subagent-driven-development

Execute plans via delegate_task subagents (2-stage review).

Quality

63%

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 ./optional-skills/software-development/subagent-driven-development/SKILL.md

Quality

Content

77%

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

The content is highly actionable with concrete executable templates and a clearly sequenced, checkpointed workflow including feedback loops. Its main weakness is token efficiency and progressive disclosure: rules are restated across several sections and a fair amount of detail lives inline rather than in the available reference files.

Suggestions

Consolidate the Red Flags, Handling Issues, Efficiency Notes, and Remember sections, which restate the same process rules, to reduce repetition and tighten token usage.

Move the lengthy 'Example Workflow' transcript into a reference file (or trim it to a brief outline) so the SKILL.md stays a lean overview pointing to detail.

Consider offloading the full review-context checklists into a reference to deepen progressive disclosure beyond the current two reference files.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but the Red Flags, Efficiency Notes, Handling Issues, and Remember sections restate rules already covered in the process, so it could be tightened.	2 / 3
Actionability	It provides fully concrete, copy-paste-ready delegate_task() and todo() call templates with real context blocks plus executable bash commands like 'pytest tests/ -q' and 'git add -A && git commit', matching the score-3 anchor.	3 / 3
Workflow Clarity	The process is clearly sequenced (read plan, per-task 4-step workflow, final review, verify/commit) with explicit validation checkpoints ('Continue only when spec-compliant', 'Continue only when approved') and fix-then-re-review feedback loops, matching the score-3 anchor.	3 / 3
Progressive Disclosure	The two references are real, one-level-deep, and well-signaled with explicit load triggers, but substantial content that could be split out (the long example workflow, red flags, efficiency notes) remains inline, so the structure is good but not fully decomposed.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 and names a concrete mechanism, but it omits explicit trigger guidance and relies on somewhat technical jargon, leaving the 'when to use' question unanswered. It is functional but not exemplary.

Suggestions

Add an explicit 'Use when...' clause stating when to invoke this skill (e.g., 'Use when executing an implementation plan with mostly independent tasks that need automated review').

Replace internal jargon like 'delegate_task subagents (2-stage review)' with natural user-facing terms while keeping the concrete mechanism, to improve trigger term quality.

Distinguish it from the related `plan` skill by framing the trigger around plan execution rather than plan creation.

Dimension	Reasoning	Score
Specificity	The phrase 'Execute plans via delegate_task subagents (2-stage review)' names the domain and a couple concrete mechanisms, but offers only one real action verb with the rest as a parenthetical, so it is not comprehensive like the score-3 anchor.	2 / 3
Completeness	It clearly states what the skill does ('Execute plans via delegate_task subagents'), but there is no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	Terms like 'plans', 'subagents', and 'review' are relevant, but 'delegate_task subagents' and '2-stage review' lean toward internal jargon and miss common user phrasings such as 'implement my plan' or 'delegate work'.	2 / 3
Distinctiveness Conflict Risk	The delegation/execution niche is fairly specific, but 'execute plans' overlaps with the related `plan` skill it references, so it could still trigger for a similar skill.	2 / 3
	Total	8 / 12 Passed

Validation

81%

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 — 13 / 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

	Total	13 / 16 Passed

Repository: NousResearch/hermes-agent
Path: optional-skills/software-development/subagent-driven-development/SKILL.md
Commit: 5be99b6

Reviewed: 4 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.