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

96%

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

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is well-structured, lean, and actionable, with a clear sequenced workflow and an explicit verification checkpoint. Its only weakness is progressive disclosure: one of its two references is an unresolved external path rather than a clean one-level-deep bundle file.

Suggestions

Replace or remove the ../../hermes/sdd-orchestrator.md reference with a path inside the bundle (e.g., references/sdd-orchestrator.md) so all references resolve one level deep.

Confirm references/tuning-knobs.md is the single home for the delegate_task configuration table and toolset checklist, and link to it inline from the Hard Rules or Execution Steps where those details are most relevant.

Keep the main body as an overview; ensure no orchestration detail that belongs in tuning-knobs.md is duplicated inline.

Dimension	Reasoning	Score
Conciseness	The body is lean — tight bullets, a compact decision table, and a short numbered workflow — with no padding or explanation of concepts Claude already knows, so every token earns its place.	3 / 3
Actionability	As an instruction-only orchestration skill it gives highly specific guidance: step 2 enumerates exact mission fields (goal, file paths, prior context, constraints, expected evidence, allowed toolsets, SKILL.md paths) and step 5 specifies verifying file existence, test results, and side effects, which is concrete and actionable without needing code.	3 / 3
Workflow Clarity	The six-step 'Execution Steps' sequence is clearly ordered and includes an explicit validation checkpoint (step 5 'Verify the claimed output'), with Hard Rules reinforcing self-report verification, satisfying the anchor requiring clear sequence plus explicit validation.	3 / 3
Progressive Disclosure	The SKILL.md is a concise overview with a well-signaled one-level-deep reference to references/tuning-knobs.md (which exists), but the second reference points to ../../hermes/sdd-orchestrator.md, an external path outside the bundle that does not resolve, breaking the one-level-deep, clear-navigation criterion.	2 / 3
	Total	11 / 12 Passed

Description

100%

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 concise yet complete, pairing an explicit trigger clause with a concrete, tool-specific capability statement and natural user keywords. It cleanly answers what the skill does and when to use it with minimal risk of conflicting with other skills.

Dimension	Reasoning	Score
Specificity	The description lists multiple specific concrete actions ('broad exploration, multi-file reads, tests/builds, fresh review, or multi-step debug') plus the mechanism ('Orchestrate complex work via delegate_task to protect context'), matching the anchor that requires listing several specific actions rather than vague language.	3 / 3
Completeness	It explicitly answers both 'what' ('Orchestrate complex work via delegate_task to protect context') and 'when' via the explicit 'Trigger:' clause, satisfying the anchor requiring explicit triggers rather than only implied timing.	3 / 3
Trigger Term Quality	It opens with 'Trigger:' followed by natural user-facing terms (review, tests/builds, multi-file reads, debug) that a user would actually say, giving good coverage rather than only technical jargon or a single keyword.	3 / 3
Distinctiveness Conflict Risk	The niche is tied to a specific tool ('delegate_task') for context-protecting orchestration, with distinct triggers unlikely to fire for unrelated skills, matching the clear-niche anchor.	3 / 3
	Total	12 / 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
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: e01b114

Reviewed: about 14 hours 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.