CtrlK
BlogDocsLog inGet started
Tessl Logo

langfuse-incident-runbook

Troubleshoot and respond to Langfuse-related incidents and outages. Use when experiencing Langfuse outages, debugging production issues, or responding to LLM observability incidents. Trigger with phrases like "langfuse incident", "langfuse outage", "langfuse down", "langfuse production issue", "langfuse troubleshoot".

67

Quality

82%

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

SKILL.md
Quality
Evals
Security

Quality

Content

82%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.

A strong, actionable incident runbook with executable scripts, clear severity tiers, and a real supporting reference file. The main gaps are minor: a few padded lines, some recovery procedures lacking an explicit re-verification loop, and the bundled reference file is not linked from the body.

Suggestions

Add an explicit pointer to the bundled reference (e.g. 'See references/implementation.md for extended diagnosis scripts and a circuit-breaker pattern') so the one-level-deep material is clearly navigable.

Close the workflow loops: after 'enable fallback mode' (Step 3) and 'docker compose restart langfuse' (Procedure C), add a re-check step pointing back to the Step 5 trace-count verification.

Tighten the Overview sentence and de-duplicate the quick-diagnosis script that appears in both Step 1 and references/implementation.md.

DimensionReasoningScore

Conciseness

Largely lean and executable with minimal over-explanation of concepts Claude already knows, though a few lines pad slightly ('Your application should work without Langfuse -- these procedures focus on restoring observability') and the reference file duplicates some triage steps already in the body.

4 / 5

Actionability

Provides copy-paste-ready bash triage and verification scripts plus concrete TypeScript snippets for fallback mode, batching, and rate-limit recovery, with specific env vars and endpoints covering the common incident cases.

5 / 5

Workflow Clarity

Clear six-step sequence with severity classification and a post-incident verification checkpoint (Step 5 checks trace count and warns if zero/ERROR), but some procedures (e.g. enable fallback, restart self-hosted) lack an explicit re-validate/re-check loop after the action, leaving minor validation gaps versus the top anchor.

4 / 5

Progressive Disclosure

Well-organized sections (Overview, Severity, Steps, Escalation, Resources) with a real one-level-deep reference file (references/implementation.md) holding extended procedures; the body never signals that reference file by name, so navigation to it is implicit rather than clearly linked.

4 / 5

Total

17

/

20

Passed

Description

82%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 well-targeted to a clear Langfuse incident niche with explicit 'what' and 'when' guidance plus concrete trigger phrases. Its main weakness is specificity — the verbs ('troubleshoot', 'respond', 'debug') are generic rather than enumerating concrete diagnostic actions.

Suggestions

Replace generic verbs with concrete capabilities, e.g. 'Triage Langfuse outages via status-page and API health checks, diagnose missing traces and 429/401 errors, and enable fallback/disabled-tracing mode.'

Add a couple of natural synonyms to the trigger list such as 'langfuse not working' or 'traces not showing' to round out keyword coverage.

DimensionReasoningScore

Specificity

Names the domain (Langfuse incidents/outages) and a couple of concrete actions ('Troubleshoot and respond', 'debugging production issues'), but the actions are generic verbs rather than a comprehensive list of specific capabilities, so it stops at the 'names domain and 1-2 concrete actions' anchor.

3 / 5

Completeness

Explicitly answers 'what' ('Troubleshoot and respond to Langfuse-related incidents and outages') AND 'when' via both a 'Use when...' clause and concrete enumerated trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Includes five natural trigger phrases users would actually say ('langfuse incident', 'langfuse outage', 'langfuse down', 'langfuse production issue', 'langfuse troubleshoot'); good coverage with a few synonyms missing (e.g. 'langfuse not working', 'traces missing'), fitting the 'good keyword coverage' anchor but not the comprehensive 5.

4 / 5

Distinctiveness Conflict Risk

Narrows to a clear niche (Langfuse-specific observability incidents) with distinct langfuse-prefixed triggers, making overlap with other skills minimal and matching the 'clear niche with distinct triggers' anchor.

5 / 5

Total

17

/

20

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.