CtrlK
BlogDocsLog inGet started
Tessl Logo

using-superpowers

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

44

Quality

44%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/using-superpowers/SKILL.md

The canonical home for this skill is using-superpowers in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

60%Scale 1-5

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 that instructs Claude to always check for and invoke relevant skills before responding. Its workflow and structure are solid, with a clear decision graph and priority ordering. However, it suffers significantly from verbosity—the core message ('always invoke skills first') is repeated excessively through the opening block, the 12-row Red Flags table, and redundant phrasing throughout, all of which could be condensed to roughly half the current length without losing any information.

Suggestions

Condense the Red Flags table to 3-4 representative examples with a summary principle, rather than 12 variations of the same message.

Remove the <EXTREMELY-IMPORTANT> block or merge its content into 'The Rule' section—it repeats the same instruction three times before the skill even begins.

Add a concrete example of an actual Skill tool invocation (e.g., showing the tool call syntax and a sample announcement message).

DimensionReasoningScore

Conciseness

The skill is noticeably verbose with extensive repetition of the same core message ('invoke skills before doing anything'). The 'Red Flags' table contains 12 rows that all say essentially the same thing in different ways. The opening HTML-tagged block repeats the urgency three times. Claude already understands instruction priority—this level of hammering wastes tokens.

2 / 5

Actionability

The skill provides concrete, actionable guidance: use the Skill tool, announce usage, create TodoWrite items for checklists, follow a specific priority order. The dot graph gives a clear decision flow. Minor gap: no concrete example of an actual Skill tool invocation call or what the announcement looks like in practice.

4 / 5

Workflow Clarity

The dot graph provides a clear decision sequence from message receipt through skill invocation to response. The priority ordering (process skills first, then implementation) is well-defined. Minor gap: no explicit validation or error-recovery step for when a skill invocation fails or returns unexpected content.

4 / 5

Progressive Disclosure

The content is well-structured with clear sections (How to Access, The Rule, Red Flags, Skill Priority, Skill Types, User Instructions). For a standalone meta-skill with no bundle files, the organization is appropriate. Minor issue: the 'When to Use' section at the bottom is vague and feels tacked on, and there are no references to supplementary materials that could offload the verbose Red Flags table.

4 / 5

Total

14

/

20

Passed

Description

29%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.

This description is for a meta-skill that bootstraps skill discovery, but it fails as a discriminating description because it triggers on 'any conversation,' making it indistinguishable from all other skills. The 'what' is vague (establishes how to find and use skills) and uses internal jargon ('Skill tool invocation') rather than user-facing language. The description would benefit from specificity about what it actually does and clearer boundaries.

Suggestions

Narrow the trigger scope - instead of 'any conversation,' specify the actual conditions where this skill adds value, such as 'when the user asks what skills are available' or 'when no other skill matches the request'.

Replace internal jargon like 'Skill tool invocation' with concrete actions the skill performs, e.g., 'Searches available skills by keyword, lists skill capabilities, and recommends the best skill for a given task.'

Add distinctiveness by clarifying what this skill does NOT do - e.g., 'Does not perform task execution; only identifies and routes to the appropriate skill.'

DimensionReasoningScore

Specificity

The description names a domain (finding and using skills) but the actions are vague - 'establishes how to find and use skills' doesn't describe concrete actions. There's no detail about what specific operations are performed.

2 / 5

Completeness

It has a weak 'what' (establishes how to find and use skills) and a 'when' clause ('when starting any conversation'), but the 'when' is so broad it's essentially meaningless for skill selection. The 'Use when' clause is present but not specific enough to score higher.

3 / 5

Trigger Term Quality

The description lacks natural user-facing keywords. Terms like 'Skill tool invocation' are internal jargon, not phrases a user would say. 'Starting any conversation' is overly broad and not a meaningful trigger term.

2 / 5

Distinctiveness Conflict Risk

Triggering on 'any conversation' means this would conflict with every other skill. It's a meta-skill that by definition overlaps with all others, creating maximum conflict risk.

1 / 5

Total

8

/

20

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.