langfuse-data-handling
Manage Langfuse data export, retention, and compliance requirements. Use when exporting trace data, configuring retention policies, or implementing data compliance for LLM observability. Trigger with phrases like "langfuse data export", "langfuse retention", "langfuse GDPR", "langfuse compliance", "export langfuse traces".
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-data-handling/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 that excels in completeness and distinctiveness by clearly specifying both what the skill does and when to use it, with Langfuse-specific trigger terms that minimize conflict risk. The main weakness is that the capability descriptions could be more granular—listing specific concrete actions rather than broad categories like 'manage data export' would improve specificity.
Suggestions
Expand the capability list with more concrete actions, e.g., 'Export trace data to JSON/CSV, configure TTL-based retention policies, handle GDPR deletion requests, audit data access logs' instead of the broader 'manage export, retention, and compliance'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Langfuse data management) and some actions (export, retention, compliance), but the actions are somewhat high-level rather than listing multiple concrete specific operations like 'export trace data to CSV, configure TTL retention policies, delete user data for GDPR requests'. | 2 / 3 |
Completeness | Clearly answers both 'what' (manage Langfuse data export, retention, and compliance) and 'when' (explicit 'Use when' clause with specific scenarios plus a 'Trigger with phrases' section listing concrete trigger terms). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms that users would actually say: 'langfuse data export', 'langfuse retention', 'langfuse GDPR', 'langfuse compliance', 'export langfuse traces'. These cover multiple natural variations and are specific to the domain. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific Langfuse product focus combined with the data export/retention/compliance niche. The trigger terms are all Langfuse-prefixed, making conflicts with other 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 skill provides highly actionable, executable TypeScript code covering a comprehensive set of Langfuse data handling scenarios. Its main weaknesses are the lack of validation/confirmation steps for destructive operations (deletion, retention enforcement) and the monolithic structure that could benefit from splitting detailed implementations into separate files. The repeated pagination patterns add unnecessary length.
Suggestions
Add dry-run mode and confirmation/verification steps to destructive operations (enforceRetention, handleDeletionRequest) — e.g., log what will be deleted before deleting, verify deletion count matches expected count
Extract the repeated pagination pattern into a shared helper function to reduce code duplication and overall length
Split detailed implementations (GDPR handlers, anonymization, score export) into a separate REFERENCE.md file, keeping SKILL.md as a concise overview with quick-start examples and pointers
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long with extensive code blocks that could be tightened. Some patterns are repeated (pagination loops, rate limiting delays) across multiple functions. However, it doesn't over-explain concepts Claude already knows, and the content is mostly domain-specific. The data categories table adds value but the error handling table is somewhat generic. | 2 / 3 |
Actionability | All guidance is provided as fully executable TypeScript code with concrete examples, specific API calls, and copy-paste ready functions. Each step includes complete, runnable code with usage examples, covering export, retention, GDPR requests, and anonymization. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced and labeled, but critical validation checkpoints are missing. The deletion operations (retention enforcement, GDPR erasure) are destructive batch operations with no confirmation step, no dry-run option, and no verification that deletion completed successfully. The pagination check (hasMore = result.data.length === 100) could silently miss data but isn't flagged. Missing feedback loops for destructive operations caps this at 2. | 2 / 3 |
Progressive Disclosure | The skill includes external resource links at the bottom, which is good. However, the content is quite long (~200 lines of code) and could benefit from splitting detailed implementations (e.g., GDPR handlers, anonymization) into separate reference files, keeping SKILL.md as a concise overview with pointers. The inline tables are appropriate but the code-heavy sections make this somewhat monolithic. | 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
3e83543
- 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.