CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

hermes-traffic-guardian

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

Quality

64%

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

Fix and improve this skill with Tessl

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

Quality

Content

60%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 body is well-sectioned with strong, executable verification guidance and a clear safety contract, but its key reference (SPEC.md) does not exist in the bundle and the long verification script is inlined where a script file belongs. Navigation and structure are therefore weaker than the otherwise concrete content.

Suggestions

Ship the referenced SPEC.md (or move its content into the body / a references/ file) so 'Read SPEC.md before implementing' resolves to a real file.

Move the ~70-line release-verification script into scripts/verify-release.sh and keep a one-line invocation plus expected output in SKILL.md.

Actually create the documented lib/, scripts/, and test/ placeholder folders (or note they are to be created by the builder) so the entry-points table matches the bundle layout.

DimensionReasoningScore

Conciseness

Most sections are lean (Scope, Safety Contract, Out of Scope are tight bullet lists), but the ~70-line inline release-verification script is substantial content that belongs in a scripts/ file or reference, matching 'mostly efficient but includes some... could be tightened'. It is not a 2 because nothing explains concepts Claude already knows and there is no filler prose.

3 / 5

Actionability

The install command and the verification script are fully executable with set -euo pipefail, explicit fingerprint checks, and error exits, and 'Required First Implementation Behavior' is a concrete numbered spec. It falls short of 5 because the entry point 'Read SPEC.md before implementing' points to a file that is not in the bundle, leaving the core implementation guidance unresolved.

4 / 5

Workflow Clarity

The verification workflow has an explicit sequence with validation checkpoints (pubkey fingerprint check, signature verification, per-file checksum checks) and a hard gate ('Only install or extract the archive after this verification succeeds'), and implementation behavior is a numbered 7-step list. It is not a 5 because the implementation steps themselves (start monitor, emit findings, export posture) have no validation or test checkpoints despite test/ being called out.

4 / 5

Progressive Disclosure

Scored against the actual bundle: references/ and assets/ do not exist and scripts/ contains only .gitkeep, so the body's pointer to SPEC.md is a dangling reference and the lib/, scripts/, test/ placeholder folders it documents are not present. Combined with the large inlined verification script that 'clearly belongs in separate files', this matches the score-2 anchor; it is not a 3 because the primary reference target is broken rather than merely poorly signaled.

2 / 5

Total

13

/

20

Passed

Description

53%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 concise and domain-scoped with a clear 'what', but it has no 'when to use' trigger clause and leans on ecosystem jargon ('attestation-aware traffic posture') rather than natural user phrases. It would trigger reliably inside the Hermes toolchain but poorly from a user's natural-language request.

Suggestions

Add an explicit trigger clause, e.g. 'Use when setting up Hermes runtime traffic monitoring, proxy inspection, or outbound exfiltration detection.'

Rewrite 'attestation-aware traffic posture' in plainer capability terms (e.g., 'exports monitoring status for attestation') to improve natural keyword coverage.

Mention the complementary sibling ('hermes-attestation-guardian') boundary briefly so routing between the two skills is unambiguous from the description alone.

DimensionReasoningScore

Specificity

The description names its domain ('Hermes runtime traffic monitoring baseline') and lists a few capability areas ('opt-in proxy inspection, egress detection, and attestation-aware traffic posture'), matching the anchor for 1-2 concrete actions but not comprehensive coverage. It does not reach a 4 because 'attestation-aware traffic posture' is jargon rather than a concrete action, and inbound detection, logging, and status export are missing.

3 / 5

Completeness

The 'what' is stated clearly (opt-in proxy inspection, egress detection, traffic posture), but there is no 'Use when...' or equivalent trigger clause, so per the judging guideline completeness is capped at 3. It is not a 4 because the 'when' is entirely absent rather than merely weakly implied.

3 / 5

Trigger Term Quality

It contains some relevant keywords ('traffic monitoring', 'proxy inspection', 'egress detection') but these are technical jargon; natural user phrases like 'network traffic', 'monitor outbound requests', or file extensions are absent. It sits above score 2 (which has only generic keywords) but below score 4's good natural-term coverage.

3 / 5

Distinctiveness Conflict Risk

The 'Hermes runtime' and 'attestation-aware' scoping carves out a clear niche distinct from sibling skills (e.g., hermes-attestation-guardian), with only minor overlap risk with generic traffic/network-monitoring skills. It is not a 5 because the description alone does not state what it excludes, relying on the body to disambiguate from the attestation skill.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

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.