using-superpowers

在开始任何对话时使用——确立如何查找和使用技能，要求在任何响应（包括澄清性问题）之前调用 Skill 工具

Quality

61%

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

71%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.

This instruction-only meta-skill is well-structured with strong progressive disclosure and concrete, actionable routing guidance. Its main weakness is rhetorical padding and repeated rationalization-counter rows that inflate the token budget without adding distinct information.

Suggestions

Trim the 红线 table to the 4-5 most distinct anti-patterns and cut the '这不可协商。你不能通过合理化来逃避' rhetoric to reduce repetition and token cost.

Add an explicit validation step to the workflow (e.g. 'after invoking a skill, confirm its checklist items are tracked as todos before proceeding') to introduce a checkpoint.

Provide one short canonical end-to-end example showing the full announce→follow→todo pattern in a single block to remove minor actionability gaps.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean rules and routing tables, but the emphatic <EXTREMELY-IMPORTANT> block and the 13-row 红线 table repeat the same 'don't rationalize, check skills first' idea several times, adding noticeable padding that could be tightened.	3 / 5
Actionability	It gives concrete executable directives — invoke skills before responding, announce '使用 [技能] 来 [目的]', create a todo per checklist item — plus concrete routing examples ('让我们构建 X' → brainstorming) and a scenario→skill mapping table, with only minor gaps in a canonical end-to-end example.	4 / 5
Workflow Clarity	The gating workflow is clearly sequenced (check → announce → follow → create todos) with explicit priority ordering (process skills before implementation skills), but it lacks an explicit validation checkpoint confirming the skill was correctly applied.	4 / 5
Progressive Disclosure	The body is well-sectioned and correctly offloads platform-specific details to one-level-deep reference files via a clear mapping table; the referenced files (codex-tools.md, pi-tools.md, etc.) all exist, yielding clean overview-plus-references navigation.	5 / 5
	Total	16 / 20 Passed

Description

51%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 conveys both purpose and the before-any-response trigger, but its triggers are phrased as instructions to Claude rather than natural user utterances, limiting trigger-term quality. As an intentionally broad meta-skill it carries inherent overlap risk.

Suggestions

Add natural user-utterance trigger phrases (e.g. 'Use at the start of any new task or conversation, before exploring code or asking clarifying questions') so the trigger reads like something a user would actually say.

Name 1-2 more concrete capabilities (e.g. 'route tasks to the right skill, declare intent, and turn skill checklists into todos') to lift specificity beyond a single action.

Reframe the 'when' clause with concrete trigger conditions rather than only timing-based instruction to push completeness toward the top anchor.

Dimension	Reasoning	Score
Specificity	The description names the skill-discovery domain and one concrete action ('调用 Skill 工具' before responding), but the action set is narrow and not comprehensive, matching the 'domain + 1-2 concrete actions' anchor rather than the 'several specific actions' level above.	3 / 5
Completeness	It states both what ('确立如何查找和使用技能') and an explicit when ('在开始任何对话时' / before any response), but the when lacks concrete user-mention trigger phrases, keeping it just below the fully-explicit anchor.	4 / 5
Trigger Term Quality	The only trigger phrasing is '在开始任何对话时' / '在任何响应之前', which is instruction-to-Claude rather than natural keywords a user would actually say; it lacks the concrete utterance-style triggers users naturally produce.	2 / 5
Distinctiveness Conflict Risk	As a meta-skill designed to gate virtually every conversation it has a distinct niche but high by-design overlap with all other skills, fitting 'somewhat specific but could overlap with similar skills' rather than 'mostly distinct'.	3 / 5
	Total	12 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: jnMetaCode/superpowers-zh
Path: skills/using-superpowers/SKILL.md
Commit: c68725b

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.