measure-before-you-fix

Before fixing a slow/stale/timeout alert, measure the step yourself. Kill the theory with a stopwatch, not a code change. Measure-first ops triage for temporal alerts (stale, timeout, freshness, wedged, N hours behind) from gbrain doctor, autopilot, sync, and cron monitors — runs BEFORE any timeout raise, threshold change, or pipeline rewrite.

Quality

91%

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

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 content is a tight, actionable measure-first playbook with executable commands, a validated procedure, and concrete failure-mode case studies, all well-sectioned for navigation. It is only slightly short of perfect on conciseness (minor rhetorical padding) and progressive disclosure (one un-verifiable external reference).

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence (no explanations of what a timeout or cron is), with every section earning its place, though a few rhetorical flourishes ("a guess wearing a diff", "Kill the theory with a stopwatch") and the duplicated threshold-mismatch narrative could be trimmed slightly below the lean 5 anchor.	4 / 5
Actionability	Fully executable, copy-paste-ready commands ("time gbrain sync --source source-a --no-embed", "grep -n 'timeoutMs\\|timeout:'", "gbrain sources status", "gbrain jobs list") plus concrete env-var constants and a complete fix code block cover the common cases per the 5 anchor.	5 / 5
Workflow Clarity	A clearly sequenced numbered procedure (1-5) with validation woven into the compare-against-budget and threshold-check steps, explicit feedback loops (red flags, "revise the theory twice without taking a new measurement"), and a verdict template; the skill is explicitly read-only (mutating: false) so the destructive/batch cap does not apply.	5 / 5
Progressive Disclosure	Well-organized with clearly signaled sections (rule, contract, procedure, failure modes, output format, dedup) and a one-level convention pointer; no bundle files exist so it is appropriately self-contained, but the single external link to ../conventions/brain-first.md is outside the verifiable bundle, leaving it just shy of the ideal 5.	4 / 5
	Total	18 / 20 Passed

Description

95%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 tight, third-person, and sharply scoped to a measure-first gate for temporal ops alerts, explicitly answering both what it does and when to route here. It is exemplary except that the capability list is more methodological than enumerative.

Dimension	Reasoning	Score
Specificity	Names the domain (temporal ops alerts) and concrete actions ("measure the step yourself", "measure-first ops triage") plus specific monitor sources (gbrain doctor, autopilot, sync, cron), but the capability verbs lean methodological rather than enumerating multiple discrete operations, leaving minor coverage gaps below the comprehensive 5 anchor.	4 / 5
Completeness	Explicitly answers both what ("measure-first ops triage for temporal alerts") and when ("Before fixing a slow/stale/timeout alert", "runs BEFORE any timeout raise, threshold change, or pipeline rewrite") with concrete trigger phrases, matching the 5 anchor exactly.	5 / 5
Trigger Term Quality	Comprehensive natural terms users would actually say — "stale", "timeout", "freshness alert", "wedged", "N hours behind", "raise the timeout" — covering synonyms and the colloquial phrasings that match the good_overall_examples standard.	5 / 5
Distinctiveness Conflict Risk	A clear niche (temporal ops alerts from named gbrain/autopilot/sync/cron monitors) with distinct triggers and an explicit runs-BEFORE-structural-fix contract, giving minimal conflict risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: garrytan/gbrain
Path: plugin-variants/gbrain-coding/skills/measure-before-you-fix/SKILL.md
Commit: e78f1c3

Reviewed: 5 days 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.