using-superpowers

Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions

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 ./skills/using-superpowers/SKILL.md

Quality

Content

61%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 skill body is a well-structured, actionable behavioral policy with clean one-level-deep platform references, but it carries rhetorical repetition that pads the token budget and lacks explicit validation checkpoints in its workflow. It is effective guidance with room to tighten.

Suggestions

Collapse the <EXTREMELY-IMPORTANT> block and trim the Red Flags table, since both restate 'invoke skills before acting'; keep one concise reinforcement instead of many.

Add an explicit validation step to the workflow (e.g., confirm the invoked skill actually matches the task before proceeding).

Add a Platform Adaptation entry for Gemini to match the existing gemini-tools.md reference and the GEMINI.md mention in the body.

Dimension	Reasoning	Score
Conciseness	Sections are short and well-organized, but the <EXTREMELY-IMPORTANT> block and the 12-row Red Flags table restate the same single idea ('check for skills first') several times, adding rhetorical padding around a concept Claude already understands.	3 / 5
Actionability	Gives concrete behavioral directives such as 'Invoke relevant or requested skills BEFORE any response', announce 'Using [skill] to [purpose]', and create a todo per checklist item, with only a minor gap in platform-specific invocation mechanics.	4 / 5
Workflow Clarity	A clear sequence exists (check for skills, invoke, announce, follow exactly, create todos), but there are no explicit validation checkpoints or feedback loops to confirm the right skill was applied, leaving checkpoints implicit.	3 / 5
Progressive Disclosure	The body is a concise overview with a clearly signaled one-level-deep reference list (Codex, Pi, Antigravity, Hermes) pointing to verified real files; the minor gap is that gemini-tools.md exists and Gemini is referenced in the body but has no Platform Adaptation entry.	4 / 5
	Total	14 / 20 Passed

Description

55%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 states both its purpose and a 'Use when' trigger, but the trigger is so broad ('any conversation') that it conflicts with almost every other skill, and the concrete actions described are minimal. It is functionally clear yet insufficiently distinct.

Suggestions

Narrow the trigger from 'any conversation' to a more specific, less conflict-prone condition (e.g., 'Use at the start of a task to decide which skills apply before responding').

Add 1-2 more concrete actions so the description enumerates what the skill actually does beyond 'requiring skill invocation'.

Include natural user-facing synonyms (e.g., 'skills', 'available skills', 'which skill to use') to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('how to find and use skills') and one concrete rule ('requiring skill invocation before ANY response'), matching the anchor that names domain plus 1-2 concrete actions without comprehensive coverage.	3 / 5
Completeness	Answers both 'what' ('establishes how to find and use skills, requiring skill invocation') and 'when' ('Use when starting any conversation'); the 'when' is present and explicit but extremely broad rather than specific.	4 / 5
Trigger Term Quality	Includes relevant phrases like 'skills', 'skill invocation', and 'clarifying questions', but 'starting any conversation' is not a phrase users naturally say and common synonyms/variations are missing.	3 / 5
Distinctiveness Conflict Risk	The trigger 'starting any conversation' is maximally broad and would fire for virtually every interaction, creating very high overlap risk with nearly every other skill.	2 / 5
	Total	12 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: obra/superpowers
Path: skills/using-superpowers/SKILL.md
Commit: b36e082

Reviewed: 10 days 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.