subagent-driven-development

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

1.41x

Quality

56%

Does it follow best practices?

Impact

99%

1.41x

Average score across 10 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./bundled/skills/subagent-driven-development/SKILL.md

The canonical home for this skill is subagent-driven-development in obra/superpowers

Quality

Content

62%

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

The body delivers an exceptionally clear, well-sequenced workflow with explicit review feedback loops and checklists, but it is somewhat verbose and its core actionable component — the referenced prompt templates — are absent from the bundle. Fixing the missing files and trimming the redundant diagrams would lift both actionability and progressive disclosure.

Suggestions

Add the missing ./implementer-prompt.md, ./spec-reviewer-prompt.md, and ./code-quality-reviewer-prompt.md files so the referenced dispatch mechanism is actually available.

Consolidate the dot diagrams or the prose bullet lists to remove the duplication between the 'When to Use'/'Process' graphs and the 'vs.'/'Example Workflow' sections.

Tighten the Advantages and Red Flags sections by merging overlapping points (e.g., the review-loop guidance appears in both).

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows, but the two dot diagrams and the lengthy Advantages/Red Flags sections restate information already conveyed in the bullet lists and example, so it is mostly efficient but could be tightened.	2 / 3
Actionability	The orchestration steps, sequencing, and example dialogue are concrete, but the central actionable artifact — the three prompt templates referenced as ./implementer-prompt.md, ./spec-reviewer-prompt.md, and ./code-quality-reviewer-prompt.md — do not exist in the bundle, leaving the dispatch mechanism incomplete.	2 / 3
Workflow Clarity	The process graph lays out a clear sequence with explicit validation checkpoints and feedback loops (spec review -> fix -> re-review, then code-quality review -> fix -> re-review), plus a Red Flags/Never checklist and an explicit review-order rule, matching the score-3 anchor.	3 / 3
Progressive Disclosure	The body is structured as an overview pointing to one-level-deep, clearly signaled prompt-template files, but those referenced files (./implementer-prompt.md, ./spec-reviewer-prompt.md, ./code-quality-reviewer-prompt.md) are missing from the bundle, so the split content does not actually exist and cannot earn the top score.	2 / 3
	Total	9 / 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 a clear, explicit trigger clause but omits any statement of what the skill does, so it answers "when" well and "what" not at all. It is specific enough to avoid being vague but stops short of comprehensive capability coverage.

Suggestions

Add a clause naming the skill's concrete actions, e.g. 'Dispatches a fresh subagent per task with two-stage spec-then-quality review.'

Broaden trigger terms with more natural user phrasing such as 'breaking a plan into tasks' or 'running a plan step by step' alongside 'implementation plans'.

State both what and when in one sentence to satisfy the completeness anchor for a top score.

Dimension	Reasoning	Score
Specificity	The description names a specific domain ("executing implementation plans with independent tasks in the current session") but lists no concrete actions the skill performs, so it lands between the vague score-1 anchor and the action-naming score-2 anchor.	2 / 3
Completeness	The "when" is explicit ("Use when executing implementation plans..."), but the "what" — what the skill actually does — is entirely absent, so it does not reach the score-3 requirement of answering both what AND while staying above score 1 because the trigger is strong rather than weak.	2 / 3
Trigger Term Quality	"implementation plans" and "tasks" are plausible user terms, but "independent tasks in the current session" reads as methodological jargon rather than natural phrasing, matching the score-2 anchor of some relevant keywords missing common variations.	2 / 3
Distinctiveness Conflict Risk	"in the current session" plus "independent tasks" carves a somewhat distinct niche, but "implementation plans" overlaps the executing-plans/writing-plans skill family, matching the score-2 anchor of specific but still potentially overlapping.	2 / 3
	Total	8 / 12 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: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/subagent-driven-development/SKILL.md
Commit: f627ab5

Reviewed: about 10 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.