acquiring-skills

Discover and install skills from Hermes, ClawHub, GitHub, and other registries. Load this skill whenever a user asks for a capability you don't already have — image generation, social media, email, calendar, finance, DevOps, search, browser automation, etc.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./src/skills/builtin/acquiring-skills/SKILL.md

Quality

Content

75%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-structured skill body with excellent concrete commands and sensible safety gates for untrusted sources. Its weaknesses are length and redundancy — install instructions are repeated across sections and the worked examples restate earlier guidance — and reference-style catalog content that is inlined rather than split out.

Suggestions

Consolidate the repeated install-instruction blocks: show the `letta skills install <source> --agent $AGENT_ID` forms once in a single section and reduce the per-registry install snippets to one example each.

Trim the "Complete Example" section to reference the numbered workflow rather than restating the ask/install/review/invoke steps, or merge it with "Search Strategy" into one end-to-end procedure.

Move the Hermes hub source table and per-registry catalogs (Hermes, ClawHub details) into a references file (e.g. references/registries.md) linked from the body, keeping SKILL.md as a lean overview, and add a post-install verification step (e.g., `letta skills list --agent $AGENT_ID`) to the example workflow.

Dimension	Reasoning	Score
Conciseness	The body is dense with non-obvious, harness-specific information, but at ~290 lines it repeats itself: install command forms reappear across five sections, and "Complete Example" restates guidance already covered in Search Strategy and Cross-Harness Compatibility. It fits anchor 3 (mostly efficient but could be tightened) rather than anchor 4, since the redundancy is more than minor trimming.	3 / 5
Actionability	Fully executable throughout: concrete CLI commands ("hermes skills search kubernetes", "letta skills install clawhub:nano-banana-pro@1.0.1"), copy-paste bash blocks, curl API examples, and a git clone/copy/cleanup recipe cover all common cases. This matches anchor 5's copy-paste-ready guidance.	5 / 5
Workflow Clarity	The Complete Example lays out a clear ask-user → install → review-compatibility → invoke sequence, and the safety section supplies validation checkpoints ("Read and inspect any scripts before executing them", "read the full SKILL.md before using it"). It falls short of anchor 5 because there is no explicit post-install verification step or error-recovery loop (e.g., confirming via `letta skills list` and what to do on install failure).	4 / 5
Progressive Disclosure	No bundle files exist; the single SKILL.md is well organized with clear sections, tables, and per-registry subsections that are easy to navigate. It fits anchor 4 (good structure, most content appropriately placed) rather than anchor 5 because substantial reference material — the Hermes hub source table and per-registry details — is inlined where a one-level-deep reference file could carry it, and it is well over the short-skill threshold.	4 / 5
	Total	16 / 20 Passed

Description

83%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 when to load it, with a concrete list of natural trigger terms. The main weakness is the very broad trigger clause ("a capability you don't already have"), which could match many requests, and slightly incomplete coverage of the skill's full functionality (search, browse, manage).

Dimension	Reasoning	Score
Specificity	"Discover and install skills from Hermes, ClawHub, GitHub, and other registries" names several concrete actions (discover, install) and specific sources, but coverage is slightly short of comprehensive — it omits browsing, searching, and managing installed skills. It lists several specific actions with minor gaps, matching anchor 4 rather than anchor 5's comprehensive coverage.	4 / 5
Completeness	It explicitly answers both: what ("Discover and install skills from Hermes, ClawHub, GitHub, and other registries") and when ("Load this skill whenever a user asks for a capability you don't already have") with a concrete list of trigger phrases. This matches anchor 5; anchor 4 would require the 'when' clause to be less explicit, which it is not.	5 / 5
Trigger Term Quality	"image generation, social media, email, calendar, finance, DevOps, search, browser automation" are natural terms users would say, giving good keyword coverage. A few natural variations are missing (e.g., "plugin", "extension", "install a skill" phrasing), so it fits anchor 4 rather than anchor 5's comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	The niche is clear (acquiring skills from external registries) with distinct source names, making it mostly distinct from other skills. However, the trigger "whenever a user asks for a capability you don't already have" is a broad surface that could overlap with many skills, so it fits anchor 4's minor overlap risk rather than anchor 5's minimal conflict risk.	4 / 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: letta-ai/letta-code
Path: src/skills/builtin/acquiring-skills/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.