Name: subagent-driven-development
Rating: 52.8 (1 reviews)
Author: administrakt0r

Blog Docs Log in Get started

subagent-driven-development

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

Quality

58%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/subagent-driven-development/SKILL.md

The canonical home for this skill is subagent-driven-development in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

77%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 body delivers a clearly sequenced, checkpoint-driven workflow with strong feedback loops and a useful worked example. Its main weakness is that the key prompt templates are referenced but absent from the bundle, weakening both actionability and progressive disclosure.

Suggestions

Ship the referenced prompt-template files (implementer-prompt.md, spec-reviewer-prompt.md, code-quality-reviewer-prompt.md) in the bundle so the dispatch guidance is complete and the references resolve.

Consider replacing one of the two graphviz diagrams with a tighter prose or numbered list version to cut redundant tokens.

Inline a minimal dispatch prompt template (or at least its key fields) so the skill is executable even before the external files are opened.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and assumes Claude's intelligence (no padding about subagents, plan files, or TDD), but the two full graphviz diagrams partly restate prose and add token weight, fitting 'efficient; minor instances of over-explanation that could be trimmed'.	4 / 5
Actionability	It gives concrete dispatch steps and a full worked example with realistic dialogue, but the core 'how to dispatch' detail lives in referenced prompt-template files (./implementer-prompt.md, ./spec-reviewer-prompt.md, ./code-quality-reviewer-prompt.md) that are not present in the bundle, leaving minor gaps.	4 / 5
Workflow Clarity	The process is explicitly sequenced with validation checkpoints and feedback loops (spec review -> fix -> re-review, then quality review -> fix -> re-review), plus a Red Flags checklist enforcing 'don't skip re-review' and 'only proceed when approved', matching the top anchor.	5 / 5
Progressive Disclosure	References are one level deep and clearly signaled in a Prompt Templates section, but the referenced files do not exist in the bundle (no references/scripts/assets directories), so the split structure cannot be verified and the pointers are effectively dangling.	3 / 5
	Total	16 / 20 Passed

Description

40%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 clearly signals when to use the skill but omits any concrete actions ('what'), leaving it trigger-heavy and capability-light. It is reasonably distinctive thanks to the same-session framing.

Suggestions

Add a concrete 'what' clause naming the actions the skill performs, e.g. 'Dispatches a fresh subagent per task and runs two-stage spec-then-quality review after each.'

Include more natural user phrasings/synonyms as triggers, such as 'running a plan', 'building tasks one at a time', or 'task-by-task implementation'.

Lead with a capability statement before the 'Use when...' clause so both what and when are explicit.

Dimension	Reasoning	Score
Specificity	The description names the domain ('executing implementation plans', 'independent tasks') but lists zero concrete actions or verbs, matching the 'Names the domain but actions are minimal' anchor rather than the 1 (no domain named) or 3 (1-2 concrete actions).	2 / 5
Completeness	The description is essentially a 'when' clause ('Use when executing implementation plans...') with no explicit 'what' describing concrete capabilities, so per the missing-what guidance it caps low; not a 1 because a domain is named.	2 / 5
Trigger Term Quality	Phrases like 'executing implementation plans' and 'independent tasks' are relevant but lack common synonyms or natural user variations (e.g. 'run the plan', 'build the tasks'), matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	'in the current session' explicitly carves a niche distinct from parallel plan-execution skills, giving minor overlap risk only with closely related skills; not 5 because it could still overlap with generic plan-execution skills.	4 / 5
	Total	11 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/subagent-driven-development/SKILL.md
Commit: 57c135b

Reviewed: 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.