hermes-ephemeral-delegation

Trigger: broad exploration, multi-file reads, tests/builds, fresh review, or multi-step debug. Orchestrate complex work via delegate_task to protect context.

Quality

76%

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 ./internal/assets/skills/hermes-ephemeral-delegation/SKILL.md

Quality

Content

86%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 content is a tight, well-structured orchestration playbook that delegates configuration detail to a verified reference and includes explicit verification of worker output, with only minor gaps in worked examples and error-recovery loops.

Suggestions

Add a concrete sample delegate_task mission (filled-in example) to make the actionability fully copy-paste ready.

Spell out a feedback loop for step 5: what to do when verification contradicts the worker's self-report (re-delegate, fix inline, or escalate).

Clarify whether the external ../../hermes/sdd-orchestrator.md reference is guaranteed present, since it points outside the skill bundle.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient — rules, a decision-gate table, and a numbered execution flow with no padding and no explanation of concepts Claude already knows; every section earns its place.	5 / 5
Actionability	Concrete, actionable guidance is given (mission checklist of goal/paths/context/constraints/evidence/toolsets, explicit verify step), but no worked example of a delegate_task call or a filled-in sample mission is provided, leaving a minor gap.	4 / 5
Workflow Clarity	Execution Steps 1-6 are clearly sequenced with an explicit verification checkpoint (step 5) and a mission checklist, but an explicit error-recovery feedback loop for when verification fails is not spelled out, keeping it just below 5.	4 / 5
Progressive Disclosure	A clear overview (Activation Contract, Hard Rules, Decision Gates, Execution Steps, Output Contract) points to a verified one-level-deep reference (references/tuning-knobs.md) for config detail, with well-signaled, appropriately split content and easy navigation.	5 / 5
	Total	18 / 20 Passed

Description

66%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 clearly states both what the skill does and when to use it with concrete triggers, but leads with a non-standard "Trigger:" label, leans on jargon, and uses imperative second-person voice rather than third person.

Suggestions

Rewrite in third person (e.g., "Orchestrates complex work via delegate_task to protect context") to avoid the second-person voice penalty.

Replace the "Trigger:" label with a natural "Use when..." clause and add user-natural synonyms (e.g., "explore the codebase", "review this PR", "run the tests").

Add one or two more concrete capabilities beyond the single "orchestrate" action to lift specificity above the domain-only level.

Dimension	Reasoning	Score
Specificity	The description names the domain and one concrete action — "Orchestrate complex work via delegate_task to protect context" — but offers only that single capability (baseline 3), and the imperative "Orchestrate" is second-person voice, which per rubric reduces specificity by 1 to 2.	2 / 5
Completeness	It explicitly answers both "what" (orchestrate complex work via delegate_task to protect context) and "when" (the five enumerated trigger categories), with concrete trigger phrases equivalent to a "Use when..." clause.	5 / 5
Trigger Term Quality	Trigger terms like "broad exploration", "tests/builds", "fresh review", and "multi-step debug" are relevant, but the "Trigger:" label plus jargon ("delegate_task", "protect context") are not the most natural user phrasings and lack common synonyms.	3 / 5
Distinctiveness Conflict Risk	The context-protecting delegation-orchestration niche is mostly distinct, though the broad trigger categories (exploration, tests/builds, review, debug) create minor overlap risk with general coding and orchestration skills.	4 / 5
	Total	14 / 20 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
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: Gentleman-Programming/gentle-ai
Path: internal/assets/skills/hermes-ephemeral-delegation/SKILL.md
Commit: a245f26

Reviewed: 1 day 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.