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

66%

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

78%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 well-structured, lean, and actionable with clean progressive disclosure to real reference files. The main improvement opportunity is tightening the repeated anti-rationalization emphasis and adding an explicit validation/retry checkpoint.

Suggestions

Consolidate the anti-rationalization guidance — the 'EXTREMELY-IMPORTANT' block, the 规则 section, and the 红线 table all repeat the same 'stop rationalizing' message; merge into one to recover tokens.

Add an explicit validate/feedback step (e.g. 'After invoking a skill, verify it matches the task; if not, fall back to a more specific skill') to raise workflow clarity into an explicit loop.

Trim the 12-row 红线 table to the highest-signal entries or compress thought/reality pairs into a shorter checklist.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's intelligence with no concept padding; the only trimmable excess is the 12-row red-lines table and the 'stop rationalizing' message repeated across three sections, fitting the 'efficient, minor over-explanation' anchor.	4 / 5
Actionability	Concrete executable guidance is present — announce '使用 [技能] 来 [目的]', create a todo per checklist item, and named routing ('brainstorming', 'systematic-debugging') — with only minor gaps in exhaustive coverage.	4 / 5
Workflow Clarity	The sequence (call skill → announce → follow → todos) is clear and the red-lines table acts as a self-check checkpoint; not a 5 because the validation is an implicit self-check rather than an explicit validate-and-retry loop.	4 / 5
Progressive Disclosure	The body is a clear overview with well-signaled one-level-deep references; all 7 referenced platform files (codex/pi/antigravity/copilot/hermes/qoder/gemini) exist and platform-specifics are appropriately split into those files.	5 / 5
	Total	17 / 20 Passed

Description

55%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 states both purpose and the always-on trigger, and is reasonably specific and distinct as a meta-skill. Its weakness is trigger-term quality: the activation cue is a timing rule rather than natural user phrasing.

Suggestions

Add a concrete natural-language trigger phrase users would actually say (e.g. 'Use whenever you start a new task or before answering any question') so the skill keys off user intent, not just timing.

Expand the 'what' with one or two more concrete capabilities (e.g. 'routes the task to the right skill and enforces a use-skill-first workflow') to lift specificity.

Consider mentioning representative trigger synonyms users say ('help me with', 'before you answer') to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	Names the meta-skill domain and two concrete actions ('确立如何查找和使用技能', '要求…调用 Skill 工具'), but coverage is not comprehensive — closest to the anchor listing 1-2 concrete actions.	3 / 5
Completeness	Both 'what' (find/use skills, require a Skill-tool call before responding) and 'when' (start of any conversation) are explicit, but the when lacks concrete user-utterance trigger phrases, so it falls below the 5 anchor.	4 / 5
Trigger Term Quality	The trigger '在开始任何对话时使用' is a timing rule rather than a phrase a user would naturally say, and the keywords ('Skill 工具', '技能') are internal/technical — missing the natural phrases users say.	2 / 5
Distinctiveness Conflict Risk	It occupies a distinct meta-routing niche with few competing skills; broadness ('any conversation') is intentional, leaving only minor overlap risk with closely related skills.	4 / 5
	Total	13 / 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: 79ea5d2

Reviewed: 2 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.