using-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
81
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 94%
↑ 1.03xAgent success when using this skill
Validation for skill structure
Evaluation results
100%
56%AI Capability Workflow Reference Guide
Skill-invocation workflow guide
Pre-action invocation
100%
100%
Low-probability threshold
60%
100%
Correct invocation method
60%
100%
Announcement step
0%
100%
Checklist-to-todo conversion
80%
100%
No-checklist handling
50%
100%
Process-before-implementation
0%
100%
Brainstorm before planning
0%
100%
Rigid skill compliance
10%
100%
Instructions define WHAT not HOW
80%
100%
Without context: $0.2368 · 1m 23s · 10 turns · 59 in / 4,082 out tokens
With context: $0.2964 · 1m 21s · 13 turns · 258 in / 3,984 out tokens
94%
46%Multi-Capability Process Checklist
Process-skills priority ordering
Skill check as first step
60%
100%
Low-threshold invocation
80%
100%
Process before implementation
100%
100%
Brainstorm before planning phase
60%
100%
Announcement in worked example
20%
100%
Wrong-skill handling
30%
80%
Rigid process compliance
30%
90%
Rationalization red flags
100%
100%
Clarifications require skill check
0%
100%
User instruction scope
0%
70%
Without context: $0.3073 · 1m 51s · 12 turns · 61 in / 5,102 out tokens
With context: $0.3432 · 1m 51s · 15 turns · 308 in / 5,137 out tokens
90%
84%Developer Training Module: Working Effectively with AI Capabilities
Skill announcement and checklist tracking
Pre-response invocation
0%
100%
Correct invocation tool
0%
80%
Announcement format
0%
100%
Checklist-to-todo conversion
0%
100%
No-checklist behavior
0%
20%
Rigid vs flexible distinction
40%
100%
Incorrect behavior examples
10%
100%
Process skill priority
0%
100%
Low-probability threshold
0%
100%
Mandatory framing
10%
100%
Without context: $0.2634 · 1m 27s · 10 turns · 9 in / 3,965 out tokens
With context: $0.3893 · 1m 43s · 20 turns · 116 in / 4,751 out tokens
- Evaluated
- Agent
- Claude Code
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.