langfuse-common-errors
Diagnose and fix common Langfuse errors and exceptions. Use when encountering Langfuse errors, debugging missing traces, or troubleshooting integration issues. Trigger with phrases like "langfuse error", "fix langfuse", "langfuse not working", "debug langfuse", "traces not appearing".
80
77%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/saas-packs/langfuse-pack/skills/langfuse-common-errors/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-structured skill description with strong trigger terms and clear 'what/when' guidance. The explicit trigger phrases are a notable strength. The main weakness is that the capability description could be more specific about what kinds of errors and fixes it covers (e.g., authentication issues, SDK configuration, missing trace data).
Suggestions
Add more specific concrete actions beyond 'diagnose and fix', such as 'resolve authentication errors, fix SDK configuration, troubleshoot missing trace data, debug callback handler setup'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Langfuse errors/exceptions) and some actions (diagnose, fix, debug missing traces, troubleshoot integration issues), but doesn't list multiple specific concrete actions like resolving auth errors, fixing SDK configuration, or handling specific exception types. | 2 / 3 |
Completeness | Clearly answers both 'what' (diagnose and fix common Langfuse errors and exceptions) and 'when' (explicit 'Use when' clause with triggers, plus a 'Trigger with phrases like' section providing concrete examples). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would actually say: 'langfuse error', 'fix langfuse', 'langfuse not working', 'debug langfuse', 'traces not appearing'. These are realistic phrases a user would type when encountering Langfuse issues. | 3 / 3 |
Distinctiveness Conflict Risk | Langfuse is a very specific tool/product, making this highly distinctive. The trigger terms are all Langfuse-specific and unlikely to conflict with other skills unless there were multiple Langfuse-related skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable troubleshooting reference with real error messages and executable fixes for each common Langfuse issue. Its main weaknesses are the lack of explicit verification steps after applying fixes (e.g., 'confirm the fix worked by running X') and the monolithic structure that could benefit from splitting into a quick-reference overview and detailed per-error files. The content is slightly verbose in places but generally earns its token cost.
Suggestions
Add a verification step after each fix (e.g., 'Re-run the auth curl command above — expect HTTP 200') to close the feedback loop and improve workflow clarity.
Consider splitting the 10 error references into a separate ERRORS_REFERENCE.md file, keeping SKILL.md as a concise overview with a quick lookup table linking to each error's section.
Remove the Prerequisites section — Claude doesn't need to be told that API credentials should be configured or that logs should be accessible; this is implicit from the troubleshooting context.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with real error messages and targeted fixes, but some sections include minor redundancy (e.g., the prerequisites section listing obvious items like 'API credentials configured'). The diagnostic script at the end adds value but the overall length is substantial for a reference document that could be tighter. | 2 / 3 |
Actionability | Every error includes the actual error message, root cause, and fully executable fix code — bash commands with proper flags, TypeScript with real API calls, and concrete patterns (singleton vs per-request). The diagnostic script is copy-paste ready. | 3 / 3 |
Workflow Clarity | Each error follows a clear pattern (Error → Cause → Fix), and the escalation path provides a sequenced troubleshooting workflow. However, there are no explicit validation/verification steps after applying fixes — e.g., 'after changing the key, re-run the auth test to confirm 200' — which would close the feedback loop for these diagnostic operations. | 2 / 3 |
Progressive Disclosure | The content is well-structured with numbered sections and a clear table-of-contents-like flow, but it's a long monolithic file (~200 lines of error references) that could benefit from splitting detailed fixes into a separate reference file. References to other skills ('langfuse-debug-bundle', 'langfuse-rate-limits') are good but the inline content is heavy. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
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 | 9 / 11 Passed | |
- Commit
70e9fa4
- 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.