subagent-driven-development
Use when executing implementation plans with independent tasks in the current session
Install with Tessl CLI
npx tessl i github:obra/superpowers --skill subagent-driven-development85
Quality
46%
Does it follow best practices?
Impact
97%
1.27xAverage score across 8 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/subagent-driven-development/SKILL.mdQuality
Discovery
7%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 fails to communicate what the skill actually does - it only provides a vague trigger condition without explaining capabilities. The language is abstract and technical rather than concrete and user-facing. Users would not naturally use phrases like 'implementation plans with independent tasks' when requesting help.
Suggestions
Add concrete actions describing what the skill does (e.g., 'Parallelizes and executes multiple independent coding tasks simultaneously' or 'Runs batch operations across files').
Replace technical jargon with natural trigger terms users would say (e.g., 'run tasks in parallel', 'execute multiple steps', 'batch processing').
Expand the 'Use when' clause with specific scenarios and user phrases that would trigger this skill (e.g., 'Use when user asks to run multiple independent tasks at once, parallelize work, or execute a multi-step plan').
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'executing implementation plans' and 'independent tasks' without specifying concrete actions. No specific capabilities are listed. | 1 / 3 |
Completeness | While it attempts a 'Use when' clause, the 'what' is extremely weak - it doesn't explain what the skill actually does, only vaguely when to use it. Both components are inadequate. | 1 / 3 |
Trigger Term Quality | The terms 'implementation plans' and 'independent tasks' are technical jargon unlikely to be naturally spoken by users. Missing common variations or natural language triggers. | 1 / 3 |
Distinctiveness Conflict Risk | The phrase 'independent tasks in the current session' provides some specificity that distinguishes it from general task execution, but 'implementation plans' is still broad enough to potentially conflict with other planning or execution skills. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill with excellent workflow clarity and actionability. The two-stage review process is clearly documented with explicit validation checkpoints and feedback loops. The main weakness is some verbosity in the advantages section and example workflow that could be tightened without losing clarity.
Suggestions
Trim the 'Advantages' section - much of it restates what's already clear from the process description
Consider shortening the example workflow to show just one complete task cycle rather than multiple tasks with similar patterns
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy - the advantages section repeats information already conveyed, and the example workflow is quite lengthy. The dot diagrams add visual clarity but also add significant token count. | 2 / 3 |
Actionability | Provides concrete, actionable guidance with specific prompt template references, clear status handling instructions, model selection criteria, and a detailed example workflow showing exact dialogue patterns. The process is copy-paste ready. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with explicit validation checkpoints (spec compliance review → code quality review), clear feedback loops (reviewer finds issues → implementer fixes → re-review), and explicit sequencing via the dot diagram and red flags section. | 3 / 3 |
Progressive Disclosure | Well-structured with clear sections, references to external prompt templates (./implementer-prompt.md, etc.), and links to related skills. Content is appropriately organized with quick reference sections and detailed explanations separated. | 3 / 3 |
Total | 11 / 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.
- 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.