.

4 / 5

Actionability

Guidance is mostly copy-paste ready: 'cdp.mjs list', 'shot <target> /tmp/browser-to-code-design.png', 'snap <target>', exact user-facing error messages, and a workflow table mapping options to skill names. The '<target>' placeholder is never defined (tab id? title?), leaving a minor gap versus fully executable guidance.

4 / 5

Workflow Clarity

The flow is explicitly sequenced across three phases with per-error-type handling at Step 1 ('File not found → ...', 'Connection error → ...', 'Empty list → ...'), a feedback loop ('If the user wants changes, go back to Step 2'), a confirmation checkpoint ('Does this context summary look complete?'), and error recovery ('skip it with a warning and continue'). The skill is read-only, so the destructive/batch validation cap does not apply.

5 / 5

Progressive Disclosure

No bundle files exist and none are needed: every line is in-flow operational content (commands, prompts, one summary template, one workflow table), nothing that belongs in a separate reference file is inlined, and navigation is easy via the top-level flow diagram plus clearly headed phases.

5 / 5

Total

18

/

20

Passed

Description

66%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 specific, well-scoped description with good natural trigger terms and low conflict risk. Its main weakness is the missing 'when to use' clause, which caps completeness and weakens trigger discoverability.

Suggestions

Add an explicit trigger clause, e.g., 'Use when the user has relevant context open in Chrome tabs (a Jira ticket, Figma design, or docs) and wants to start a development workflow.'

Include common synonyms users would say — 'ticket', 'issue', 'browser context', 'mockup' — to broaden natural trigger coverage.

Mention the summarization/confirmation step so the 'what' covers the full capability (gather → summarize → confirm → hand off).

DimensionReasoningScore

Specificity

The description lists several concrete actions — 'Gather context from Chrome browser tabs (Jira, Figma, docs)' and 'hand off to a workflow skill (brainstorming, planning, debugging, code review)' — with named sources and workflow types in third-person voice. Minor gaps in coverage (e.g., tab selection, content extraction, summarization) keep it below the comprehensive level 5.

4 / 5

Completeness

The 'what' is clear (gather browser context, hand off to a workflow skill), but there is no 'Use when...' clause or equivalent explicit trigger guidance; the 'when' is only weakly implied by the parenthetical source and workflow lists, which caps completeness at 3.

3 / 5

Trigger Term Quality

'Chrome browser tabs', 'Jira', 'Figma', 'docs', 'debugging', and 'code review' are natural phrases users would say when needing this skill. A few natural terms are missing — e.g., 'ticket', 'issue', 'browser context', 'mockup' — so it does not reach comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The niche — extracting context from live Chrome tabs and routing to a workflow — is distinct, with source and workflow names that differentiate it. Minor overlap risk remains with the underlying chrome-cdp skill and generic workflow-orchestration skills.

4 / 5

Total

15

/

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

fernandezbaptiste/claude-playground-explorer

Path

browser-to-code/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.