using-superpowers

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

Quality

32%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/using-superpowers/SKILL.md

Quality

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 functions as a meta/bootstrap skill but fails as a skill description. It lacks concrete actions, contains no user-facing trigger terms, and its scope ('any conversation') makes it indistinguishable from every other skill. It reads more like an internal system instruction than a skill description.

Suggestions

Define concrete actions the skill performs, e.g., 'Indexes available skills, matches user requests to appropriate skill files, and loads relevant skill instructions.'

Replace the overly broad 'any conversation' trigger with specific scenarios, e.g., 'Use when the user asks what skills are available, requests help finding a capability, or when no other skill clearly matches the user's request.'

Add natural trigger terms users might say, such as 'what can you do', 'list skills', 'help me find', 'available tools' to improve trigger term quality and distinctiveness.

Dimension	Reasoning	Score
Specificity	The description does not list any concrete actions or capabilities. 'Establishes how to find and use skills' is abstract and meta-level, not describing what specific tasks the skill performs.	1 / 3
Completeness	It has a 'when' clause ('Use when starting any conversation') but the 'what' is extremely vague — it only says it 'establishes how to find and use skills' without specifying concrete actions. The 'when' is also overly broad (every conversation), which undermines its usefulness as a trigger.	2 / 3
Trigger Term Quality	There are no natural user-facing keywords. Users would never say 'starting any conversation' or 'Skill tool invocation' — these are internal system concepts, not terms a user would use in a request.	1 / 3
Distinctiveness Conflict Risk	Triggering on 'any conversation' means this would conflict with every other skill. It is maximally generic in scope and would always be selected, providing no meaningful differentiation.	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.

This is a meta-skill about skill discovery and usage that suffers significantly from verbosity and repetition. The core instruction ('always invoke skills before responding') is hammered home through multiple redundant mechanisms (bold warnings, a 12-row table of rationalizations, a DOT graph, and repeated emphatic statements). While the workflow is clear and the platform adaptation references are well-structured, the token cost is disproportionate to the information conveyed.

Suggestions

Reduce the Red Flags table to 3-4 representative examples instead of 12 variations of the same idea, cutting token usage significantly.

Remove the EXTREMELY-IMPORTANT block and SUBAGENT-STOP block or consolidate them into the main flow—the emphatic repetition wastes tokens on a concept already clearly stated.

Replace the DOT graph with a simple numbered list of 4-5 steps; the graph syntax consumes many tokens for a linear decision flow.

Consolidate the 'How to Access Skills' and 'Platform Adaptation' sections into a single brief section with a reference link for platform-specific details.

Dimension	Reasoning	Score
Conciseness	Extremely verbose and repetitive. The core message ('invoke skills before responding') is stated in at least 5 different ways. The 12-row 'Red Flags' table is padded with variations of the same idea. The DOT graph, while structured, adds tokens for a concept that could be expressed in 3 bullet points. Much of this content tells Claude things it should already understand about following instructions.	1 / 3
Actionability	Provides some concrete guidance (invoke Skill tool before responding, use TodoWrite for checklists, priority ordering), but much of the content is motivational/behavioral rather than executable. The platform-specific tool invocation section is concrete but brief. No executable code examples; the DOT graph is illustrative but not directly actionable.	2 / 3
Workflow Clarity	The workflow is clearly sequenced via the DOT digraph showing the decision flow from message receipt through skill invocation to response. The priority ordering (process skills first, then implementation) and the rigid vs flexible distinction provide clear sequencing guidance. For a meta-skill about skill usage, the workflow is unambiguous.	3 / 3
Progressive Disclosure	References external files (references/copilot-tools.md, references/codex-tools.md) which is good, but the main content is a monolithic wall of text with multiple sections that could be condensed. The skill types section and platform adaptation section feel like they could be separate references. The content is structured with headers but overly long inline.	2 / 3
	Total	8 / 12 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: obra/superpowers
Commit: 6efe32c

Reviewed: 4 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.