Tessl • The management layer for AI agent skills

SkillPublic

extension-creator

Create AiderDesk extensions by setting up extension files, defining metadata, implementing Extension interface methods, and updating documentation. Use when building a new extension, creating extension commands, tools, or event handlers.

Quality

85%

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

81%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-validated skill body with excellent workflow sequencing and a verified, well-signaled reference bundle. Its main weakness is token efficiency: the Process Overview, Postconditions/Success metrics, and several Common Situations examples duplicate content that already exists in the Rules or belongs in reference files.

Suggestions

Collapse the Process Overview section into the "Follow the correct flow" rule (or replace it with a one-line pointer to project-global-flow.md / in-repo-flow.md), since it restates the same numbered steps already given in the Rules.

Remove the duplicate "Success metrics" subsection — its three bullets are repeated verbatim within the Postconditions list directly above it.

Move the longer Common Situations code examples (memory API, disposables/addDisposable, extractText) into the existing reference files (e.g., extension-interface.md, event-types.md) and keep only one-line API signatures inline, shrinking the SKILL.md body toward a true overview.

Dimension	Reasoning	Score
Conciseness	The content is skill-specific rather than general-knowledge padding, but the Process Overview section repeats the Rules nearly verbatim, the Postconditions section duplicates its own three "Success metrics" lines ("Extension loads without errors", "appears in extensions list", "capabilities work as expected"), and several full code examples in Common Situations (memory API, disposables) could be tightened or moved out. This is more than the minor trimming of the 4 anchor.	3 / 5
Actionability	Guidance is fully executable: exact paths (`.aider-desk/extensions/`, `packages/extensions/extensions.json`), method names, the positional `createLlm` signature, copy-paste TypeScript snippets, and a concrete validation command (`node <skill-dir>/assets/scripts/validate-extension-ui.mjs <file-or-dir>` with exit-code criteria).	5 / 5
Workflow Clarity	Both installation flows are numbered step-by-step with explicit validation checkpoints — the JSX validator with a fix-all-issues feedback loop ("Run the validator script and fix all reported issues"), type checking for In-Repo, and a thorough postconditions checklist — matching the top anchor.	5 / 5
Progressive Disclosure	All 12 referenced files exist, are one level deep, and are clearly signaled ("for full details"), with assets organized under templates/ and scripts/. However, the ~530-line body inlines substantial API detail (memory, disposables, message-rendering examples) that belongs in the reference files, keeping it short of the ideal overview split.	4 / 5
	Total	17 / 20 Passed

Description

87%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 concrete capabilities and an explicit use-when clause with natural trigger terms, anchored to a specific product niche. Minor keyword synonyms (plugin, slash command) and unmentioned capability areas (UI/config components) keep specificity and trigger coverage just below maximum.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "setting up extension files, defining metadata, implementing Extension interface methods, and updating documentation" — but omits capabilities like UI components, config, and installation targets, so it falls short of the comprehensive 5 anchor.	4 / 5
Completeness	Explicitly answers both what ("Create AiderDesk extensions by setting up extension files, defining metadata, implementing Extension interface methods, and updating documentation") and when ("Use when building a new extension, creating extension commands, tools, or event handlers") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural phrases like "building a new extension" and "creating extension commands, tools, or event handlers" match what a user would say, though common synonyms (e.g., "plugin", "add a slash command") are missing.	4 / 5
Distinctiveness Conflict Risk	"AiderDesk extensions" is a clear, product-specific niche with distinct triggers; minimal overlap risk with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (533 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 8 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 1 missing, 9 deeper-than-1-level	Warning

	Total	13 / 16 Passed

Repository: hotovo/aider-desk
Path: resources/skills/extension-creator/SKILL.md
Revision: 980f390

Reviewed: 6 days ago

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.

extension-creator

Table of Contents

Is this your skill?