CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

magic-web-error-logging

Enforce Magic Web structured business error logging when adding, changing, migrating, or reviewing `logger.error` calls in `src`, `enterprise/src`, or `customer/src`, including catch blocks, callbacks, ErrorBoundaries, workers, WebSocket/storage flows, and logger adapters. Use to choose `eventKey/errorKind/error/message/context`, preserve historical diagnostics, prevent unsafe payloads, and verify the JS probe plus `/log-report` behavior.

77

Quality

97%

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

SKILL.md
Quality
Evals
Security

Quality

Content

93%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 dense, highly actionable rulebook: concrete code shape, exact commands, a sequenced workflow with verification checklist and done criteria, and clean one-level-deep references. Its only weakness is the absence of an explicit fix-and-re-validate loop when verification fails, which keeps workflow clarity just below the top anchor.

DimensionReasoningScore

Conciseness

The body is lean, imperative rules with zero explanation of concepts Claude already knows — no 'what an ErrorBoundary is', no library tutorials, no padding. Every bullet encodes a project-specific decision rule ('Never pass `namespace`, `eventId`, `release`, or `captureSource`; the Logger supplies them'), so every token earns its place per the 5 anchor. Not a 4: no instances of over-explanation were found to trim.

5 / 5

Actionability

Fully executable guidance: a copy-paste-ready structured `logger.error` call, the exact `errorKind` vocabulary, concrete source files to read, and exact verification commands (`rg -n "logger\.error"`, `corepack pnpm exec vitest run --config ./vitest.config.ts`, `git diff --check`). Common mapping cases are covered in the body plus the dedicated examples reference. Matches the 5 anchor; not a 3/4 because nothing is pseudocode or missing key details.

5 / 5

Workflow Clarity

The 6-step Required Workflow is clearly sequenced and closes with validation ('Run focused verification and review the diff specifically for diagnostic loss'), reinforced by a Verification section with commands, a manual checklist, and Done Criteria. However, the 5 anchor requires an explicit error-recovery feedback loop ('if checks fail: fix and re-validate'), and the body never states what to do when verification fails — completion is gated on passing but failure handling is only implicit. This is a minor validation gap, so 4 rather than 5; it is clearly above the 3 anchor, which would require missing or merely implicit checkpoints.

4 / 5

Progressive Disclosure

SKILL.md is a well-organized overview (workflow, required shape, field rules, review priorities, verification) with clearly signaled, purpose-conditioned one-level-deep references — 'Read [references/contract.md](references/contract.md) when deciding field behavior, Provider visibility, serialization, or sensitive-data boundaries' and 'Read [references/examples.md](references/examples.md) when migrating legacy calls...'. Both files exist, contain substantive content, and contain no further nested references. Matches the 5 anchor's clear-overview pattern; not a 4 because both pointers are explicit and no content that belongs in references is inlined.

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.

The description is exemplary: it names concrete actions, gives explicit and varied trigger conditions with natural codebase vocabulary, answers both what and when clearly, and is tightly scoped to a distinct niche. Third-person imperative voice is used correctly with no fluff or over-claims.

DimensionReasoningScore

Specificity

The description lists multiple specific concrete actions — 'Enforce Magic Web structured business error logging', 'choose `eventKey/errorKind/error/message/context`', 'preserve historical diagnostics, prevent unsafe payloads', 'verify the JS probe plus `/log-report` behavior' — with comprehensive coverage across adding, changing, migrating, and reviewing. It matches the 5 anchor ('lists multiple specific concrete actions; comprehensive coverage'); it is not a 4 because no action area is missing, and not below because nothing is generic or vague.

5 / 5

Completeness

Both 'what' and 'when' are explicit: what — enforce structured business error logging, choose fields, preserve diagnostics, prevent unsafe payloads, verify probe and `/log-report` behavior; when — 'when adding, changing, migrating, or reviewing `logger.error` calls in `src`, `enterprise/src`, or `customer/src`, including catch blocks, callbacks...'. Explicit 'Use to...' trigger guidance is present, so the completeness cap of 3 does not apply, and the 'when' is concrete rather than the weaker form that would merit a 4.

5 / 5

Trigger Term Quality

Natural trigger terms users of this codebase would actually say are comprehensively covered: '`logger.error` calls', 'catch blocks, callbacks, ErrorBoundaries, workers, WebSocket/storage flows', 'logger adapters', plus exact paths ('`src`, `enterprise/src`, or `customer/src`') and synonyms for the activity (adding, changing, migrating, reviewing). Matches the 5 anchor including file/path-level variations; a 4 would require missing natural terms, and none are evident.

5 / 5

Distinctiveness Conflict Risk

A clear niche with distinct triggers: Magic Web structured error logging tied to specific identifiers (`logger.error`, the structured field set, `/log-report`) and specific directories. It would not plausibly trigger for any other skill, matching the 5 anchor; it is not a 4 because there is no meaningful overlap with adjacent skills — the domain, fields, and paths are unique to this purpose.

5 / 5

Total

20

/

20

Passed

Validation

100%

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

dtyq/magic

Path

frontend/magic-web/.agents/skills/magic-web-error-logging/SKILL.md

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.