using-superpowers

Use when starting any conversation - routes work through the correct worker agents before any task action, requiring explicit worker selection and visible compliance

Quality

60%

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

73%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 content is highly actionable with concrete templates, pipelines, role boundaries, and a clearly sequenced workflow with checkpoints. Its main weakness is conciseness: the same routing and compliance format is restated multiple times alongside rhetorical emphasis blocks.

Suggestions

Collapse 'Mandatory Worker Routing', 'Worker Self-Identification', 'Worker Compliance Footer', and 'Execution Template' into a single canonical workflow section so each format token is defined once.

Remove or shrink the ALL-CAPS <EXTREMELY-IMPORTANT> block and the 'Red Flags' rationalization list; the Core Rule and Execution Template already enforce the behavior.

Consider moving the worker-role catalog and default-pipeline heuristics into a reference file (e.g. WORKERS.md) to shorten the main SKILL.md and improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body restates the same routing/self-identification/compliance format across 'Mandatory Worker Routing', 'Worker Self-Identification', 'Worker Compliance Footer', and again in 'Execution Template', plus an ALL-CAPS emphasis block and a rhetorical 'Red Flags' list — several padded, redundant sections rather than lean guidance; no concept-explanation padding is present, but the structural repetition is notable verbosity.	2 / 5
Actionability	Provides copy-paste-ready output templates ('Selected worker agents: <ordered list>', 'Active agent: <agent name>', 'Worker compliance: followed <agent-name> format'), concrete per-task default pipelines, explicit Does/Does-not role boundaries, and worked examples — fully executable guidance covering the common cases for an instruction-only skill.	5 / 5
Workflow Clarity	The Execution Template gives a clearly sequenced four-step workflow (Route → Execute current worker → Compliance footer → Re-announce next worker) with explicit checkpoints and a feedback loop ('If a worker cannot follow its format... say so explicitly and stop'), matching the clear-sequence-with-validation anchor.	5 / 5
Progressive Disclosure	Single self-contained file with no nested references and consistently well-organized section headers throughout; the worker-role catalog and default pipelines could arguably live in reference files but are reasonably placed inline, fitting 'good structure; most content appropriately placed' rather than the fully-split score 5.	4 / 5
	Total	16 / 20 Passed

Description

47%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 states both what the skill does and when to use it, but its trigger is the overly broad 'any conversation', which yields poor trigger-term quality and high conflict risk. Specificity is adequate but not comprehensive.

Suggestions

Replace the generic 'starting any conversation' trigger with concrete trigger phrases a user would actually say (e.g., 'Use when beginning a coding, review, or refactoring task that warrants routing to a specialized worker agent').

Narrow the trigger scope so the skill is distinguishable from topic-specific skills and does not fire on every conversational turn.

Add one or two more concrete actions (e.g., 'announces the selected worker pipeline and enforces per-worker output format') to lift specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (worker-agent routing) and a couple of concrete actions — 'routes work through the correct worker agents' and 'requiring explicit worker selection and visible compliance' — but coverage is not comprehensive, matching the '1-2 concrete actions' anchor rather than the fuller list at score 4.	3 / 5
Completeness	Both 'what' (routes work through worker agents with explicit selection and visible compliance) and 'when' ('Use when starting any conversation') are present and explicit, but the 'when' is generic rather than concrete trigger phrases, so it sits at the 'both present, when could be more specific' anchor rather than 5.	4 / 5
Trigger Term Quality	The only trigger cue is 'Use when starting any conversation', which is generic rather than a phrase a user would naturally utter; the rest ('worker agents', 'task action') is technical jargon with no natural synonyms, fitting the 'one or two generic keywords; missing the natural phrases' anchor.	2 / 5
Distinctiveness Conflict Risk	The trigger 'starting any conversation' makes the skill fire on essentially every turn, creating high overlap risk with virtually all other skills; although the described capability (worker routing) is named, the maximal trigger scope matches the 'very broad; high overlap risk' anchor rather than the niche-distinct score 5.	2 / 5
	Total	11 / 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: roman01la/skills-agents
Path: skills/using-superpowers/SKILL.md
Commit: aa6f9d3

Reviewed: 24 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.