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

75%

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

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.

A well-structured meta-skill that routes tasks to a skill family with concrete templates, a decision tree, and a quick-reference table. It leans on behavioral coaching prose that partially restate each other and would benefit from tighter editing and a resolvable reference.

Suggestions

Trim or consolidate the Failure Modes list against Core Operating Behaviors to remove reverse restatements and concept explanations Claude already knows (e.g. the sycophancy and overcomplication paragraphs).

Make the lifecycle sequence explicitly gate each phase with a validation checkpoint rather than relying on the general 'Verify, Don't Assume' directive.

Resolve or inline the `../../references/definition-of-done.md` pointer so the single external reference is resolvable from the skill bundle.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient (routing tree, templates, quick-reference table) but includes coaching prose Claude already knows ("Sycophancy is a failure mode", "Your natural tendency is to overcomplicate") and the Failure Modes section largely restates the Core Operating Behaviors in reverse.	3 / 5
Actionability	Concrete routing is provided via the ASCII decision tree, the 16-step lifecycle sequence, the copy-paste ASSUMPTIONS template, and the Quick Reference table; minor gaps remain in criteria for borderline skills like doubt-driven-development.	4 / 5
Workflow Clarity	The numbered lifecycle sequence and the STOP/wait-for-resolution confusion procedure give a clear ordered flow with general verification checkpoints, but per-step validation gates are not woven explicitly into the lifecycle itself.	4 / 5
Progressive Disclosure	Clear section structure with a single clearly-signaled one-level-deep reference ("See ../../references/definition-of-done.md"); no bundle files exist in the review directory so the reference is unverifiable, and some inline coaching could plausibly live in a reference file.	4 / 5
	Total	15 / 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.

A strong, third-person description that answers what and when with concrete trigger phrases and a clearly distinct meta-skill niche. It is slightly held back on specificity by offering only two high-level actions.

Dimension	Reasoning	Score
Specificity	"Discovers and invokes agent skills" names the domain plus two concrete actions, matching the 1-2-actions anchor; it is not a 4 because only two high-level actions are given with no further breakdown.	3 / 5
Completeness	It states both what ("Discovers and invokes agent skills ... the meta-skill that governs how all other skills are discovered and invoked") and when ("Use when starting a session or when you need to discover which skill applies") with concrete trigger phrases.	5 / 5
Trigger Term Quality	"Use when starting a session or when you need to discover which skill applies to the current task" supplies natural trigger phrases with good coverage; not a 5 because it stops at two scenarios without synonyms or variants.	4 / 5
Distinctiveness Conflict Risk	The explicit framing "This is the meta-skill that governs how all other skills are discovered and invoked" carves a clear niche with distinct discovery triggers and minimal overlap with the skills it routes to.	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: 48cb116

Reviewed: ~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.