CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

custom-metrics

Create, track, retrieve, update, and delete custom business metrics for configs. Covers full lifecycle: define metrics with the LaunchDarkly MCP server, emit events via SDK, and query results.

Quality

73%

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/custom-metrics/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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 complete, executable code for every lifecycle step and clear step sequencing anchored by an overview table. Its weaknesses are verbosity from repetitive tracking-pattern examples and an inlined session-tracker class, a missing validation checkpoint before the destructive delete operation, and no progressive disclosure — everything lives in one long file with no reference bundle to split it. Tightening the padding, adding a pre-delete verification step, and moving bulk API reference material to a separate file would lift all three weak dimensions.

Suggestions

Add an explicit validation checkpoint before deletion, e.g., fetch the metric with get-metrics (or get_metric()) and confirm with the user that the key is correct before calling delete-metric or delete_metric().

Trim redundancy by collapsing the four near-identical Common Tracking Patterns into one parameterized example and cutting or compressing the SessionMetricsTracker class and the bare Naming Conventions string list.

Move the bulk REST API reference (create/get/list/update/delete function bodies) into a references/ file (e.g., references/api-examples.md) and keep SKILL.md as a concise overview with clearly signaled one-level-deep links.

DimensionReasoningScore

Conciseness

The body is dominated by executable code and API specifics Claude would not know (correct approach), but it carries noticeable padding: four near-identical "Common Tracking Patterns" functions, a 60-line SessionMetricsTracker class, a list of bare metric-key strings under Naming Conventions, and glosses like "milliseconds - Time duration". Mostly efficient with content that could be tightened matches the 3 anchor; it is not 4 because the redundant pattern examples and tracker class go beyond minor over-explanation.

3 / 5

Actionability

Fully executable, copy-paste-ready code throughout: complete Python functions with status-code error handling (201/409/404 branches), a full JSON payload for the MCP create-metric call, TypeScript parity examples, and an end-to-end workflow covering the common cases. This matches the 5 anchor; nothing is pseudocode or left abstract.

5 / 5

Workflow Clarity

Sequencing is strong (a 5-step lifecycle table mirrored by numbered sections) with some verification steps ("Then confirm with get-metrics", using get-metric-events to catch eventKey mismatches). However, delete is a destructive operation with no pre-delete verification or confirmation step, and the rubric explicitly caps workflow clarity at 3 when destructive operations lack validation, taking precedence over the strength of the sequencing.

3 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/ directories), so all ~300 lines of REST API code, tracking patterns, and the session tracker class are inlined in a single SKILL.md. Section headers keep it above the 2 anchor (which features no structure), but substantial content that clearly belongs in separate reference files is inline, matching the 3 anchor.

3 / 5

Total

14

/

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 highly specific and comprehensive about what the skill does, covering the full create/track/retrieve/update/delete lifecycle with concrete mechanisms. Its main weakness is the complete absence of any "Use when..." trigger guidance, which both caps completeness and leaves natural trigger-phrase coverage thinner than it could be. It is clearly distinguishable from neighboring skills except for mild overlap on the generic term "metrics".

Suggestions

Add an explicit trigger clause, e.g., "Use when the user wants to define, track, or manage custom business metrics (KPIs) for LaunchDarkly AI configs."

Include natural synonyms and variations users might say, such as "KPI", "measure", "monitor", or "business metric", to broaden trigger-term coverage.

Sharpen distinctiveness from related skills by signaling scope boundaries, e.g., noting that built-in agent metrics (tokens, cost, duration) are handled by a different skill.

DimensionReasoningScore

Specificity

Lists five concrete CRUD actions ("Create, track, retrieve, update, and delete custom business metrics") plus concrete mechanisms ("define metrics with the LaunchDarkly MCP server, emit events via SDK, and query results"), giving comprehensive lifecycle coverage. It exceeds the 4 anchor because coverage of actions is comprehensive rather than having minor gaps.

5 / 5

Completeness

The "what" is clearly and concretely answered (full metric lifecycle via MCP server and SDK), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not 4 because the "when" is entirely absent rather than present but imprecise.

3 / 5

Trigger Term Quality

Natural domain terms are present ("custom business metrics", "metrics", "track", "events", "query") that users would plausibly say, but common variations like "KPI", "measure", "monitor", or "instrument" are missing. Good coverage with a few natural terms missing matches the 4 anchor; not 5 because no synonyms or extensions are included.

4 / 5

Distinctiveness Conflict Risk

"Custom business metrics for configs" scoped to the LaunchDarkly MCP server and SDK is a clear niche with distinct triggers, but the broad term "metrics" creates minor overlap risk with closely related skills (e.g., built-in agent metrics, online evals). Mostly distinct with minor overlap matches the 4 anchor; not 5 because of that adjacent-skill overlap.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (530 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

launchdarkly/ai-tooling

Path

skills/agentcontrol/custom-metrics/SKILL.md

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.