using-agent-skills

Discovers and invokes agent skills. Use when starting a session, or when you need to decide which skill or workflow applies to the piece of work at hand. This is the meta-skill that governs how all other skills are discovered and invoked.

Quality

68%

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 catalog of sibling skills with a clear decision tree, lifecycle sequence, and strong behavioral guidance. The main costs are redundancy (behaviors restated as failure modes; the catalog rendered three ways) and a dangling reference to a file outside the skill bundle.

Suggestions

Merge 'Failure Modes to Avoid' into 'Core Operating Behaviors' (each failure mode restates an existing behavior) to cut roughly 15 lines of duplication.

Consolidate the three renderings of the skill catalog — ASCII tree, lifecycle list, and Quick Reference table — into one primary view plus one compact lookup, or move the Quick Reference table to a reference file.

Fix or inline the `../../references/definition-of-done.md` reference: the path escapes the skill bundle and no references/ directory ships with the skill, so the Definition of Done content is effectively unavailable.

Dimension	Reasoning	Score
Conciseness	The body is mostly tables and decision trees, but carries noticeable redundancy: the 'Failure Modes to Avoid' section restates the six 'Core Operating Behaviors' almost item-for-item, and the skill catalog appears three times (ASCII tree, 16-step lifecycle, and 23-row Quick Reference table). This matches 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than the noticeably padded 2, since each section is individually lean.	3 / 5
Actionability	Concrete, executable guidance is present: a condition-to-skill routing tree, a copy-paste 'ASSUMPTIONS I'M MAKING' template, and an example Good/Bad phrasing for confusion management. It stays below 5 because the actual invocation mechanism (how to load or run a named skill) is never specified, leaving a minor gap between 'apply the corresponding skill' and execution.	4 / 5
Workflow Clarity	Multi-step processes are clearly sequenced: the numbered 16-step lifecycle with an explicit parallelism note ('runs parallel with 7-9, not after') and a reduced bug-fix path ('debugging-and-error-recovery → test-driven-development → code-review-and-quality'). Verification checkpoints exist ('A task is not complete until verification passes', the Definition of Done), but per-step validation inside the sequences is mostly implicit, matching 'clear sequence with most checkpoints present; minor validation gaps'.	4 / 5
Progressive Disclosure	The document is well-organized with clear headers, and the single external reference ('See `../../references/definition-of-done.md`') is well-signaled and one level deep. It does not reach 5 because no bundle directory exists in this skill — the referenced file sits outside the skill folder and cannot be verified — and the 23-row Quick Reference table is inline content that could plausibly live in a separate reference file.	4 / 5
	Total	15 / 20 Passed

Description

70%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 well-formed description in third-person voice that clearly states both capability and trigger conditions for a meta-skill. Its main weaknesses are limited action specificity (only two verbs) and an abstract 'when' clause that could name more concrete trigger phrases.

Suggestions

Add one or two more concrete capabilities to the 'what' clause (e.g., how skills are surfaced, ordered, or chained) to lift specificity.

Make the 'when' clause more concrete with user-shaped phrases such as 'Use when the user asks which skill to use, mentions a workflow, or starts a new session'.

Dimension	Reasoning	Score
Specificity	"Discovers and invokes agent skills" names the domain and exactly two concrete actions (discover, invoke), matching the anchor for 1-2 concrete actions without comprehensive coverage. It does not reach 4 because no additional specific capabilities are listed (e.g., what discovery or invocation actually involves), and it is above 2 because the domain is named with real actions rather than generic processing.	3 / 5
Completeness	It explicitly answers both: what ("Discovers and invokes agent skills") and when ("Use when starting a session, or when you need to decide which skill or workflow applies"). The 'when' is present and explicit but somewhat abstract ("the piece of work at hand") rather than concrete trigger phrases, matching the anchor where 'when' could be more specific rather than the fully concrete 5.	4 / 5
Trigger Term Quality	Natural phrases like "Use when starting a session", "decide which skill or workflow applies", and "skill" are terms users would plausibly say when needing this meta-skill. It falls short of 5 because common variations such as "tool", "task routing", or specific trigger contexts are missing, but the coverage is solid rather than partial.	4 / 5
Distinctiveness Conflict Risk	"This is the meta-skill that governs how all other skills are discovered and invoked" carves out a clear niche that is distinguishable from task-level skills. Minor overlap risk remains with generic skill-selection or planning prompts, so it sits at mostly-distinct rather than the minimal-conflict 5.	4 / 5
	Total	15 / 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: 2686b62

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.