tldraw-offline

Drive and script tldraw offline canvases with an agent.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/creative/tldraw-offline/SKILL.md

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.

The body is a strong, executable skill: dense runnable curl and JS recipes, clearly sequenced workflows with explicit validation and feedback loops, and well-signaled references to real bundle scripts. Its only weakness is mild verbosity in one edge-case tangent and some inlineable reference material.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence (no padding about what tldraw/curl/JS is) and stays information-dense, with only minor over-explanation such as the multi-paragraph cua-driver foreground-delivery tangent that could be trimmed; not a 5 because that tangent and a few caveats run longer than strictly needed.	4 / 5
Actionability	Copy-paste-ready executable curl recipes (token/port read, /api/search, /exec, /script-workspace, /script-status) and complete JS document-script examples cover the common cases, matching the fully-executable anchor; not below 5 because the examples are concrete and runnable rather than pseudocode.	5 / 5
Workflow Clarity	A numbered Procedure section plus two clearly distinguished workflows (A /exec for one-off edits, B script/main.js for durable behavior) and a Verification section with explicit validation checkpoints and feedback loops (pending→retry→report, error→read errorLogPath) match the anchor for clear sequencing with explicit validation and error recovery.	5 / 5
Progressive Disclosure	References to scripts/main.js, scripts/counter.js, and scripts/validate_shapes.mjs are one level deep, clearly signaled, and all point to real bundle files, giving good structure and easy navigation; not a 5 because the SKILL.md body still inlines sizable material (the shape-props table and the full interactive-UI pattern code) that could live in separate reference files.	4 / 5
	Total	18 / 20 Passed

Description

53%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.

The description is specific and distinctive, naming a clear product niche with two concrete actions, but it omits any explicit "Use when..." trigger guidance and lacks synonym coverage, leaving it mid-pack on completeness and trigger terms.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user has tldraw offline open and wants to build or modify a canvas, add interactive/document scripts, or automate a whiteboard."

Broaden trigger terms with natural synonyms users say: whiteboard, diagram, drawing, wireframe, and the .tldraw file extension.

Expand the action list beyond "drive" and "script" to concrete capabilities (read canvas, edit shapes, write durable document scripts, verify changes).

Dimension	Reasoning	Score
Specificity	Quotes "Drive and script tldraw offline canvases with an agent" name the domain plus two concrete actions ("Drive", "script"), matching the anchor for 1-2 concrete actions that are not comprehensive; not a 4 because it lists only two actions rather than several.	3 / 5
Completeness	The description gives a clear "what" (drive and script canvases) but no "when" / "Use when..." clause, and the guideline caps completeness at 3 when explicit trigger guidance is missing; not a 4 because the when is entirely absent rather than weakly implied.	3 / 5
Trigger Term Quality	The phrase "tldraw offline canvases" supplies the product name and "canvas" but omits natural synonyms a user might say (whiteboard, diagram, drawing, .tldraw), matching the anchor with relevant keywords but missing common variations; not a 4 because synonym coverage is thin.	3 / 5
Distinctiveness Conflict Risk	Naming the specific product "tldraw offline" carves a clear niche with minimal conflict risk, sitting mostly-distinct with only minor overlap against generic canvas skills; not a 5 because the terse single sentence lacks the concrete trigger phrases of the anchor-5 example.	4 / 5
	Total	13 / 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
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: NousResearch/hermes-agent
Path: optional-skills/creative/tldraw-offline/SKILL.md
Commit: 6680afb

Reviewed: about 4 hours 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.