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

72%

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

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with executable commands and clear workflows, and is well-structured into navigable sections. Its main weakness is progressive disclosure — everything lives inline in one long file rather than being split across reference files — with minor conciseness padding.

Suggestions

Move the page-actions cheat sheet, stealth-flag table, environment variables, and troubleshooting table into one or more reference files (e.g. `references/page-actions.md`, `references/troubleshooting.md`) and link to them from SKILL.md.

Trim the "Why this matters for Bitterbot" prose and the "Agents are cheaper..." aside to keep the overview lean.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient — commands, tables, and flag references — but includes unnecessary prose such as the "Why this matters for Bitterbot" bullets and "Agents are cheaper than authoring step-by-step CLI calls," which could be trimmed. Not score 3 because of this explanatory padding.	2 / 3
Actionability	It provides fully executable bash and curl commands that are copy-paste ready (e.g. `notte functions create --file workflow.py`, the curl invocation), plus concrete flag and page-action cheat sheets.	3 / 3
Workflow Clarity	The Functions section lays out a clear numbered deploy/run/schedule sequence, and the troubleshooting table plus "Stop sessions you start" tip provide error-recovery feedback loops; no destructive/batch validation is required here.	3 / 3
Progressive Disclosure	Sections are well-organized, but the skill is a single monolithic ~200-line file with no external references, and content that could be split out (page-action cheat sheet, stealth flags, env vars, troubleshooting) is inline. Not score 3 because no references exist and the file exceeds the under-50-line simple-skill carve-out.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 is specific and distinctive, naming several concrete capabilities of the Notte CLI, but its trigger phrasing leans on ecosystem jargon and lacks an explicit natural-language "Use when..." clause. This weakens completeness and trigger-term quality despite strong specificity.

Suggestions

Add an explicit, plain-language trigger clause such as "Use when deploying a recurring browser flow as a scheduled API endpoint, or when the bundled browser is blocked by captcha/anti-bot defenses."

Replace ecosystem-internal jargon ("Bitterbot-callable," "crystallized skills," "dream-engine") with terms users would naturally say, or relegate them to a secondary clause.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "Deploy browser automations as scheduled, API-callable serverless Functions," "stealth sessions, vault-backed login, captcha solving," and "natural-language agent runs" — rather than vague language.	3 / 3
Completeness	"What" is clearly stated, but the "when" is only implied via "ideal for crystallized skills + dream-engine cron schedules" rather than an explicit "Use when..." trigger clause, which caps completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	It includes some relevant keywords ("browser automations," "captcha solving," "stealth sessions") but is heavily jargon-laden ("Bitterbot-callable endpoint," "crystallized skills," "dream-engine cron schedules") and misses common natural phrasings a user would say. Not score 3 because the natural-term coverage is thin and domain-internal.	2 / 3
Distinctiveness Conflict Risk	It carves a clear niche tied to the Notte CLI / serverless browser Functions ecosystem with distinct triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 12 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: e73c717

Reviewed: about 16 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.