code-mate-hermes

Runs Hermes Agent in one-shot mode for bounded local tasks. Use when the user explicitly asks to delegate work to Hermes and accepts its automatic tool approval behavior.

Quality

84%

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

Quality

Content

93%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 concise, fully executable, and well-structured, with validation present for the destructive workflow; the only gap is an explicit fix-and-retry feedback loop on non-zero exits.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept over-explanation; every line is actionable guidance and assumes Claude's competence, matching the 'lean and efficient; every token earns its place' anchor.	5 / 5
Actionability	It gives a copy-paste command (`hermes -z "<prompt>"`), a concrete availability check (`command -v hermes`), and specific exit-code meanings, fully executable for the common case.	5 / 5
Workflow Clarity	The Run section is a clear numbered sequence with validation checkpoints (availability gate, exit-code interpretation, diff inspection for the destructive case), but the error-recovery loop is implicit rather than an explicit fix-and-retry, so it sits below the 5 anchor.	4 / 5
Progressive Disclosure	The skill is under 50 lines with no need for external references and is organized into two well-signaled sections (Run, Authentication And Permissions), meeting the simple-skill exception for a top score.	5 / 5
	Total	19 / 20 Passed

Description

75%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 cleanly answers both what and when with a distinctive, low-conflict trigger, but its capability list and trigger-term breadth are narrow — one action and one primary trigger phrase.

Suggestions

Add one or two more concrete actions (e.g., 'runs a single bounded task and returns stdout') to lift specificity above a single named action.

Include a synonym or natural variation of the trigger (e.g., 'hand off a task to Hermes' or 'run Hermes unattended') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete action ('Runs Hermes Agent in one-shot mode for bounded local tasks') but does not enumerate multiple specific actions, matching the '1-2 concrete actions, not comprehensive' anchor rather than the multi-action anchor at 4.	3 / 5
Completeness	It explicitly states both what ('Runs Hermes Agent in one-shot mode for bounded local tasks') and when with a concrete conditional trigger ('Use when the user explicitly asks to delegate work to Hermes and accepts its automatic tool approval behavior'), matching the top anchor.	5 / 5
Trigger Term Quality	It includes a natural trigger phrase ('delegate work to Hermes') and the product name, but offers only one primary trigger with no synonyms or variations, fitting 'some relevant keywords but missing common variations' rather than the broad coverage at 4.	3 / 5
Distinctiveness Conflict Risk	It targets a clear niche (delegating to a named agent, Hermes) with a distinct trigger and an explicit accept-YOLO condition, giving minimal overlap with other skills.	5 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: CherryHQ/cherry-studio
Path: resources/code-cli-skills/code-mate-hermes/SKILL.md
Commit: 113ef7e

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.