claude-code-telemetry-enable

Enable and configure Claude Code OTEL telemetry for local or Railway observability stacks. Use when setting up Claude Code to send metrics, logs, and traces to observability backends.

Quality

69%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/claude-code-telemetry-enable/SKILL.md

Quality

Content

63%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 and largely actionable with real scripts and concrete config, but it carries some padding and references bundle files that are not present. Tightening verbose sections and aligning the references list with the actual bundle would lift it.

Suggestions

Remove the imagined 'verify'/'status' dashboard output blocks and the redundant 'Next Steps' section to tighten conciseness.

Reconcile the References and Scripts lists with the actual bundle: either add the missing files (env-telemetry-custom.txt, telemetry-variables.md, privacy-settings.md, enable-railway.sh, disable-telemetry.sh) or drop the dangling references.

Add an explicit validation step to the enable/disable operations (e.g., confirm the config file parses and CLAUDE_CODE_ENABLE_TELEMETRY is set before declaring success) to reach the top workflow_clarity anchor.

Dimension	Reasoning	Score
Conciseness	Mostly efficient (concrete env vars, troubleshooting) but padded in places: the imagined 'verify'/'status' dashboard outputs and a 'Next Steps' section that restates earlier content are unnecessary.	3 / 5
Actionability	Provides concrete env-var configs and references real scripts (enable-local.sh, verify-telemetry.sh exist); the 'enable-local'/'enable-railway' invocation strings read as pseudo-commands rather than a real CLI, a minor gap.	4 / 5
Workflow Clarity	The 'verify' operation has a clear 5-step checklist with connectivity feedback; config-write and 'disable' operations touch user config but lack explicit validation checkpoints, leaving a minor gap below anchor 5.	4 / 5
Progressive Disclosure	Structure is good and references are clearly signaled one level deep, but several referenced files do not exist in the bundle (env-telemetry-custom.txt, telemetry-variables.md, privacy-settings.md, enable-railway.sh, disable-telemetry.sh), so navigation breaks.	3 / 5
	Total	14 / 20 Passed

Description

75%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.

A clear, well-formed description that states concrete capabilities and an explicit 'Use when' trigger, sitting just below the top anchor on specificity and trigger breadth. It is distinct and unlikely to misfire, though its trigger phrase list could be richer.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('Enable and configure Claude Code OTEL telemetry', 'send metrics, logs, and traces'), with minor gaps in coverage; not the comprehensive list of anchor 5.	4 / 5
Completeness	Explicitly answers both 'what' (enable/configure telemetry, send metrics/logs/traces) and 'when' ('Use when setting up Claude Code to send...'), with the 'when' concrete but less rich than anchor 5's multi-trigger phrase list.	4 / 5
Trigger Term Quality	Includes natural terms ('telemetry', 'observability', 'metrics, logs, and traces', 'local or Railway') a user might say, though common synonyms like 'monitoring' or full 'OpenTelemetry' are sparse.	4 / 5
Distinctiveness Conflict Risk	Targets a fairly distinct niche (Claude Code OTEL telemetry, local or Railway stacks) with specific triggers; only minor overlap risk with a general observability-stack-setup 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
referenced_paths_exist	Referenced path issues: 5 missing	Warning

	Total	15 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/claude-code-telemetry-enable/SKILL.md
Commit: 93ed392

Reviewed: 1 day 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.