notte

Deploy browser automations as scheduled, API-callable serverless Functions — plus stealth sessions, vault-backed login, captcha solving, and natural-language agent runs via the Notte CLI. Turns any browser flow into a deterministic Bitterbot-callable endpoint, ideal for crystallized skills + dream-engine cron schedules.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/notte/SKILL.md

Quality

Content

75%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 strong, terse CLI reference with excellent command coverage, clear sequencing, and useful decision guidance versus bundled tools. The main gaps are non-runnable Functions commands missing function_id, minor duplication across Tips/Troubleshooting, and reference-shaped tables inlined in the single file.

Suggestions

Make the Functions workflow fully runnable by showing the function_id argument, e.g. 'notte functions run --function-id <function_id>' and 'notte functions schedule-set --function-id <function_id> --cron "0 */2 * * *"'.

Deduplicate the Lightpanda '--headless=false' caveat and the '@B3 wrong element' fallback — keep each in one place (Troubleshooting) and drop the repeats.

Consider moving the page-actions cheat sheet and environment-variable table into a references/ file to slim the main SKILL.md body.

Dimension	Reasoning	Score
Conciseness	The body is command-dense with tables and copy-paste blocks and assumes Claude's competence, but has trimmable redundancy — the Lightpanda '--headless=false' caveat appears in the stealth flags table, Tips, and Troubleshooting, and the '@B3 wrong element' advice is duplicated.	4 / 5
Actionability	Mostly executable copy-paste commands throughout (quick start, vault, agents, page actions), but the flagship Functions workflow shows 'notte functions run', 'schedule-set', and 'fork' without the required function_id argument, so those commands are not runnable as written.	4 / 5
Workflow Clarity	Multi-step flows are clearly sequenced (capture → create → run/schedule; start → goto → observe → scrape → stop) with error-recovery guidance in Tips and Troubleshooting, though checkpoints are advisory rather than embedded as explicit validate-before-proceeding steps.	4 / 5
Progressive Disclosure	No bundle files exist, and the single-file skill is well organized with clear section headers; the page-actions cheat sheet, env-var table, and troubleshooting table are defensible inline but are reference-shaped content that could be split out.	4 / 5
	Total	16 / 20 Passed

Description

71%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, action-rich description that clearly states what the tool does, weakened by the absence of an explicit 'Use when...' trigger clause and some missing natural trigger synonyms. It is distinct from neighboring browser/scraping skills thanks to named capabilities and the Functions/scheduling angle.

Suggestions

Add an explicit trigger clause, e.g. 'Use when deploying or scheduling browser automations, scraping sites behind logins/captchas/Cloudflare, or running headless browser tasks as API endpoints.'

Include natural synonyms users would actually say — 'web scraping', 'anti-bot', 'Cloudflare bypass', 'headless browser' — to improve trigger-term coverage.

Trim the environment-specific 'Bitterbot-callable endpoint, ideal for crystallized skills + dream-engine cron schedules' phrasing, which reads as internal jargon rather than trigger guidance.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'deploy browser automations as scheduled, API-callable serverless Functions', 'stealth sessions', 'vault-backed login', 'captcha solving', 'natural-language agent runs' — with comprehensive coverage of the tool's capabilities and no notable gaps, in third-person voice.	5 / 5
Completeness	The 'what' is explicit and concrete, but the 'when' is only weakly implied via 'ideal for crystallized skills + dream-engine cron schedules' with no explicit 'Use when...' trigger clause, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Natural terms like 'browser automations', 'captcha', 'cron schedules', and 'login' are present, but common user phrasings such as 'web scraping', 'anti-bot', 'Cloudflare', or 'headless browser' are missing.	4 / 5
Distinctiveness Conflict Risk	The named Notte CLI and distinctive capabilities (serverless Functions, vault-backed login, stealth proxies) carve a clear niche, but the crowded browser-automation/scraping space leaves minor overlap risk.	4 / 5
	Total	16 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: Bitterbot-AI/bitterbot-desktop
Path: skills/notte/SKILL.md
Commit: 1c7dc1b

Reviewed: 20 hours 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.