devtools-source-maps

Guidelines for utilizing source maps and structured stack traces in DevTools. Covers DebuggerWorkspaceBinding, StackTrace, SymbolizedError, and related UI widgets.

Quality

68%

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 ./.agents/skills/devtools-source-maps/SKILL.md

Quality

Content

82%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 tight, actionable reference with executable TypeScript examples, clear primary rules, and a verification checklist, demonstrating strong actionability and good conciseness. Its main gap is the absence of an explicit validation feedback loop tying the checklist into the workflow, and inlined API reference that could be separated for cleaner progressive disclosure.

Suggestions

Promote the Verification Checklist into an explicit ordered workflow with a validate->fix->retry loop (e.g., after rendering, run the checklist, fix any failing item, re-render) to raise workflow clarity.

Consider extracting the detailed Core APIs and UI Widget Reference into a separate reference file referenced one level deep, keeping SKILL.md as a concise overview.

Trim the restating intro paragraph (lines 8-10) since the title and Primary Rules already convey the purpose.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence, jumping straight into rules and executable TS snippets without explaining what source maps are; a slightly restating intro paragraph keeps it just short of the lean 'every token earns its place' anchor.	4 / 5
Actionability	Provides multiple fully executable, copy-paste-ready TypeScript snippets with real imports and API calls (rawLocationToUILocation, createStackTraceFromProtocolRuntime, StackTracePreviewContent, SymbolizedErrorWidget) covering the common cases, matching the 'fully executable; copy-paste ready' anchor.	5 / 5
Workflow Clarity	Primary Rules are numbered and the Verification Checklist supplies checkpoints (dispose calls, ignoreListManager, WASM/inline mapping), giving a clear sequence with most checkpoints present; it falls short of 5 because there is no explicit validate->fix->retry feedback loop tying the checklist to the build/render steps.	4 / 5
Progressive Disclosure	A single self-contained, well-organized file with clear numbered sections and no bundle files, appropriate for a skill that needs no external references; not a 5 because a notable amount of API/widget reference detail is inlined that could otherwise be split out.	4 / 5
	Total	17 / 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 names a clear, distinctive niche and concrete component names but lacks explicit 'Use when...' trigger guidance, which caps completeness, and its verbs ("utilizing", "Covers") are minimal rather than enumerating concrete actions. Adding concrete action verbs and a trigger clause would raise specificity and completeness.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should invoke this skill (e.g., 'Use when rendering or parsing stack traces, symbolized errors, or source-mapped locations in DevTools').

Replace the generic verb 'utilizing' with concrete actions (e.g., 'Map runtime coordinates to original source locations, render structured stack traces, and display symbolized errors').

Include common synonyms or file/extension triggers (e.g., 'source maps, .map files, stack traces, symbolized errors') to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete components ("DebuggerWorkspaceBinding, StackTrace, SymbolizedError, and related UI widgets") but the verbs are minimal ("utilizing", "Covers") rather than enumerating concrete actions, matching the anchor that names domain plus 1-2 concrete actions but is not comprehensive.	3 / 5
Completeness	Provides a clear 'what' (guidelines for utilizing source maps and structured stack traces) but has no 'Use when...' or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3 even though the 'what' is clear.	3 / 5
Trigger Term Quality	Includes relevant natural terms ("source maps", "structured stack traces", "DevTools") but misses common synonyms or variations and file extensions, fitting the 'some relevant keywords but missing common variations' anchor rather than the 4 (a few natural terms missing) or 2 (one generic keyword) anchors.	3 / 5
Distinctiveness Conflict Risk	Targets a specific niche (DevTools source maps and structured stack traces) with named internal abstractions, giving it mostly distinct triggers with only minor overlap risk against adjacent DevTools skills; not a 5 because the 'Guidelines for utilizing' framing is still somewhat broad.	4 / 5
	Total	13 / 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: ChromeDevTools/devtools-frontend
Path: .agents/skills/devtools-source-maps/SKILL.md
Commit: 31f2967

Reviewed: ~14 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.