Name: custom-metrics
Rating: 60.8 (1 reviews)
Author: launchdarkly

custom-metrics

Create, track, retrieve, update, and delete custom business metrics for configs. Covers full lifecycle: define metric kinds via API, emit events via SDK, and query results.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/agentcontrol/custom-metrics/SKILL.md

Quality

Content

71%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 highly actionable with executable code and a clear lifecycle sequence, but it is over-long for a single file and carries illustrative extras that could be trimmed or split into reference files.

Suggestions

Move the "Common Tracking Patterns" and "Session Metrics Tracker" sections into a separate reference file (e.g. TRACKING_PATTERNS.md) and link to them from the body.

Trim or collapse the four near-identical tracking-pattern functions into one parameterized example to reduce token cost.

Add an explicit validation checkpoint before destructive operations (e.g. confirm the metric exists via get_metric before delete/update) to strengthen workflow clarity.

Dimension	Reasoning	Score
Conciseness	The core CRUD + API-key detection is efficient and executable, but the four redundant "Common Tracking Patterns" functions and the full SessionMetricsTracker class are illustrative padding beyond what the skill needs.	3 / 5
Actionability	Every operation ships as complete, copy-paste-ready Python with real endpoints, payloads, and status-code handling, and the complete workflow example ties the common cases together.	5 / 5
Workflow Clarity	The lifecycle table plus numbered sections 1–5 give a clear sequence, and per-call status-code checks (201/409/404/204) provide error-recovery feedback, but there is no explicit validate-then-proceed checkpoint for destructive delete/update operations.	4 / 5
Progressive Disclosure	Section headers and an external References list provide structure, but ~500 lines of inline code (tracking patterns, session tracker, API reference) that belongs in separate reference files are all monolithically inlined in SKILL.md with no bundle files present.	3 / 5
	Total	15 / 20 Passed

Description

71%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 action-rich, covering the full metric CRUD lifecycle, but omits an explicit 'when to use' trigger clause. Adding a 'Use when...' sentence would lift completeness and distinctiveness.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user wants to define, track, or manage custom business metrics for configs."

Add natural synonyms or concrete triggers (e.g. "KPIs", "custom events", "agent metrics") so users phrasing the request differently still match.

Reinforce the LaunchDarkly-specific scope to further reduce overlap with generic metrics or analytics skills.

Dimension	Reasoning	Score
Specificity	Five concrete verbs ("Create, track, retrieve, update, and delete") plus three sub-actions ("define metric kinds via API, emit events via SDK, and query results") give comprehensive coverage of the metric lifecycle.	5 / 5
Completeness	The description clearly states what the skill does but lacks any "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Natural terms like "custom business metrics" and "configs" are present, but synonyms (e.g. KPIs, measurements) and concrete file/extension triggers are missing, so it falls short of comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	"custom business metrics for configs" carves a distinct niche tied to the LaunchDarkly context, with only minor overlap risk against a related built-in-metrics skill.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (504 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: launchdarkly/ai-tooling
Path: skills/agentcontrol/custom-metrics/SKILL.md
Commit: add614f

Reviewed: 9 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.