hermes-agent-skill-authoring

Author in-repo SKILL.md files: frontmatter and structure.

Quality

71%

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/software-development/hermes-agent-skill-authoring/SKILL.md

Quality

Content

88%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 a tightly written, highly actionable authoring walkthrough with clear sequencing, validation checkpoints, and a verification checklist. Its only real weakness is progressive disclosure: it is a large single-file skill with no bundle references to offload detail into.

Suggestions

Move the Platform Gating POSIX-signal catalogue and the validate-locally python snippet into references/ files, pointing to them from the body to reduce inline bulk and exercise progressive disclosure.

Consider trimming the Common Pitfalls list to the highest-impact items to push conciseness toward 5.

Add a short 'See AGENTS.md: Skill authoring standards (HARDLINE)' pointer near the top so the source-of-truth reference is signaled earlier for navigation.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational with strong leading words and no padding about concepts Claude already knows, but at ~200 lines a few sections (e.g. the 10-item Pitfalls list) could be trimmed slightly, keeping it just short of 'every token earns its place'.	4 / 5
Actionability	Provides fully executable guidance throughout: concrete tool calls (e.g. search_files(pattern='*', target='files', path='skills')), an executable copy-paste validation snippet, exact repo paths, and specific commands like scripts/run_tests.sh and the docs generator.	5 / 5
Workflow Clarity	The numbered Workflow has explicit validation checkpoints (validate locally with the python snippet, re-run docs generator), feedback loops for error recovery, and a Verification Checklist; because validation is present, the destructive/batch cap does not apply.	5 / 5
Progressive Disclosure	Well-organized into clear modern sections with one-level-deep references (AGENTS.md as source of truth, references/templates/scripts for bulky material) and no nested references; however no bundle files exist and the ~200-line body is fairly monolithic rather than split into referenced files.	4 / 5
	Total	18 / 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 a clear, concise, third-person capability statement with a distinct in-repo niche, but it lacks an explicit 'Use when...' trigger clause and offers only partial keyword and action coverage. Adding a trigger clause and one or two more concrete actions would raise completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. 'Use when adding or editing a skill under skills/ or optional-skills/ in the hermes-agent repo.'

Broaden trigger terms with natural phrasings users actually say, such as 'create skill', 'write skill', or 'skill authoring'.

Optionally name one more concrete action (e.g. validation or docs regen) to push specificity toward comprehensive coverage without exceeding the 60-char ceiling.

Dimension	Reasoning	Score
Specificity	Names the domain ('in-repo SKILL.md files') and a couple of concrete facets ('frontmatter and structure'), but does not enumerate the broader set of actions the body covers (validation, tests, docs, tier decisions), so coverage is not comprehensive.	3 / 5
Completeness	The 'what' is clear ('Author in-repo SKILL.md files: frontmatter and structure') but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Contains relevant keywords ('SKILL.md', 'author', 'frontmatter', 'in-repo') a user might say, but misses common natural variations like 'create skill', 'write skill', or 'skill authoring', so keyword coverage is partial.	3 / 5
Distinctiveness Conflict Risk	The 'in-repo' qualifier scopes it to a clear niche distinct from personal/local skill authoring, with only minor overlap risk against closely related sibling skills like requesting-code-review.	4 / 5
	Total	13 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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	Warning

	Total	12 / 16 Passed

Repository: NousResearch/hermes-agent
Path: skills/software-development/hermes-agent-skill-authoring/SKILL.md
Commit: 6327930

Reviewed: 3 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.