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

66%

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

65%

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 complete executable code and a clear lifecycle sequence, but it is over-long for a single file, lacks validation checkpoints for destructive operations, and uses no progressive disclosure.

Suggestions

Move the full API reference, SessionMetricsTracker class, and naming-convention list into separate reference files (e.g., REFERENCE.md, EXAMPLES.md) and link to them from a concise overview.

Add an explicit validation/confirmation checkpoint before destructive operations (e.g., confirm metric exists via get_metric before delete, and require user confirmation).

Trim redundant tracking-pattern examples and verbose print-based logging to reduce token overhead while preserving the executable examples.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable code, but the ~500-line body carries redundancy (four near-identical tracking patterns, a SessionMetricsTracker class that re-teaches patterns, and verbose print logging in every function) that could be tightened.	2 / 3
Actionability	Provides fully executable, copy-paste-ready Python for create/get/list/update/delete and SDK tracking with real imports, endpoints, and a complete end-to-end workflow example.	3 / 3
Workflow Clarity	The lifecycle is clearly sequenced with a table and complete example, but destructive operations (delete) and API calls lack explicit validate/confirm checkpoints and there is no validate→fix→retry feedback loop.	2 / 3
Progressive Disclosure	Sections are well-organized, but the content is monolithic in SKILL.md with no bundle files; API reference, session tracker, and naming list that could be split out are inline rather than one-level-deep referenced.	2 / 3
	Total	9 / 12 Passed

Description

67%

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 distinctive about the metrics lifecycle, but it omits explicit "Use when..." trigger guidance, which caps completeness and weakens trigger-term quality.

Suggestions

Add a 'Use when...' clause naming natural user triggers, e.g., 'Use when creating or tracking custom business metrics, emitting metric events, or querying metric results for configs.'

Include common natural keyword variations users would say (e.g., 'custom metrics', 'business metrics', 'metric events', 'track events') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Create, track, retrieve, update, and delete" plus "define metric kinds via API, emit events via SDK, and query results" — matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	Clearly states what the skill does (full lifecycle of metrics) but lacks an explicit "Use when..." trigger clause, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Contains relevant domain terms ("custom business metrics", "configs", "API", "SDK", "events") but misses common natural variations users would say and has no "Use when..." trigger phrasing.	2 / 3
Distinctiveness Conflict Risk	Has a clear niche (custom business metrics for configs via LaunchDarkly) with distinct triggers unlikely to overlap with the referenced built-in-metrics skill.	3 / 3
	Total	10 / 12 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: 3 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.