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

32

Quality

26%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

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

Quality

Content

35%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is a meta-skill for skill discovery and invocation. Its core message ('always check for applicable skills before responding') is valid but delivered with extreme verbosity and repetition. The 'Red Flags' table, EXTREMELY-IMPORTANT block, and repeated '1% chance' language all say the same thing in different ways, consuming significant token budget. The workflow is reasonably clear via the dot graph but lacks error handling paths.

Suggestions

Drastically reduce repetition: consolidate the EXTREMELY-IMPORTANT block, the '1% chance' mentions, and the 12-row Red Flags table into a single concise rule with 2-3 key examples of rationalization to avoid.

Add error handling to the workflow: what should Claude do if the Skill tool returns no matching skill, or if an invoked skill doesn't apply after reading it?

Replace the dot graph with a simple numbered list of 4-5 steps — the graph consumes many tokens for a flow that's essentially linear with one branch.

Remove or significantly shorten the Platform Adaptation section — Claude can follow a simple 'check your platform docs for tool equivalents' instruction without listing each platform.

DimensionReasoningScore

Conciseness

Extremely verbose and repetitive. The 'Red Flags' table alone contains 12 rows hammering the same point ('check for skills first'). The EXTREMELY-IMPORTANT block, the repeated '1% chance' language, and extensive rationalization table all explain something Claude should grasp from a single clear instruction. The dot graph adds tokens for a relatively simple flow.

1 / 3

Actionability

Provides some concrete guidance (invoke Skill tool before responding, use TodoWrite for checklists, announce skill usage) but much of the content is motivational/behavioral rather than executable. The platform adaptation section references files but doesn't give concrete tool invocation syntax. The dot graph is descriptive but not directly executable.

2 / 3

Workflow Clarity

The dot graph provides a clear sequence for the skill-checking workflow, and the priority ordering (process skills first, then implementation) is helpful. However, there are no validation checkpoints or error recovery steps — what happens if a skill invocation fails? What if the Skill tool returns nothing? These gaps prevent a score of 3.

2 / 3

Progressive Disclosure

References external files (references/copilot-tools.md, references/codex-tools.md) for platform-specific details, which is good progressive disclosure. However, the main content itself is monolithic — the Red Flags table, Skill Types, and Skill Priority sections could be more concisely organized. No bundle files are provided to verify referenced paths exist.

2 / 3

Total

7

/

12

Passed

Description

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 rather than a task-specific skill, which makes it inherently difficult to evaluate against standard criteria. It lacks concrete actions, uses internal jargon instead of natural user language, and its trigger condition ('any conversation') is maximally broad, creating conflict with every other skill. The description would benefit from clearly stating what value it provides and narrowing its scope.

Suggestions

Replace the overly broad trigger 'any conversation' with specific conditions that actually warrant this skill, such as 'when the user asks what skills are available' or 'when no other skill matches the request'.

Add concrete actions describing what this skill actually does, e.g., 'Lists available skills, searches skill descriptions, and recommends the most relevant skill for the user's task.'

Include natural trigger terms users might say, such as 'what can you do', 'list skills', 'help me find a tool', or 'available capabilities'.

DimensionReasoningScore

Specificity

The description lacks concrete actions. It mentions 'establishes how to find and use skills' and 'requiring Skill tool invocation' but doesn't describe what specific capabilities or tasks the skill performs. The language is abstract and procedural rather than action-oriented.

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.' The when clause is present but overly broad (every conversation), and the what lacks substance.

2 / 3

Trigger Term Quality

There are no natural user-facing keywords. Terms like 'Skill tool invocation' and 'establishes how to find and use skills' are internal system jargon that no user would naturally say. 'Starting any conversation' is overly generic and not a meaningful trigger term.

1 / 3

Distinctiveness Conflict Risk

The description says to use this skill at the start of 'any conversation,' which means it would trigger for literally every request, creating maximum conflict with all other skills. It has no distinct niche or domain.

1 / 3

Total

5

/

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
obra/superpowers
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.