creating-skills

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Letta Code's capabilities with specialized knowledge, workflows, or tool integrations.

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 ./src/skills/builtin/creating-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, actionable meta-skill with a clear sequenced workflow, real bundled scripts and references that are properly signaled and verified to exist, and explicit validation/feedback loops. The main weakness is conciseness: conceptual analogies and some overlap between sections could be trimmed.

Suggestions

Trim illustrative analogies ("onboarding guides", "narrow bridge with cliffs") and consolidate overlap between the About Skills and Anatomy of a Skill sections to tighten conciseness toward a 4-5.

Make validation checkpoints more explicit and manual rather than delegated to the packaging script (e.g., call out a verify step after Step 4 editing and before Step 5 packaging) to lift workflow_clarity toward 5.

Consider moving the full progressive-disclosure pattern code blocks (Patterns 1-3) into a reference file, keeping only the selection guidance inline, to reduce body length and improve progressive_disclosure toward 5.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and earns most of its tokens, but includes some unnecessary explanation and analogies that could be tightened (e.g., "Think of them as onboarding guides", the "narrow bridge with cliffs" analogy, and conceptual overlap between the About Skills and Anatomy sections), fitting the 3 anchor better than 4.	3 / 5
Actionability	It provides concrete, executable commands (npx tsx .../init-skill.ts, .../package-skill.ts), real bundled scripts, a concrete YAML frontmatter example, and specific worked scenarios (editing-pdfs, building-frontend-apps, querying-bigquery); the minor gap is that design-principle portions (degrees of freedom) remain somewhat abstract, keeping it just below a 5.	4 / 5
Workflow Clarity	The 6-step Skill Creation Process is clearly sequenced ("Follow these steps in order") with checkpoints present (test added scripts in Step 4, packaging auto-validates with an explicit fix-and-retry loop in Step 5, and the iterate feedback loop in Step 6); validation is partly delegated to scripts rather than spelled out as explicit manual checkpoints, so it sits at 4 rather than 5.	4 / 5
Progressive Disclosure	References are one level deep, clearly signaled ("See references/workflows.md for sequential workflows and conditional logic", "See references/output-patterns.md for template and example patterns"), and the referenced files genuinely exist with relevant detailed content; the minor gap is that the body is fairly long (~365 lines) with substantial inline example content, keeping it just below a 5.	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, explicit description that clearly states both what the skill does and when to use it with natural trigger phrases and a distinct niche. Its only weakness is specificity: it names just two concrete actions (create, update) rather than a comprehensive action list.

Dimension	Reasoning	Score
Specificity	The description names the domain ("creating effective skills") and 1-2 concrete actions ("create a new skill", "update an existing skill") but stops there; the remainder ("specialized knowledge, workflows, or tool integrations") describes capability scope rather than additional actions, so it is not comprehensive enough for a 4.	3 / 5
Completeness	It explicitly answers both what ("Guide for creating effective skills") and when ("This skill should be used when users want to create a new skill (or update an existing skill)...") with concrete trigger phrases, satisfying the anchor for a 5; the explicit "should be used when" clause avoids the 3-cap for missing trigger guidance.	5 / 5
Trigger Term Quality	"create a new skill" and "update an existing skill" are natural phrases users would actually say, plus the capability keywords (knowledge, workflows, tool integrations) give good coverage; a few common synonyms (build, make, write) are missing, keeping it just below a 5.	4 / 5
Distinctiveness Conflict Risk	Skill creation is a clear, unique meta-niche with distinct triggers (create/update a skill) that no domain skill would compete with, giving minimal conflict risk per the 5 anchor.	5 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 6 missing	Warning
referenced_paths_exist	Referenced path issues: 12 missing	Warning

	Total	14 / 16 Passed

Repository: letta-ai/letta-code
Path: src/skills/builtin/creating-skills/SKILL.md
Commit: 051b47f

Reviewed: 2 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.