hermes-attestation-guardian

Hermes-only runtime security attestation and drift detection skill for operator-managed Hermes infrastructure.

Quality

67%

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/hermes-attestation-guardian/SKILL.md

Quality

Content

77%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 highly actionable with executable commands, clear sequencing, and strong fail-closed validation checkpoints, but it is held back by an oversized inline release-verification block and inline configuration detail that would be better split into a one-level-deep reference.

Suggestions

Move the release-artifact verification script into a referenced file (e.g. references/verify-release.sh) and keep only a short invocation + trust note in SKILL.md.

Relocate the advisory-feed override-knob catalog to a references/ doc, leaving a brief summary and pointer inline.

Trim redundant section framing so each remaining section is purely actionable guidance.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean command/reference material that assumes competence, but the ~70-line inline release-verification bash block and the inline override-knob catalog add bulk that could be tightened or moved out of SKILL.md, keeping it just short of fully efficient.	2 / 3
Actionability	Commands are concrete, executable, and copy-paste ready (e.g. `node scripts/generate_attestation.mjs --policy ... --generated-at ... --write-sha256`), with real flags and output paths throughout.	3 / 3
Workflow Clarity	The generate→verify→baseline-diff sequence is explicit, the fail-closed behavior section enumerates every non-zero-exit condition, and risky paths (signature verification, `--allow-unsigned`) carry explicit validation checkpoints and warnings.	3 / 3
Progressive Disclosure	Sections are well organized and runtime logic is correctly split into scripts/, but the large inline release-verification block and the advisory-feed override knobs are content that could live one level deeper in a reference file, so navigation is not fully realized.	2 / 3
	Total	10 / 12 Passed

Description

57%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 narrowly scoped and clearly distinguishable, but it names only a couple of actions and omits any explicit "Use when" trigger guidance, leaning on domain jargon rather than natural user phrasing.

Suggestions

Add an explicit "Use when..." clause naming natural triggers, e.g. "Use when generating or verifying Hermes runtime security attestations or checking posture drift."

List a few more concrete actions (e.g. generate attestations, verify signatures, diff against an authenticated baseline) to move specificity toward multiple concrete operations.

Soften jargon ("operator-managed Hermes infrastructure") in favor of terms an operator would naturally say when requesting the skill.

Dimension	Reasoning	Score
Specificity	Names the domain and two concrete actions ("runtime security attestation and drift detection") but stops at two rather than listing multiple specific operations, so it is not comprehensive enough for a 3.	2 / 3
Completeness	It states what the skill does but has no "Use when..." clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Includes relevant niche terms ("security attestation", "drift detection") but leans on jargon ("operator-managed Hermes infrastructure") and lacks common natural variations a user would actually say, so it is not a full 3.	2 / 3
Distinctiveness Conflict Risk	The "Hermes-only" scoping plus the explicit non-OpenClaw boundary carve out a clear, narrow niche that is unlikely to trigger for unrelated skills.	3 / 3
	Total	9 / 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-attestation-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.