subagent-driven-development
Use when executing implementation plans with independent tasks in the current session
46
32%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/subagent-driven-development/SKILL.mdQuality
Discovery
17%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 too abstract and vague to be useful for skill selection. It fails to specify what concrete actions the skill performs, uses no natural trigger terms a user would say, and is so generic it could conflict with many other skills. The only positive aspect is the presence of a 'Use when' clause, though even that is poorly defined.
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 execution', 'run tasks simultaneously', 'batch tasks', 'multi-task', or 'do these at the same time'.
Clarify the 'when' clause with more explicit triggers, e.g., 'Use when the user has a plan with multiple independent steps that can be executed concurrently, or when they ask to parallelize work or run multiple tasks at once.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'executing implementation plans' and 'independent tasks' without specifying any concrete actions. It does not describe what the skill actually does—no specific operations, tools, or outputs are mentioned. | 1 / 3 |
Completeness | It has a 'Use when' clause which addresses the 'when' question, but the 'what' is extremely weak—it only says 'executing implementation plans' without explaining what that entails. The 'when' itself is also vague ('independent tasks in the current session'). | 2 / 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 'do these steps'. The language is abstract and jargon-heavy. | 1 / 3 |
Distinctiveness Conflict Risk | 'Executing implementation plans with independent tasks' is very generic and could overlap with many skills related to task execution, project management, code generation, or workflow automation. There are no distinct triggers to differentiate it. | 1 / 3 |
Total | 5 / 12 Passed |
Implementation
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 process steps, validation checkpoints, and error handling for all subagent statuses. However, it is significantly over-verbose, with redundant sections (Advantages restates the process benefits, Red Flags repeats workflow constraints already shown in the diagram) that consume excessive tokens. Actionability suffers from lack of concrete tool invocation examples — the skill describes what to do conceptually but doesn't show the actual mechanism for dispatching subagents.
Suggestions
Cut the 'Advantages' section entirely — the benefits are self-evident from the process description and add ~40 lines of redundant content
Add a concrete example of the actual tool call or mechanism used to dispatch a subagent (e.g., the specific tool invocation with arguments), rather than just prose descriptions
Consolidate 'Red Flags' into a compact checklist of ~5 items instead of the current ~15 bullet points with sub-bullets, moving detailed guidance into the process section where it's contextually relevant
Move the extended example workflow to a separate file (e.g., ./example-workflow.md) and keep only a 5-line summary in the main skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~250+ lines. The 'Advantages' section restates what's already clear from the process description. The 'When to Use' section, example workflow, and extensive 'Red Flags' list contain significant redundancy. The Graphviz diagrams, while structured, add substantial token cost for information that could be conveyed more concisely. The 'Why subagents' explanation tells Claude things it can infer. | 1 / 3 |
Actionability | The skill provides a clear process flow and references prompt templates (implementer-prompt.md, spec-reviewer-prompt.md, code-quality-reviewer-prompt.md), but lacks concrete executable examples of how to actually dispatch subagents (what tool call, what arguments). The example workflow is illustrative prose rather than executable commands or tool invocations. The model selection guidance is vague ('cheap model', 'standard model') without specifying actual model names. | 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 ordering constraint (spec before quality) is explicitly called out. | 3 / 3 |
Progressive Disclosure | The skill references external prompt templates and other skills appropriately, but the main file itself is a monolithic wall of text that includes extensive sections (Advantages, Red Flags, Example Workflow) that could be trimmed or moved to separate files. The inline example workflow alone is ~50 lines that could be a separate reference file. | 2 / 3 |
Total | 8 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- obra/superpowers
- Commit
6efe32c
- 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.