CtrlK
BlogDocsLog inGet started
Tessl Logo

hermes-agent-skill-authoring

Author in-repo SKILL.md: frontmatter, validator, structure, and writing-quality principles.

62

Quality

76%

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/software-development/hermes-agent-skill-authoring/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%

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 a clear, validated workflow and well-organized self-contained structure; its main weakness is internal redundancy across the principles, pitfalls, and checklist sections.

Suggestions

Collapse the duplicated no-op-prose/duplication/sediment guidance so each rule lives in one source of truth, then reference it from the other sections rather than restating it.

Trim overlap between 'Common Pitfalls' and the 'Verification Checklist' so the checklist checks outcomes and the pitfalls explain mistakes, without repeating the same wording.

Consider moving the boilerplate peer YAML shape or the validate-locally snippet into references/ so the always-visible SKILL.md stays leaner.

DimensionReasoningScore

Conciseness

The body is mostly lean and assumes Claude's competence (no basic concept explanations, strong leading words like 'tracer bullet'), but the 'Writing Quality Principles', 'Common Pitfalls', and 'Verification Checklist' sections restate the same rules (no-op prose, duplication, sediment) — a redundancy the skill itself warns against, matching the 'could be tightened' anchor.

2 / 3

Actionability

Provides exact paths, concrete tool calls ('write_file', "skill_manage(action='patch',...)", 'ls skills/<category>/'), a copy-paste-ready Python validation snippet, and a concrete YAML shape, matching the fully-executable anchor.

3 / 3

Workflow Clarity

The numbered Workflow (survey peers -> draft -> validate locally -> git add/commit) includes an explicit validation step with runnable assertions and a final Verification Checklist, matching the clear-sequence-with-validation-checkpoints anchor.

3 / 3

Progressive Disclosure

No bundle files are present, but the file is well-organized into clear sections, sits within the recommended 8-15k char range, and explicitly tells the author when to split into references/*.md past 20k chars — matching well-organized, appropriately self-contained content with one-level-deep disclosure guidance.

3 / 3

Total

11

/

12

Passed

Description

67%

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 occupies a clear niche, but it omits an explicit 'Use when...' trigger, which caps completeness and leaves trigger-term coverage partial.

Suggestions

Add an explicit trigger clause, e.g. 'Use when adding or editing a SKILL.md committed to the hermes-agent repo.'

Include natural user phrases like 'create a skill', 'skill conventions', or 'add a skill to this branch' alongside 'SKILL.md' to improve trigger-term coverage.

Frame the behavior in third person with a verb-led trigger (e.g. 'Authors... Use when...') to satisfy both completeness and the voice guideline.

DimensionReasoningScore

Specificity

Names the concrete domain ('in-repo SKILL.md') and lists multiple specific components — 'frontmatter, validator, structure, and writing-quality principles' — matching the anchor for listing multiple specific concrete actions.

3 / 3

Completeness

It clearly answers 'what' (author in-repo SKILL.md with those components) but lacks any 'when' trigger — no 'Use when...' clause — so per the guidelines completeness is capped at 2.

2 / 3

Trigger Term Quality

Contains relevant keywords a user authoring skills would say ('SKILL.md', 'frontmatter') but misses common natural variations like 'add a skill', 'create skill', or 'skill conventions', matching the 'some relevant keywords but missing variations' anchor.

2 / 3

Distinctiveness Conflict Risk

'Author in-repo SKILL.md' is a narrow, distinct niche (skill authoring restricted to the committed repo tree) unlikely to trigger for unrelated skills, matching the clear-niche anchor.

3 / 3

Total

10

/

12

Passed

Validation

75%

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

Validation12 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

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

Warning

Total

12

/

16

Passed

Repository
NousResearch/hermes-agent
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.