CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

76%

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 ./.claude/skills/claude-code-telemetry-enable/SKILL.md

The canonical home for this skill is claude-code-telemetry-enable in fernandezbaptiste/Skrillz

SKILL.md
Quality
Evals
Security

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 highly actionable with concrete configuration blocks, verification steps, and executable troubleshooting, and it avoids concept-explaining padding. Its weaknesses are duplication and broken bundle wiring: env vars are stated twice, the telemetry catalog is inlined, and over half of the referenced bundle files are missing.

Suggestions

Fix the bundle wiring: either add the five missing referenced files (references/env-telemetry-custom.txt, references/telemetry-variables.md, references/privacy-settings.md, scripts/enable-railway.sh, scripts/disable-telemetry.sh) or remove their References/Scripts entries, and reference the existing but unlisted scripts/activate-telemetry.sh if it is part of the flow.

De-duplicate the environment variables: keep them once in the reference templates and link to them, rather than repeating the full set inline in both `enable-local` and Configuration Details.

Move the "What Gets Captured" metric/log-event/trace catalog into references/telemetry-variables.md so the main file stays an overview.

DimensionReasoningScore

Conciseness

The body avoids explaining concepts Claude already knows, but the environment-variable set is stated twice (inline under `enable-local` and again under Configuration Details) and the full metric/log-event/trace catalog is inlined. This matches 'mostly efficient but could be tightened' rather than the efficient anchor 4.

3 / 5

Actionability

Concrete, mostly executable guidance throughout: copy-paste env blocks, parameterized operation examples ("--endpoint https://your-alloy-abc123.railway.app:443"), and runnable troubleshooting commands (curl, docker compose ps, lsof). Minor gaps keep it below 5: the Quick Start "Invoke this skill with: enable-local" blocks are not real commands, and enable-custom has no backing script or template.

4 / 5

Workflow Clarity

There is a clear enable → verify → view flow: the verify operation lists 5 checks with expected output, and Troubleshooting gives recovery paths (port conflict, permission denied). Not score 5 because `disable` leaves an ambiguous either/or action (rename file OR set env var) and the connection between operations is implicit rather than an explicit validated sequence.

4 / 5

Progressive Disclosure

Sections are well organized with dedicated References and Scripts lists, but scored against the actual bundle: 5 of the 9 referenced files do not exist (references/env-telemetry-custom.txt, references/telemetry-variables.md, references/privacy-settings.md, scripts/enable-railway.sh, scripts/disable-telemetry.sh), while scripts/activate-telemetry.sh exists but is never referenced. The inlined variable catalog is content that the missing telemetry-variables.md should hold, matching 'some structure but could be better organized' rather than the minor-gaps anchor 4.

3 / 5

Total

14

/

20

Passed

Description

78%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 strong description with an explicit what-and-when structure and good natural trigger terms for the telemetry/observability domain. Its main weakness is limited action coverage — only enable and configure are named, while the body also supports verify, disable, status, and custom endpoints.

Suggestions

Mention one or two more concrete capabilities in the description (e.g., 'verify telemetry connectivity and disable it') to lift specificity from naming 1-2 actions to listing several.

Include the full term "OpenTelemetry" alongside "OTEL" and common backend names (Grafana, DataDog) to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

"Enable and configure Claude Code OTEL telemetry" names the domain and 1-2 concrete actions (enable, configure), matching the anchor for domain plus 1-2 actions but not comprehensive coverage. It is not score 2 because enable/configure are concrete verbs rather than generic handling, and not score 4 because only two actions are listed rather than several.

3 / 5

Completeness

It explicitly answers both: what ("Enable and configure Claude Code OTEL telemetry for local or Railway observability stacks") and when ("Use when setting up Claude Code to send metrics, logs, and traces to observability backends"). Both halves are present with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Natural keywords include "telemetry", "OTEL", "metrics, logs, and traces", "observability backends", and "local or Railway" — good coverage of what a user would say when configuring telemetry. A few common terms are missing ("OpenTelemetry" spelled out, "monitoring", "Grafana"), placing it between anchors 3 and 4 but noticeably above the midpoint.

4 / 5

Distinctiveness Conflict Risk

"Claude Code OTEL telemetry" is a clear niche with distinct triggers, but the "observability stacks" phrasing overlaps with the sibling observability-stack-setup skill referenced in the body. This is minor overlap risk with a closely related skill (anchor 4) rather than the fully distinct niche of anchor 5.

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

referenced_paths_exist

Referenced path issues: 5 missing

Warning

Total

15

/

16

Passed

Repository

fernandezbaptiste/Skrillz

Path

.claude/skills/claude-code-telemetry-enable/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.