CtrlK
BlogDocsLog inGet started
Tessl Logo

subagent-driven-development

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

31

Quality

23%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Fix and improve this skill with Tessl

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

Quality

Content

47%

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

The skill has excellent workflow clarity with well-defined steps, validation checkpoints, feedback loops, and error handling for all subagent statuses. However, it is significantly over-verbose — the Graphviz diagrams, lengthy example workflow, and 'Advantages' section consume tokens explaining things Claude can infer. Actionability suffers from lack of concrete tool invocation examples for dispatching subagents.

Suggestions

Remove or drastically shorten the Graphviz diagrams — replace with a concise numbered list or brief ASCII flow; the process section and example already convey the workflow

Remove the 'Advantages' section entirely — Claude doesn't need to be sold on why to use a skill it's been told to use

Add a concrete example of the actual tool call / mechanism for dispatching a subagent (e.g., the specific API call or tool invocation with parameters)

Specify actual model names or tiers in the Model Selection section instead of vague 'cheap model' / 'standard model' / 'most capable model'

DimensionReasoningScore

Conciseness

The skill is extremely verbose at ~250+ lines. The Graphviz diagrams, while visually descriptive, consume massive token budgets and duplicate information already stated in prose. The 'Advantages' section explains obvious benefits Claude can infer. The 'Example Workflow' section is lengthy and largely redundant with the process description. The 'When to Use' decision tree could be 2-3 bullet points.

1 / 3

Actionability

The skill provides a clear process and references prompt templates (implementer-prompt.md, spec-reviewer-prompt.md, code-quality-reviewer-prompt.md), but lacks concrete examples of how to actually dispatch subagents (what tool call, what arguments). The model selection guidance is vague ('cheap model', 'standard model', 'most capable model') without naming specific models or parameters. The example workflow is illustrative but not executable.

2 / 3

Workflow Clarity

The multi-step process is clearly sequenced with explicit validation checkpoints (spec compliance review → code quality review), feedback loops (reviewer finds issues → implementer fixes → re-review), and clear handling of all implementer statuses (DONE, DONE_WITH_CONCERNS, NEEDS_CONTEXT, BLOCKED). The 'Red Flags' section provides strong guardrails including ordering constraints.

3 / 3

Progressive Disclosure

The skill references external prompt templates (./implementer-prompt.md, ./spec-reviewer-prompt.md, ./code-quality-reviewer-prompt.md) and other skills appropriately, but no bundle files were provided to verify these exist. The main file itself contains too much inline content that could be split out — the example workflow, advantages section, and Graphviz diagrams bloat the overview significantly.

2 / 3

Total

8

/

12

Passed

Description

0%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description is critically underspecified. It fails to communicate what concrete actions the skill performs, uses abstract jargon instead of natural trigger terms, and lacks any distinguishing characteristics that would help Claude select it appropriately from a pool of skills. The 'Use when' clause is present but the trigger condition is too vague to be actionable.

Suggestions

Add specific concrete actions the skill performs, e.g., 'Executes multiple independent coding tasks in parallel, such as writing tests, refactoring modules, and updating documentation simultaneously'

Include natural trigger terms users would actually say, such as 'parallel tasks', 'run multiple tasks', 'batch execution', 'do these at the same time', or whatever the actual use case entails

Clarify the 'what' portion by explaining the mechanism (e.g., parallel execution, task orchestration) and differentiate from sequential task execution or simple plan creation

DimensionReasoningScore

Specificity

The description uses vague language like 'executing implementation plans' and 'independent tasks' without specifying any concrete actions. There are no specific capabilities listed—just abstract concepts.

1 / 3

Completeness

While there is a 'Use when' clause, the 'what does this do' part is essentially missing—'executing implementation plans with independent tasks' doesn't explain what the skill actually does. The 'when' trigger is also too vague to be useful.

1 / 3

Trigger Term Quality

The terms 'implementation plans' and 'independent tasks' are not natural phrases users would say. Users are more likely to say things like 'run tasks in parallel', 'execute my plan', or reference specific task types. The language is overly abstract and jargon-heavy.

1 / 3

Distinctiveness Conflict Risk

'Executing implementation plans with independent tasks' is extremely generic and could overlap with virtually any task execution, project management, or workflow automation skill. There are no distinct triggers to differentiate it.

1 / 3

Total

4

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
lucianghinda/superpowers-ruby
Reviewed

Table of Contents

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.