using-skills

Always use this skill at the beginning of a session. It establishes how to find and use skills, and requires relevant Skill tool invocation before ANY response including clarifying questions

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 ./using-skills/SKILL.md

Quality

Content

67%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 a well-structured, actionable meta-skill with a clear decision flowchart and concrete invocation protocol. It is held back mainly by repetitive emphasis (the caps block and the long Red Flags table) that could be tightened for token efficiency.

Suggestions

Collapse the EXTREMELY-IMPORTANT caps block and the Red Flags table into a concise 'Stop and invoke if you catch yourself thinking...' list of 3-4 items to cut repetition.

Move the per-environment access instructions (Codex, other environments) into a short reference or trim to one line, since the Claude Code path already conveys the pattern.

Add a one-line note on what to do when an invoked skill turns out not to apply, to close the minor workflow gap.

Dimension	Reasoning	Score
Conciseness	Mostly efficient behavioral guidance, but the all-caps EXTREMELY-IMPORTANT block and the 12-row Red Flags table repeat the same anti-rationalization point ('Skills tell you HOW to...') and could be trimmed without losing clarity.	3 / 5
Actionability	Gives concrete, executable steps ('Invoke Skill tool', "Announce: 'Using [skill] to [purpose]'", 'Create TodoWrite todo per item') and a decision flowchart; minor gaps in that platform-specific invocation is left to external docs.	4 / 5
Workflow Clarity	The dot flowchart lays out a clear sequence with decision checkpoints (might a skill apply? → invoke → announce → checklist? → todos → follow), and there are no destructive/batch operations requiring validation caps; only a minor lack of explicit error/feedback handling.	4 / 5
Progressive Disclosure	No bundle files exist and none are needed; the body is organized into clearly labeled sections (How to Access Skills, The Rule, Red Flags, Skill Priority, Skill Types, User Instructions), though the leading ALL-CAPS block is loosely structured.	4 / 5
	Total	15 / 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 establishes this as a mandatory session-start meta-skill with explicit when-guidance, but it lacks natural trigger terms a user would actually say and its 'what' is somewhat abstract. It is distinct from domain skills but reads more as a mandate than a capability description.

Suggestions

Add natural trigger phrases a user might say (e.g., 'Use when starting a new session or before answering any user request') so the trigger is not purely imperative.

Make the 'what' more concrete by naming the specific behaviors it enforces (skill discovery, mandatory invocation, announce-and-follow protocol) rather than the vague 'establishes how to find and use skills'.

Consider softening the all-caps mandate tone in the description so it reads as a capability statement in third person.

Dimension	Reasoning	Score
Specificity	Names the meta-skill domain ('find and use skills') and one concrete action ('Skill tool invocation before ANY response including clarifying questions'), but the action set is thin and the domain is abstract.	3 / 5
Completeness	Both 'what' ('establishes how to find and use skills') and 'when' ('Always use this skill at the beginning of a session... before ANY response including clarifying questions') are present, with explicit trigger guidance equivalent to a 'Use when...' clause; the 'what' is slightly vague.	4 / 5
Trigger Term Quality	It offers no natural user trigger phrases ('at the beginning of a session' is a mandate, not something a user would say); only the generic term 'skills' appears.	2 / 5
Distinctiveness Conflict Risk	The session-start, always-invoke framing gives it a distinct niche as a meta-skill, with only minor overlap risk against other session-bootstrap instructions.	4 / 5
	Total	13 / 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: ceshine/ceshine-agent-skills
Path: using-skills/SKILL.md
Commit: a8d25c2

Reviewed: 3 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.