instrument-feature-analytics

Plan analytics instrumentation for a feature. Use when implementing any feature — every feature must ship with telemetry. Decides which events and properties the metrics need (funnels, adoption, status flows), checks compatibility with the existing datalake and event registry, and walks through local, staging, and production verification.

Quality

81%

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 highly actionable with executable verification queries and a clearly sequenced, checkpoint-driven workflow; structure is solid though it lives in a single somewhat long file rather than splitting detail into references.

Suggestions

Tighten the opening framing (e.g. "The hard part... is deciding which events and properties matter") to remove conversational padding and reach the lean score-5 conciseness anchor.

Consider moving the three verification SQL blocks into a short references file (e.g. references/verification_queries.md) and summarizing inline, to improve progressive disclosure and keep SKILL.md as an overview.

Add a brief inline note on how to handle a failed verification (expected count mismatch or unexpected NULL values) as an explicit recovery step.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence with concrete SQL and commands, but includes light framing prose ("The hard part — and the reason they'd normally ask a data person...") that could be trimmed, placing it just below the lean score-5 anchor.	4 / 5
Actionability	Provides fully executable, copy-paste-ready SQL verification queries plus a specific run command ("DEBUG_LEVEL=1 uv run vibe") and concrete registry paths, covering the common cases, matching the score-5 anchor.	5 / 5
Workflow Clarity	A clear 9-step sequence with explicit validation checkpoints across local, staging, and production, plus interpretation guidance for query results (e.g. completeness 1.0 = present on every event), matching the score-5 anchor with feedback loops.	5 / 5
Progressive Disclosure	Well-organized into clearly signaled sections (Process, Naming, Verification queries) in a single self-contained file with no nested references; slightly long for one file but appropriately structured, sitting between the good-structure score-4 and the one-level-deep-reference score-5 anchors.	4 / 5
	Total	18 / 20 Passed

Description

73%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 specific about capabilities and complete in stating both what and when, but its single trigger phrase is generic and the "any feature" framing makes it conflict with a wide range of skills.

Suggestions

Add concrete trigger terms users would actually say — e.g. "Use when implementing a feature that needs telemetry, tracking, events, or analytics instrumentation" — to improve trigger-term coverage.

Narrow the trigger scope so it does not fire on every feature build; reserve it for cases where analytics/telemetry instrumentation is genuinely in scope.

Include relevant file-type or domain cues (e.g. event registry, datalake, Metabase/BigQuery) so it is distinguishable from generic implementation skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Decides which events and properties the metrics need (funnels, adoption, status flows)", "checks compatibility with the existing datalake and event registry", "walks through local, staging, and production verification" — giving comprehensive coverage, matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers both what ("Plan analytics instrumentation... Decides which events and properties...") and when ("Use when implementing any feature") with a concrete trigger phrase, matching the score-5 anchor.	5 / 5
Trigger Term Quality	The only trigger phrase is "Use when implementing any feature"; it lacks common natural terms users would say (telemetry, tracking, events, analytics, metrics) and their synonyms, so it sits at the some-relevant-keywords-but-missing-variations anchor rather than 4.	3 / 5
Distinctiveness Conflict Risk	"every feature must ship with telemetry" / "Use when implementing any feature" is extremely broad and would trigger on virtually any feature-build request, creating high overlap risk with many other skills, fitting the score-2 anchor.	2 / 5
	Total	15 / 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: mistralai/mistral-vibe
Path: .vibe/skills/instrument-feature-analytics/SKILL.md
Commit: a84be03

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.