using-agent-skills

Discovers and invokes agent skills. Use when starting a session or when you need to discover which skill applies to the current task. This is the meta-skill that governs how all other skills are discovered and invoked.

Quality

69%

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-agent-skills/SKILL.md

Quality

Content

56%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 body is a clear, well-structured router for skill discovery, but it carries redundant restatements, generic off-purpose behaviors, an unspecified invocation mechanism, and a dangling reference to a missing file.

Suggestions

Resolve the dangling reference: create ../../references/definition-of-done.md or remove the pointer, since progressive disclosure depends on references that actually exist.

Show the invocation mechanism (e.g., the Skill/tool call to dispatch a chosen skill) so actionability covers both discovery and invocation rather than only discovery.

Collapse the three restatements of the skill map (ASCII tree, Lifecycle Sequence, Quick Reference table) into one canonical view, and trim the generic Core Operating Behaviors that are not specific to skill discovery.

Dimension	Reasoning	Score
Conciseness	The discovery routing is restated three times (ASCII tree, Lifecycle Sequence, Quick Reference table) and the Core Operating Behaviors are generic engineering virtues off-purpose to skill discovery, so it is mostly efficient but could be tightened.	3 / 5
Actionability	Discovery guidance is concrete (decision tree, numbered sequence, lookup table), but the invocation half is unspecified — it names target skills without showing how to actually invoke them, leaving a key detail missing.	3 / 5
Workflow Clarity	The Lifecycle Sequence is a clearly numbered multi-step process with a general verification bar, but checkpoints are not woven explicitly into the sequence itself, leaving minor validation gaps.	4 / 5
Progressive Disclosure	Sections are well organized and a reference is signaled, but the referenced ../../references/definition-of-done.md does not exist (no references bundle) and there is no real progressive split, leaving references un-signaled in practice.	3 / 5
	Total	13 / 20 Passed

Description

82%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 cleanly answers both what and when with concrete, third-person trigger phrases and a distinct meta-skill niche. It is only slightly limited in action specificity, which is inherent to a routing meta-skill.

Dimension	Reasoning	Score
Specificity	"Discovers and invokes agent skills" names the domain plus two concrete actions, but coverage of actions is limited rather than comprehensive, matching the anchor listing 1-2 concrete actions.	3 / 5
Completeness	It explicitly states what it does ("Discovers and invokes agent skills... governs how all other skills are discovered and invoked") and when to use it ("Use when starting a session or when you need to discover which skill applies"), with concrete trigger phrases.	5 / 5
Trigger Term Quality	Triggers like "starting a session" and "discover which skill applies to the current task" are natural phrases users would say, though a few natural synonyms are missing for a full 5.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche as "the meta-skill that governs how all other skills are discovered and invoked," with distinct triggers unlikely to fire for a domain skill.	5 / 5
	Total	17 / 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: addyosmani/agent-skills
Path: skills/using-agent-skills/SKILL.md
Commit: df1edb2

Reviewed: about 19 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.