CtrlK
BlogDocsLog inGet started
Tessl Logo

langfuse-observability

Set up comprehensive observability for Langfuse with metrics, dashboards, and alerts. Use when implementing monitoring for LLM operations, setting up dashboards, or configuring alerting for Langfuse integration health. Trigger with phrases like "langfuse monitoring", "langfuse metrics", "langfuse observability", "monitor langfuse", "langfuse alerts", "langfuse dashboard".

72

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

80%

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 and token-efficient with complete executable examples and a clear step sequence. Its main weaknesses are the absence of verification checkpoints in the setup workflow and an orphaned reference file that duplicates inline content.

Suggestions

Add explicit verification checkpoints between steps, e.g., after Step 3 a 'curl http://localhost:3000/metrics' check and after Step 5 a 'confirm the Grafana panel returns data' step.

Link to references/implementation.md from the body (e.g., a '## Advanced setup' section pointing to it) and move the deeper Grafana dashboard JSON and alert rules there to reduce inline duplication.

Reconcile metric names between the body (langfuse_traces_created_total, langfuse_flush_errors_total) and references/implementation.md (langfuse_traces_total, langfuse_errors_total) so the two stay consistent.

DimensionReasoningScore

Conciseness

The body is lean and code/config-heavy, assuming Claude's competence without explaining basics like what Prometheus or metrics are; every section earns its tokens.

3 / 3

Actionability

Provides fully executable TypeScript instrumentation, a /metrics endpoint, Prometheus scrape config, Grafana dashboard JSON, and alertmanager rules that are copy-paste ready.

3 / 3

Workflow Clarity

Steps 1-6 are clearly sequenced, but there are no explicit validation or verification checkpoints (e.g., confirm Prometheus scrapes /metrics or the dashboard renders), fitting the anchor where sequence exists but checkpoints are missing.

2 / 3

Progressive Disclosure

A references/implementation.md bundle exists but is never referenced or signaled from the body, while substantial inline content (metrics setup, Grafana JSON, alert rules) overlaps with that file — matching 'references present but not clearly signaled; content that should be separate is inline'.

2 / 3

Total

10

/

12

Passed

Description

100%

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, complete, and well-triggered, clearly scoping a Langfuse observability skill with concrete capabilities and natural trigger phrases. It uses appropriate imperative/third-person voice without fluff.

DimensionReasoningScore

Specificity

Names multiple concrete actions — 'observability ... with metrics, dashboards, and alerts' — matching the anchor for listing several specific capabilities rather than vague abstraction.

3 / 3

Completeness

Explicitly answers both what (set up observability with metrics/dashboards/alerts) and when via a 'Use when...' clause, satisfying the highest completeness anchor.

3 / 3

Trigger Term Quality

Provides natural phrases a user would actually say ('langfuse monitoring', 'monitor langfuse', 'langfuse dashboard', 'langfuse alerts') with good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

Targets a clear Langfuse-observability niche with distinct, product-specific triggers, making conflicts with other skills unlikely.

3 / 3

Total

12

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository
jeremylongshore/claude-code-plugins-plus-skills
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.