CtrlK
BlogDocsLog inGet started
Tessl Logo

built-in-metrics

Instrument an existing codebase with LaunchDarkly config tracking. Walks the four-tier ladder (managed runner → provider package → custom extractor + trackMetricsOf → raw manual) and picks the lowest-ceremony option that still captures duration, tokens, and success/error.

53

Quality

59%

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/agentcontrol/built-in-metrics/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

60%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 well-structured: a clear four-step workflow with a verification checklist, a tier-decision matrix that deep-links into a one-level reference bundle, and a method reference table. It loses points for some over-explanation and for keeping all executable code in the references rather than showing a minimal inline example.

Suggestions

Trim explanatory prose that restates what the SDK does or why runId/observability matters; trust Claude's competence here.

Add one short inline copy-paste example (e.g., a Tier-2 trackMetricsOf snippet) so the body is executable without opening a reference.

Resolve the Vercel row's unlinked 'use the Vercel provider docs' into a concrete reference path or note its absence.

DimensionReasoningScore

Conciseness

The body is mostly efficient but includes explanatory padding Claude largely already knows (e.g., why runId matters, the meaning of 'drift', elaborated method-table prose) that could be tightened.

3 / 5

Actionability

It gives concrete method signatures and a tier matrix, but the body itself contains no executable code blocks — actual copy-paste code lives only in the references, so guidance is concrete but not directly executable from SKILL.md.

3 / 5

Workflow Clarity

The Explore → Look up tier → Implement → Verify sequence is clearly numbered with an explicit validation/verify checklist and error-recovery guidance, leaving only minor checkpoint gaps.

4 / 5

Progressive Disclosure

SKILL.md acts as an overview with a real references/ bundle (8 files), every matrix row links to the matching reference file, and references are one level deep; minor gaps like an unlinked 'use the Vercel provider docs' keep it just below 5.

4 / 5

Total

14

/

20

Passed

Description

58%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 and distinct, naming concrete actions and the LaunchDarkly niche, but it omits any explicit 'Use when...' trigger guidance and relies on product jargon over natural user phrasing. Completeness is capped at 3 by the missing trigger clause.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers (e.g., 'Use when adding agent metrics to an LLM call, wiring LaunchDarkly observability, or preparing an AI config for the Monitoring tab').

Broaden trigger keywords with user-natural synonyms and file/package hints beyond the LaunchDarkly product name.

Rephrase into consistent third-person capability statements to tighten specificity toward a 5.

DimensionReasoningScore

Specificity

It lists several concrete actions — 'Instrument an existing codebase with LaunchDarkly config tracking', walking the 'four-tier ladder', and picking the option that 'captures duration, tokens, and success/error' — with only minor coverage gaps relative to the score-5 anchor.

4 / 5

Completeness

The 'what' is clear, but there is no explicit 'Use when...' clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Keywords are present (LaunchDarkly, config tracking, metrics) but the natural phrases a user would say are thin; it leans on product/jargon terms rather than synonyms like 'agent observability' or 'instrument LLM calls'.

3 / 5

Distinctiveness Conflict Risk

The LaunchDarkly-specific framing and the four-tier ladder carve out a clear niche with only minor overlap against a sibling like configs-create or custom-metrics.

4 / 5

Total

14

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
launchdarkly/ai-tooling
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.