hermes-traffic-guardian

Hermes runtime traffic monitoring baseline for opt-in proxy inspection, egress detection, and attestation-aware traffic posture.

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/hermes-traffic-guardian/SKILL.md

Quality

Content

62%Weight 40%Scale 1-3

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

The body is well-structured with strong workflow clarity and explicit validation gates, but it carries an oversized inline verification script and references SPEC.md and placeholder folders that don't exist in the bundle.

Suggestions

Move the Release Artifact Verification bash block into a script under scripts/ (e.g. scripts/verify-release.sh) and reference it, keeping the body as a concise overview.

Provide the referenced SPEC.md or remove the 'Read SPEC.md before implementing' instruction so referenced materials resolve to real files.

Relocate the hardcoded VERSION='0.0.1-beta5' and pinned pubkey fingerprint into a version/deprecation section or a referenced config to avoid time-sensitive content bloating the core body.

Dimension	Reasoning	Score
Conciseness	Sections like Scope and Safety Contract are lean and assume Claude's competence, but the ~70-line inline Release Artifact Verification script with a hardcoded version and pinned pubkey adds bulk that could be tightened or externalized.	2 / 3
Actionability	The verification script and install command are fully executable and copy-paste ready, but the core monitoring task is described only as numbered steps with no executable code because implementation is intentionally deferred.	2 / 3
Workflow Clarity	The 7-step Required First Implementation Behavior is clearly sequenced, and the verification workflow has explicit validation checkpoints with feedback loops (mismatch -> exit 1) and a 'only proceed when verification succeeds' gate.	3 / 3
Progressive Disclosure	Clear section structure exists, but the primary reference (SPEC.md) is not a real bundle file, the verification code is inlined rather than split into scripts/, and the placeholder folders are mostly empty.	2 / 3
	Total	9 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 but lacks any explicit 'Use when...' trigger guidance, which caps its completeness. It leans on framework-specific jargon rather than natural user phrasing.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should invoke this skill, e.g. 'Use when monitoring Hermes outbound runtime traffic or inspecting proxy egress.'

Soften framework jargon with natural terms users would actually say, such as 'outbound traffic', 'network inspection', or 'exfiltration detection'.

Mirror common phrasings ('when the user mentions egress, exfiltration, or proxy inspection') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names a concrete domain and lists multiple specific actions ('opt-in proxy inspection, egress detection, and attestation-aware traffic posture') in third-person voice.	3 / 3
Completeness	It clearly states what the skill does but provides no 'Use when...' clause or explicit trigger guidance, capping completeness at 2 per the rubric.	2 / 3
Trigger Term Quality	Relevant keywords exist ('traffic monitoring', 'proxy inspection', 'egress detection') but they skew toward Hermes-specific technical jargon rather than natural phrasing a user would say, missing common variations.	2 / 3
Distinctiveness Conflict Risk	The Hermes scoping plus 'attestation-aware traffic posture' carve out a clear, narrow niche unlikely to trigger for the wrong skill.	3 / 3
	Total	10 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: prompt-security/clawsec
Path: skills/hermes-traffic-guardian/SKILL.md
Commit: c6194eb

Reviewed: 14 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.