using-kit

Enforces skill discovery and invocation governance for every task. Use at the start of any conversation, before responding to any user message, when deciding whether a skill applies, when building or modifying features (triggers the brainstorming chain), or when operating within a team context. Defines the default workflow chain (brainstorming -> writing-plans -> build-flow -> finish-branch) and prevents rationalizing away skill usage.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

85%

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

The body is well-structured and highly actionable, with a clear sequenced workflow chain, a decision flow diagram, and concrete tool/announcement guidance. The only real weakness is conciseness — the repeated 'do not rationalize' emphasis across the EXTREMELY-IMPORTANT block and the 12-row Red Flags table is redundant.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient but padded: the EXTREMELY-IMPORTANT block restates 'The Rule', and the 12-row Red Flags table repeats the single 'don't rationalize, check skills first' idea many times, which could be tightened without losing clarity.	2 / 3
Actionability	It gives concrete executable guidance for an instruction skill — named tools ('Use the `Skill` tool', 'Never use the Read tool on skill files'), an exact announcement template ('Using [skill] to [purpose]'), TodoWrite per checklist item, and a decision flow diagram.	3 / 3
Workflow Clarity	The Default Workflow Chain is a clearly numbered four-step sequence with 'Each skill invokes the next', and the Red Flags table plus the flow diagram provide decision feedback and a self-check checklist for the governance process.	3 / 3
Progressive Disclosure	The content is organized into clearly headed sections (Access Skills, The Rule, Workflow Chain, Red Flags, Skill Priority, Skill Types, User Instructions) with no nested or broken references; a single self-contained file is appropriate for this always-on meta-skill.	3 / 3
	Total	11 / 12 Passed

Description

77%

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 answers both what the skill does and when to use it, with a concrete named workflow chain. Its main weakness is trigger breadth — the meta-triggers are situational rather than natural user keywords and apply to essentially every conversation.

Suggestions

Tighten triggers to natural user phrasings (e.g. 'Use when the user asks to build or modify a feature') instead of internal decision points like 'before responding to any user message'.

Narrow the always-on trigger scope so the skill is less likely to conflict with every other skill on every message, or reframe it as applying only when a task is identifiable.

Replace the buzzword 'invocation governance' with a concrete capability verb to keep specificity fully grounded in observable actions.

Dimension	Reasoning	Score
Specificity	It lists multiple concrete actions — 'Enforces skill discovery and invocation governance', 'Defines the default workflow chain (brainstorming -> writing-plans -> build-flow -> finish-branch)', and 'prevents rationalizing away skill usage' — naming specific named skills in the chain.	3 / 3
Completeness	It explicitly states both what it does (enforces skill governance, defines the default workflow chain) and when to use it via an explicit 'Use at the start of any conversation, before responding...' clause with multiple triggers.	3 / 3
Trigger Term Quality	It gives trigger situations ('building or modifying features', 'team context', 'start of any conversation') but these are meta-decision points rather than the natural keywords a user would actually say, and coverage of common user phrasings is limited.	2 / 3
Distinctiveness Conflict Risk	The niche (skill-usage governance) is distinct from implementation skills, but triggers like 'start of any conversation' and 'before responding to any user message' are maximally broad and would cause it to fire on nearly every message, raising overlap risk.	2 / 3
	Total	10 / 12 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: shousper/claude-kit
Path: skills/using-kit/SKILL.md
Commit: ae181ef

Reviewed: about 3 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.