Name: lightweight-charts-plugin-authoring
Rating: 77.60000000000001 (1 reviews)
Author: tradingview

lightweight-charts-plugin-authoring

Use when creating, extending, debugging or publishing a Lightweight Charts™ plugin — a custom series, a series primitive or a pane primitive — or when turning a chart idea ("I want the chart to show/draw X") into a working plugin. Covers choosing the plugin type, scaffolding with create-lwc-plugin, building on @tradingview/lwc-toolkit instead of hand-rolled helpers, which of the ten official plugin packages to read as the reference implementation, where the docs are, and the autoscale, whitespace, visible-range, hit-test and conflation mistakes every plugin author makes once. Reach for it whenever the user mentions a custom series, primitive, renderer, drawing on the chart canvas, lwc-plugin, plugin-examples, the toolkit, or the plugin catalog — even if they never say the word "plugin".

Quality

96%

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

92%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 authoring skill: executable scaffolding/build commands, a sequenced working method with validation and checklists, and clean progressive disclosure into three real reference files. The only weakness is modest verbosity in a few narrative passages.

Suggestions

Tighten the 'Scaffold, don't start blank' wizard paragraph by replacing the narrative of prompt questions with a compact list, keeping only the actionable guidance about hint comments and the build scripts.

Compress connective sentences like 'The single most consequential decision, and the one to make first' into the table that already conveys the point, trimming prose around the decision tables.

Consider moving the per-plugin 'Read' table's longer rationale lines into references/official-plugins.md (already referenced) so the body holds only the mapping.

Dimension	Reasoning	Score
Conciseness	Dense and assumes Claude's competence — no basic-concept padding — but at ~340 lines some connective prose (the interactive-wizard narrative, 'The single most consequential decision, and the one to make first') could be trimmed without losing the actionable core.	4 / 5
Actionability	Copy-paste-ready executable commands ('npm create lwc-plugin@latest', 'pnpm typecheck', 'rg -n …', 'curl -fsSL …', 'node -p …') plus TypeScript import snippets and a problem→toolkit-module table cover the common cases concretely.	5 / 5
Workflow Clarity	A numbered 7-step 'Working method' where each step is 'the cheapest place to find the previous step's mistakes', a dedicated correctness checklist, typecheck/build validation, and 'name the test that would have caught the regression and write it' provide explicit checkpoints and feedback loops.	5 / 5
Progressive Disclosure	The body is an overview that clearly signals one-level-deep references (references/toolkit.md, references/official-plugins.md, references/package-contract.md — all present), with the bulk detail appropriately split out and easy to navigate.	5 / 5
	Total	19 / 20 Passed

Description

100%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.

An exceptionally strong description: it states concrete capabilities, surfaces both natural and technical trigger terms, and explicitly answers what and when, all in a distinctive niche. Voice is third-person/impersonal throughout, matching the score-5 reference examples.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'creating, extending, debugging or publishing', 'choosing the plugin type', 'scaffolding with create-lwc-plugin', 'building on @tradingview/lwc-toolkit', plus named autoscale/whitespace/visible-range/hit-test/conflation mistakes — giving comprehensive, non-generic coverage.	5 / 5
Completeness	Explicitly answers both what ('Covers choosing the plugin type, scaffolding… building on @tradingview/lwc-toolkit… where the docs are') and when ('Use when creating…' and 'Reach for it whenever the user mentions…') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural and technical terms — 'custom series, primitive, renderer, drawing on the chart canvas, lwc-plugin, plugin-examples, the toolkit, or the plugin catalog — even if they never say the word plugin' — covering synonyms and package names users would actually say.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (Lightweight Charts plugin authoring) with distinct triggers (lwc-plugin, plugin-examples, custom series, primitive) and minimal overlap risk; the body further scopes the boundary against the sibling lightweight-charts skill.	5 / 5
	Total	20 / 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: tradingview/lightweight-charts
Path: .github/skills/lightweight-charts-plugin-authoring/SKILL.md
Commit: 6777212

Reviewed: 1 day 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.