CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ultimate-browsing

Reaches web pages the user's browser cannot open: WAF-blocked and bot-scored hosts, platform-native readers (Chinese and social platforms), archive snapshots with provenance, and a browser you own for stealth or throwaway profiles. Not for plain search, an unblocked static fetch, or a page the user's browser can open.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

An excellent routing-and-execution skill body: copy-paste-ready commands for all three tiers, an explicit escalation feedback loop, and built-in validation/provenance checkpoints. The only notable nit is that routing guidance appears in three overlapping forms, which slightly dents token efficiency.

DimensionReasoningScore

Conciseness

Dense and padding-free — no concept explanations, assumes competence throughout ("the read; refs come from it", "never presented as the live page"). Routing information is restated in three forms (Phase 0 diagram, per-tier "When" lines, "Escalate to..." bullets), which is minor trimmable redundancy, so it fits anchor 4 rather than the every-token-earns-its-place of anchor 5.

4 / 5

Actionability

Fully executable, copy-paste-ready guidance covering every tier's common cases: `python3 -B -m engine "<URL>"` with flag documentation, the yt-dlp subtitle command, `mcporter call 'douyin.parse_douyin_video_info(...)'`, curl examples, the complete connectPipe JS loop with try/finally and cleanup, and extract_cookies.py invocations with concrete flags. Placeholders like `<browser-skill-root>` are environment-dependent but justified.

5 / 5

Workflow Clarity

A mandatory route-first decision tree (Phase 0) gives a clear sequence; an explicit error-recovery feedback loop exists ("Tier 1/1.5 returned empty or partial → Tier 2 2a owned engine"); and validation checkpoints are explicit: `--selector` for "positive-proof validation", "A stealth binary is not proof of access: inspect the rendered result and report challenges that remain", and provenance rules for snapshot results. This matches anchor 5; it is above anchor 4 because checkpoints are explicit rather than implicit.

5 / 5

Progressive Disclosure

The body is a clear overview with a Reference docs table specifying "When to read" each file; per-category references (social.md, web.md, video.md, career.md, dev.md, search.md) are directly linked in the agent-reach table; deep-dives sit one hub-hop away in insane-search/README.md, not in nested chains. Every referenced path was verified to exist in the bundle. This matches anchor 5's clear, well-signaled, easy-to-navigate structure.

5 / 5

Total

19

/

20

Passed

Description

87%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: concrete, well-scoped, and unusually disciplined about negative triggers, which makes routing unambiguous. The only gaps are a few missing natural trigger synonyms (403, Cloudflare) and the single-verb framing of capabilities.

DimensionReasoningScore

Specificity

Enumerates concrete capability categories — "WAF-blocked and bot-scored hosts", "platform-native readers (Chinese and social platforms)", "archive snapshots with provenance", "a browser you own for stealth or throwaway profiles" — but hangs them all on the single verb "Reaches" rather than multiple distinct actions, matching anchor 4 (several specifics, minor gaps) rather than the multi-action comprehensiveness of anchor 5.

4 / 5

Completeness

Explicitly answers both: the "what" is the enumerated reach capability, and the "when" is delivered as equivalent explicit trigger guidance — the opening scope clause "web pages the user's browser cannot open" plus the concrete negative triggers "Not for plain search, an unblocked static fetch, or a page the user's browser can open". This clearly matches anchor 5 rather than anchor 4, where the 'when' would be less explicit.

5 / 5

Trigger Term Quality

Includes natural phrases users would say — "web pages the user's browser cannot open", "WAF-blocked", "Chinese and social platforms", "archive snapshots" — but misses the most common user phrasings for this need ("403", "Cloudflare", "can't access"). Good coverage with a few natural terms missing fits anchor 4, not the synonym-complete anchor 5.

4 / 5

Distinctiveness Conflict Risk

The explicit exclusion clause ("Not for plain search, an unblocked static fetch, or a page the user's browser can open") cleanly fences off web search and the general browser skill, giving a clear niche with minimal conflict risk — anchor 5.

5 / 5

Total

18

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 13 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 2 missing, 30 deeper-than-1-level

Warning

Total

14

/

16

Passed

Repository

code-yeongyu/lazycodex

Path

plugins/omo/skills/ultimate-browsing/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.