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

62%

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

57%

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

The skill is well-structured with genuine one-level-deep reference files and concrete routing tables, but its core 'how to find a skill' guidance is thin and the rationalization-avoidance material is repetitive. Tightening the redundancy and adding concrete skill-discovery steps would raise the weaker dimensions.

Suggestions

Add a concrete, numbered workflow for locating the right skill (e.g., list candidate skills, match against the task, announce the chosen one) so the promised '查找技能' capability is actionable.

Consolidate the '红线' table entries that express the same idea (e.g., the several 'check skills first / don't rationalize' rows) to remove redundancy.

Trim the emphatic rhetoric in the EXTREMELY-IMPORTANT block; the rule is already stated, so the motivational restatement costs tokens without adding guidance.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean imperative rules and tables, but the 12-row '红线' table and the emphatic '这不可协商' rhetoric repeat the same 'do not rationalize, check skills first' idea several times and could be tightened.	2 / 3
Actionability	Concrete guidance exists (announcement template '使用[技能]来[目的]', routing tables, platform reference paths), but the core promised capability of how to actually find the right skill is underspecified — it says 'call the Skill tool' without explaining discovery/search mechanics.	2 / 3
Workflow Clarity	Sequencing rules are present (skill check before clarifying questions, brainstorm before EnterPlanMode, process skills before implementation skills), but the body presents rules rather than an explicit numbered workflow with checkpoints.	2 / 3
Progressive Disclosure	The body is a clear overview with well-signaled one-level-deep references (references/codex-tools.md, pi-tools.md, copilot-tools.md, hermes-tools.md, qoder-tools.md, gemini-tools.md), all verified to exist and appropriately split by platform under the '平台适配' section.	3 / 3
	Total	9 / 12 Passed

Description

67%

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 states both purpose and an explicit activation trigger, which is its main strength. It is weakened by trigger terms that are operational rather than natural user language and by an over-broad trigger that risks constant co-activation.

Suggestions

Reword the trigger to include natural user-side phrasing (e.g., '当用户开始新任务或不确定该用哪个技能时') in addition to the behavioral 'before any response' condition.

Narrow or qualify the trigger so it does not fire on literally every turn, reducing conflict with other process skills.

Lead with a third-person capability statement (e.g., '查找并调用适用技能') before the directive, to make the what-vs-when split cleaner.

Dimension	Reasoning	Score
Specificity	Names the domain ('查找和使用技能') and a concrete action ('调用 Skill 工具' before responding), but it does not list multiple specific concrete actions like the score-3 anchor; it stays a single directive rather than a comprehensive capability list.	2 / 3
Completeness	It explicitly answers both what (establish how to find/use skills, require calling the Skill tool) and when ('在开始任何对话时使用', '在任何响应（包括澄清性问题）之前'), with explicit trigger guidance, so it is not capped at 2.	3 / 3
Trigger Term Quality	Relevant operational keywords appear ('查找和使用技能', '调用 Skill 工具', '澄清性问题'), but these are agent-behavior terms rather than natural phrases a user would say, and common user-side variations are missing.	2 / 3
Distinctiveness Conflict Risk	The meta-skill niche is distinguishable from domain skills, but its trigger ('start of any conversation / before any response') is extremely broad and co-triggers with essentially everything, creating overlap with other process/meta skills.	2 / 3
	Total	9 / 12 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: 12a4dc1

Reviewed: about 20 hours 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.