subagent-driven-development

Use when executing implementation plans with independent tasks in the current session

Quality

60%

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/subagent-driven-development/SKILL.md

Quality

Content

62%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 skill body is a clearly sequenced, well-gated process with strong feedback loops and a useful Red Flags checklist, but it is somewhat verbose and its central dispatch mechanism depends on three referenced prompt-template files that are not actually bundled. Adding the missing templates (or inlining their essentials) would resolve the biggest gap.

Suggestions

Bundle the referenced ./implementer-prompt.md, ./spec-reviewer-prompt.md, and ./code-quality-reviewer-prompt.md files, or inline their key contents so the dispatch step is executable as written.

Collapse the two dot diagrams into one concise diagram or a short numbered list; the process and when-to-use graphs duplicate content already in the surrounding prose.

Trim the Advantages and comparison subsections, which restate points from When to Use and the core principle.

Dimension	Reasoning	Score
Conciseness	The body is mostly operational and avoids over-explaining basics, but the two verbose dot diagrams, the repeated "vs. Manual / vs. Executing Plans" comparisons, and the Advantages section restate points already covered in When to Use and could be tightened.	3 / 5
Actionability	Process steps, status-handling rules, and model-selection signals are concrete, but the core dispatch mechanism relies on ./implementer-prompt.md, ./spec-reviewer-prompt.md, and ./code-quality-reviewer-prompt.md, none of which exist in the bundle, leaving a key executable gap.	3 / 5
Workflow Clarity	The process is explicitly sequenced with a per-task loop, mandatory two-stage review (spec compliance must pass before code quality), re-review feedback loops, and a Red Flags checklist acting as a validation gate for a complex process.	5 / 5
Progressive Disclosure	Sections are well-organized and references are clearly signaled in a dedicated Prompt Templates section, but every referenced template file is absent from the (empty) bundle, so the one-level-deep references are navigation dead-ends rather than real split content.	3 / 5
	Total	14 / 20 Passed

Description

57%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, well-triggered one-liner that names its niche and uses an explicit "Use when" clause, but it blends what and when into a single clause and gives only one generic action. It is solid but could be more specific about the concrete mechanics (fresh subagent per task, two-stage review).

Suggestions

Add a concrete what clause naming the mechanism, e.g. "Dispatches a fresh subagent per task with spec-compliance then code-quality review. Use when executing implementation plans with independent tasks in the current session."

Include a natural synonym or two (e.g. "running a plan", "breaking a plan into tasks") so the trigger matches more user phrasings.

Dimension	Reasoning	Score
Specificity	"executing implementation plans with independent tasks" names the domain but offers only one broad action (executing) with no concrete mechanics, matching the "names the domain but actions are minimal/generic" anchor rather than the 1-2 concrete actions needed for a 3.	2 / 5
Completeness	Both a what (executing implementation plans with independent tasks) and an explicit when ("Use when ... in the current session") are present, but the what and when overlap in one clause and could be more explicitly separated, fitting the 4 rather than the fully concrete 5.	4 / 5
Trigger Term Quality	"executing implementation plans", "independent tasks", and "current session" are relevant natural phrases, but coverage lacks common synonyms/variations a user might say, fitting the "some relevant keywords but missing variations" anchor.	3 / 5
Distinctiveness Conflict Risk	The qualifiers "independent tasks" and "in the current session" carve a distinct niche, but it overlaps with a closely related executing-plans skill (called out in the body), so it is mostly distinct with minor overlap risk rather than minimal conflict.	4 / 5
	Total	13 / 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: lucianghinda/superpowers-ruby
Path: skills/subagent-driven-development/SKILL.md
Commit: 99fac3d

Reviewed: 7 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.