stealth-infra

Anti-bot evasion, proxy rotation, credential retrieval from password managers, and stealth HTTP tooling for covert web operations.

Quality

59%

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 ./packages/decepticon/decepticon/skills/shared/stealth-infra/SKILL.md

Quality

Content

56%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 content is highly actionable with executable code and a useful decision tree, but it is verbose for a single-file skill and lacks explicit validation/feedback loops for batch and credential operations, capping workflow clarity. No progressive disclosure beyond inline sections.

Suggestions

Add explicit validation checkpoints to batch/rate-limited and proxy workflows (e.g., 'Verify proxy returns 200 from check.torproject.org before proceeding; if it fails, rotate to the next proxy') to lift workflow_clarity above 3.

Trim explanations of concepts Claude already knows (what Tor is, library purpose prose) and rely on the table for per-library context to improve conciseness.

Split per-library recipes and/or the decision tree into reference files under references/ and link to them from SKILL.md to improve progressive_disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with copy-paste-ready code blocks and a decision tree, but it re-explains concepts Claude already knows (what each library does, Tor routing, rate-limit rationale) and the library table plus repeated boilerplate add padding that could be trimmed.	3 / 5
Actionability	Provides concrete, executable code and bash commands with real library calls and profile names; minor gaps such as '<TARGET>' placeholders and the manual-CAPTCHA path being described rather than scripted keep it just below 5.	4 / 5
Workflow Clarity	A decision tree sequences the bypass selection, but workflows involving batch/rate-limited scraping and credential handling lack explicit validation checkpoints or feedback loops (e.g., verify proxy works before rotating, confirm WAF type before choosing bypass), so it caps at 3.	3 / 5
Progressive Disclosure	Sections are well-organized but the entire reference material is inlined into one ~250-line SKILL.md with no separate reference files and no bundle files; content that could be split (per-library recipes, decision tree) is inline, so it sits at the 'some structure, should be separate' anchor.	3 / 5
	Total	13 / 20 Passed

Description

62%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 is specific and trigger-rich with a clear opsec niche, but the description string omits an explicit 'Use when...' clause, capping completeness at 3. Trigger coverage is strong but a few natural synonyms are missing.

Suggestions

Add an explicit 'Use when...' clause to the description string (e.g., 'Use when the engagement RoE requires OPSEC quiet/silent, or targets deploy WAFs, anti-bot shields, or Cloudflare') to lift completeness above 3.

Surface a couple more natural synonyms in the description (e.g., 'web scraping', 'Tor', 'SOCKS') so trigger_term_quality reaches full coverage.

Mention CAPTCHA solving and rate limiting in the description to make the capability list comprehensive.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Anti-bot evasion, proxy rotation, credential retrieval from password managers, and stealth HTTP tooling'); gaps exist (e.g., CAPTCHA solving and rate limiting from the body aren't surfaced here), so it is not fully comprehensive at 5.	4 / 5
Completeness	It clearly states what the skill does but the description line itself lacks an explicit 'Use when...' trigger clause; the 'when' guidance lives in metadata.when_to_use rather than the description, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Strong coverage of natural trigger terms (stealth, anti-bot, captcha, proxy rotation, password manager, keyring, 1Password, TLS fingerprint); falls just short of 5 since common synonyms like 'web scraping', 'SOCKS', or 'Tor' are not all surfaced in the description line itself.	4 / 5
Distinctiveness Conflict Risk	The opsec/stealth niche is distinct and unlikely to trigger for unrelated skills, though it could overlap marginally with a generic web-scraping or HTTP-request skill, keeping it just below 5.	4 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: PurpleAILAB/Decepticon
Path: packages/decepticon/decepticon/skills/shared/stealth-infra/SKILL.md
Commit: 0cf691e

Reviewed: 2 days 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.