langfuse-performance-tuning
Optimize Langfuse tracing performance for high-throughput applications. Use when experiencing latency issues, optimizing trace overhead, or scaling Langfuse for production workloads. Trigger with phrases like "langfuse performance", "optimize langfuse", "langfuse latency", "langfuse overhead", "langfuse slow".
80
77%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/saas-packs/langfuse-pack/skills/langfuse-performance-tuning/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 completeness and distinctiveness. It clearly states when to use the skill and provides explicit trigger phrases. Its main weakness is the lack of specific concrete actions—it says 'optimize' but doesn't enumerate what optimization techniques or operations are actually performed.
Suggestions
Add specific concrete actions the skill performs, e.g., 'configure async flushing, batch trace submissions, reduce payload sizes, tune sampling rates' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Langfuse tracing performance) and a general action (optimize), but does not list multiple specific concrete actions. 'Optimize' is somewhat vague—it doesn't specify what concrete techniques or operations are performed (e.g., batching traces, reducing payload size, configuring async flushing). | 2 / 3 |
Completeness | The description clearly answers both 'what' (optimize Langfuse tracing performance for high-throughput applications) and 'when' (experiencing latency issues, optimizing trace overhead, scaling for production workloads), with explicit trigger phrases provided. | 3 / 3 |
Trigger Term Quality | The description includes a dedicated trigger phrase list with natural terms users would say: 'langfuse performance', 'optimize langfuse', 'langfuse latency', 'langfuse overhead', 'langfuse slow'. These are realistic phrases a user experiencing issues would use, and the coverage of variations is good. | 3 / 3 |
Distinctiveness Conflict Risk | The description targets a very specific niche—Langfuse tracing performance optimization—which is unlikely to conflict with other skills. The trigger terms are all Langfuse-specific, making accidental activation for unrelated skills very unlikely. | 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 skill with executable code examples and useful reference tables for Langfuse performance tuning. Its main weaknesses are the lack of a feedback loop (re-benchmark after optimization) and the length—it could be more concise by extracting detailed implementations into referenced files. The performance targets table at the top is a nice touch but isn't connected back to a verification step.
Suggestions
Add an explicit Step 7 that re-runs the benchmark from Step 1 and compares results against the performance targets table, creating a measure-optimize-verify feedback loop.
Extract the full benchmark script and utility classes (TraceSampler, truncateForTrace) into referenced files, keeping only concise usage examples inline in SKILL.md.
Remove the Prerequisites section—Claude already understands async patterns and doesn't need to be told to have a performance baseline.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with useful code examples and tables, but includes some unnecessary elements like the prerequisites section (Claude knows what async patterns are), and the memory monitoring section is basic Node.js knowledge that doesn't add much value. Some code examples could be tighter. | 2 / 3 |
Actionability | Fully executable TypeScript code throughout—benchmark script, batch configuration, non-blocking wrapper, payload truncation utility, and sampling implementation are all copy-paste ready with concrete parameters and real API calls. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced from benchmarking through optimization, but there's no validation/verification loop—after applying optimizations, there's no explicit step to re-run the benchmark and compare against the targets defined at the top. For a performance tuning workflow, a 'measure → optimize → re-measure' feedback loop is essential. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and tables, and links to external Langforce docs at the end. However, the skill is quite long (~200 lines of code) and could benefit from splitting detailed implementations (e.g., the full benchmark script, the sampler class) into separate reference files while keeping the SKILL.md as a concise overview. | 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
4dee593
- 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.