finding-agents

Find other agents on the same server. Use when the user asks about other agents, wants to migrate memory from another agent, or needs to find an agent by name or tags.

Quality

83%

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

Quality

Content

88%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 highly actionable, well-organized single-file skill: all commands are executable, options and output fields are documented, and the multi-step pattern is clearly sequenced. The only issues are cosmetic — redundant repeated commands in Examples versus Common Patterns, and a usage pattern misplaced under the Related Skills heading.

Suggestions

Deduplicate the Examples section against Common Patterns — drop `letta agents list --tags "origin:letta-code"` and the plain `letta agents list` repeats that already appear above, keeping only genuinely new combinations.

Move "Finding Agents by Topic" out from under the "Related Skills" heading to sit alongside the other Common Patterns, leaving Related Skills to reference only the migrating-memory skill.

Dimension	Reasoning	Score
Conciseness	The body is efficient — an options table with defaults and no padding explaining concepts Claude already knows — but the Examples section repeats commands already shown verbatim in Common Patterns (e.g. `letta agents list --tags "origin:letta-code"` appears twice, plain `letta agents list` three times). This is minor trimmable redundancy, matching anchor 4 rather than the every-token-earns-its-place anchor 5.	4 / 5
Actionability	Every command is fully executable and copy-paste ready, the options table documents flags with defaults, seven worked examples cover the common cases, and the Output section documents the returned fields. This matches anchor 5: specific examples covering the common cases with no gaps.	5 / 5
Workflow Clarity	This is a simple, single-purpose skill whose core action (`letta agents list` with documented flags) is unambiguous, and the one multi-step pattern ("Finding Agents by Topic") is a clearly numbered 3-step sequence. All operations are read-only, so no destructive/batch validation cap applies; per the simple-skill guidance a single unambiguous action scores 5.	5 / 5
Progressive Disclosure	No bundle files exist and none are needed — the skill is appropriately self-contained with well-labeled sections. The one organization flaw is that "Finding Agents by Topic" is nested as a subsection under "Related Skills" despite being a usage pattern rather than a related skill, which is the minor gap that distinguishes anchor 4 from anchor 5.	4 / 5
	Total	18 / 20 Passed

Description

78%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 description that clearly states what the skill does and gives three explicit, natural trigger conditions. Its main weakness is specificity: the single verb "find" undersells the concrete capabilities (fuzzy search, tag filtering, memory-block inclusion) documented in the body.

Suggestions

Enumerate the concrete actions in the description, e.g. "List, search, and filter agents on the same Letta server by name, query, or tags. Find agent IDs for memory migration."

Add common user phrasings as triggers, such as "list agents" or "search for an agent", to round out trigger-term coverage.

Dimension	Reasoning	Score
Specificity	"Find other agents on the same server" names the domain and one concrete action, but does not enumerate the concrete capabilities (list, fuzzy search, tag filtering) that the skill actually provides. It matches anchor 3 (domain plus 1-2 concrete actions) rather than anchor 4, which requires several specific actions listed.	3 / 5
Completeness	It explicitly answers both parts: a clear "what" ("Find other agents on the same server") followed by an explicit "Use when" clause with three concrete trigger scenarios. This matches the anchor-5 example structure exactly, and is not missing any element that anchor 4 would imply.	5 / 5
Trigger Term Quality	Phrases like "asks about other agents", "wants to migrate memory from another agent", and "find an agent by name or tags" are natural things a user would say. A few common variants ("list agents", "search agents") are missing, so it does not reach anchor 5's comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	The server-scoped agent-finding niche with memory-migration and name/tag triggers is mostly distinct from other skills. "Asks about other agents" could plausibly overlap with general agent-management or listing skills, giving minor overlap risk consistent with anchor 4 rather than the fully distinct anchor 5.	4 / 5
	Total	16 / 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: letta-ai/letta-code
Path: src/skills/builtin/finding-agents/SKILL.md
Commit: d4d1db7

Reviewed: 5 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.