CtrlK
BlogDocsLog inGet started
Tessl Logo

source-maps

Use when auditing slow page loads, heavy assets, or rendering delays related to Provide source maps for production debugging. Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes.

47

Quality

50%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/source-maps/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

53%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 lean, well-sectioned overview with a properly signaled one-level reference that delivers the code examples it promises, so token efficiency and progressive disclosure are solid. The main weakness is actionability — the body itself contains no executable config, command, or code, deferring everything concrete to the reference file — and the workflow lacks an explicit post-fix verification step even though the reference file contains one.

Suggestions

Add one minimal executable anchor to the Fix section (e.g., the Webpack `devtool: 'source-map'` option or `sourcemap: 'hidden'` for Vite) so the skill is actionable without opening the reference, keeping the rest of the detail in references/rule.md.

Append an explicit verification step after Fix (e.g., "Verify the error tracker de-minifies a real stack trace", mirroring the reference's Verification section) so the Check → Fix workflow has a closing checkpoint.

Trim the intro sentence explaining what source maps are for and remove the trailing duplicate rule-page URL, both of which add tokens without new information.

DimensionReasoningScore

Conciseness

The ~30-line body is tight and sectioned (Quick Reference, Check, Fix, Explain, Code Review) with no padding, though the opening line "Source maps are essential for debugging production issues effectively without compromising the performance benefits of minification" explains a concept Claude already knows, and the trailing "Rule page" URL duplicates metadata already in the frontmatter. Not level 5 because of those two trimmable items; not level 3 because the waste is minor rather than a pattern of unnecessary explanation.

4 / 5

Actionability

The body offers only high-level direction — "Update the build configuration to generate source maps and integrate with an error tracking service" and "Upload source maps to error tracking services (e.g., Sentry)" — with no concrete config keys, commands, or code samples anywhere in the body; the promised executable detail lives entirely in references/rule.md. Not level 1 because the Quick Reference bullets do name specific actions and a concrete tool (Sentry); not level 3 because there is no partially executable guidance — nothing in the body can be acted on without opening the reference.

2 / 5

Workflow Clarity

The Check → Fix → Explain → Code Review sections form a recognizable sequence, and "Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes" acts as an implicit pre-change checkpoint. However, there is no post-fix verification step in the body (the reference file's Verification section is never surfaced as a workflow step), so checkpoints remain implicit. Not level 4 because validation is implied rather than explicit; not level 2 because the sequence is defined and each step has a stated intent.

3 / 5

Progressive Disclosure

The body is a compact overview that defers detail via a clearly signaled, one-level-deep pointer — "For full implementation details, code examples, and framework-specific guidance, see references/rule.md" — and that file exists and actually contains the promised Webpack/Vite code examples, matching the bundle structure. Not level 5 because the trailing duplicated rule URL is dead weight and the Quick Reference bullets partially duplicate content in the reference file rather than being organized as per-topic navigation into it; not level 3 because the split between overview and detail is appropriate and the reference is prominently signaled.

4 / 5

Total

13

/

20

Passed

Description

46%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 has an explicit 'Use when' trigger and names its domain, but the sentence construction is broken — the rule title is spliced into the middle of the trigger clause — and the chosen trigger terms describe general performance auditing rather than source-map debugging, hurting both completeness and distinctiveness. Key natural terms for the actual topic (stack traces, minified code, error tracking, Sentry) are absent.

Suggestions

Rewrite the description as a clean sentence pair: state the what first (e.g., "Configure source maps for production debugging and upload them to error tracking services instead of serving them publicly"), then a separate explicit "Use when..." clause.

Replace the generic performance-audit triggers ("slow page loads, heavy assets, rendering delays") with topic-specific natural phrases users would actually say, such as "stack traces point to minified code", "debugging production errors", "source maps", or "Sentry shows unreadable errors".

Add distinguishing terms (minified code, error tracking service, hidden source maps) so this skill does not collide with sibling performance-audit skills that share the page-load/asset/rendering trigger phrasing.

DimensionReasoningScore

Specificity

The description names the domain and a couple of concrete actions — "Provide source maps for production debugging" and "Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes" — but the actions are few and the key phrase is awkwardly embedded mid-sentence rather than listed. It is above level 2 (domain plus real actions, not just generic processing) but below level 4, which expects several specific actions with only minor coverage gaps.

3 / 5

Completeness

Both a 'what' ("Provide source maps for production debugging") and an explicit 'when' ("Use when auditing slow page loads, heavy assets, or rendering delays related to...") are present, so it clears the level-2/3 floor for missing triggers. However, the sentence is grammatically broken ("related to Provide source maps...") and the when-clause's triggers (page loads, assets, rendering delays) are misaligned with the debugging purpose, so it does not reach level 4's 'both present and clearly tied' standard.

3 / 5

Trigger Term Quality

It contains relevant keywords ("slow page loads", "heavy assets", "rendering delays", "DevTools", "Lighthouse", "source maps", "production debugging"), but the natural phrases a user would say for this actual topic — "stack traces", "minified code", "error tracking", "Sentry" — are missing, and the performance-audit phrasing is not how a user would ask about source maps. Not level 4 because common variations and synonyms for the core topic are absent; not level 2 because several genuinely relevant keywords are present.

3 / 5

Distinctiveness Conflict Risk

"slow page loads, heavy assets, or rendering delays" are generic performance-audit triggers shared by virtually every sibling performance-checklist skill, creating high overlap risk; the only distinctive terms ("source maps", "production debugging") are buried in the garbled embedded title. Not level 1 because source maps plus production debugging do carve out a recognizable niche; not level 3 because the leading triggers would fire for the wrong performance skills far more often than for this one.

2 / 5

Total

11

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
thedaviddias/Front-End-Checklist
Reviewed

Table of Contents

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.