subagent-driven-development

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

Quality

59%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

70%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.

This is a thorough, well-sequenced process skill with excellent workflow clarity and strong actionability via exact commands and formats, though it is somewhat verbose and ships references to template files that are missing from the bundle.

Suggestions

Add the missing template files (implementer-prompt.md, task-reviewer-prompt.md, re-review-prompt.md) or remove the dead 'Template:' references so progressive disclosure resolves.

Tighten repeated ledger/rulings emphasis across prose and the 'Common Rationalizations' table to recover token budget.

Convert remaining principle-level governance prose into concrete, copy-paste-ready dispatch language to reach full actionability.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with no basic-concept padding, but it restates ledger/rulings themes across prose and the 'Common Rationalizations' table, so some sections could be tightened to match the lean anchor of 4.	3 / 5
Actionability	Concrete, executable guidance is strong — exact script invocations, explicit ledger line formats, a 5-element dispatch spec, and four-status report handling — but some governance prose stays principle-level, keeping it just below the fully copy-paste-ready anchor of 5.	4 / 5
Workflow Clarity	Two DOT flowcharts sequence the full process, the per-task loop has five numbered stages, and the fix loop has explicit rounds, a breaker, and scoped re-review checkpoints — a clear match for 'explicit validation steps; feedback loops for error recovery; checklists'.	5 / 5
Progressive Disclosure	Structure and one-level-deep 'Template:' references are well signaled, but the referenced template files (implementer-prompt.md, task-reviewer-prompt.md, re-review-prompt.md) do not exist in the bundle, so the disclosure points to content that is absent.	3 / 5
	Total	15 / 20 Passed

Description

48%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 gives a clear, explicit trigger ('Use when...') and is reasonably distinct, but it is light on concrete actions and offers only a weak 'what', leaving completeness and specificity below their anchors.

Suggestions

Add 1-2 concrete actions to raise specificity, e.g. 'Dispatch one implementer subagent per task, review each for spec and quality, then run a whole-branch review.'

Broaden trigger terms with natural synonyms users say, e.g. 'build plan', 'task list', or 'run the plan'.

Make the 'what' explicit rather than implied, so both what it does and when to use it are clearly stated.

Dimension	Reasoning	Score
Specificity	The phrase 'executing implementation plans with independent tasks' names the domain but offers no concrete actions beyond the generic 'executing', matching the 'names domain but actions are minimal or generic' anchor rather than the 1-2 concrete actions required for a 3.	2 / 5
Completeness	The 'when' is explicit ('Use when executing implementation plans with independent tasks in the current session') but the 'what' is only weakly implied (just 'executing'), so it does not clearly answer both what and when as required for a 4.	3 / 5
Trigger Term Quality	'executing implementation plans', 'independent tasks', 'current session' are relevant natural phrases, but common synonyms users would say (e.g. 'build', 'task list', 'plan tasks') are missing, matching 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	'executing implementation plans with independent tasks in the current session' carves a mostly-distinct niche with only minor overlap risk against generic plan-execution skills, matching 'mostly distinct; minor overlap risk'.	4 / 5
	Total	12 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (569 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 4 missing, 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: obra/superpowers
Path: skills/subagent-driven-development/SKILL.md
Commit: b36e082

Reviewed: 6 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.