session-summary
Generate a session summary for Langfuse tracing — capture what happened, decisions made, and metrics for observability.
52
57%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/session-summary/SKILL.mdQuality
Discovery
57%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 identifies a clear, distinctive niche (Langfuse tracing session summaries) and includes some relevant domain keywords. However, it lacks an explicit 'Use when...' clause, and the described actions ('what happened, decisions made, and metrics') are somewhat vague rather than listing concrete operations. Adding explicit trigger guidance and more specific capability details would strengthen it.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to summarize a Langfuse session, generate tracing reports, or review observability data from LLM traces.'
Make the capabilities more concrete by specifying exact actions, e.g., 'Summarizes trace spans, aggregates token usage and latency metrics, and documents tool calls and model decisions from a Langfuse session.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Langfuse tracing, session summaries) and some actions (capture what happened, decisions made, metrics), but the actions are somewhat vague — 'what happened' and 'decisions made' are not concrete, specific operations like 'extract tables' or 'fill forms'. | 2 / 3 |
Completeness | The 'what' is addressed (generate a session summary capturing events, decisions, and metrics), but there is no explicit 'Use when...' clause or equivalent trigger guidance telling Claude when to select this skill. | 2 / 3 |
Trigger Term Quality | Includes relevant keywords like 'session summary', 'Langfuse', 'tracing', 'observability', and 'metrics' which are useful trigger terms. However, it misses common variations users might say such as 'trace', 'logging', 'spans', 'LLM monitoring', or 'session recap'. | 2 / 3 |
Distinctiveness Conflict Risk | The description targets a very specific niche — Langfuse tracing session summaries for observability — which is unlikely to conflict with other skills. The combination of 'Langfuse', 'tracing', and 'session summary' creates a distinct trigger profile. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a well-structured template for session summaries and a reasonable workflow, but falls short on the core Langfuse integration — the actual tracing/logging step is vague with no executable code, specific tool names, or API examples. The analytical steps (review, catalog, assess) over-explain what Claude can infer, while the most technically specific part (Langfuse logging) is under-specified.
Suggestions
Add concrete Langfuse MCP tool invocation examples (e.g., specific tool names, payload structures) for step 5 instead of 'use the appropriate Langfuse tracing tool'.
Add a validation step after Langfuse logging to confirm the trace was successfully sent, with error handling guidance if it fails.
Condense steps 1-3 into a shorter checklist — Claude doesn't need detailed instructions on how to analyze a conversation or assess quality; focus on the output format and Langfuse-specific integration details.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is moderately efficient but includes some unnecessary elaboration. The step-by-step breakdown of 'Review the full session' and 'Assess session quality' explains analytical concepts Claude already understands. The structured template itself is valuable and earns its tokens, but the surrounding prose could be tightened. | 2 / 3 |
Actionability | The structured summary template is concrete and useful as a format specification, but the Langfuse integration guidance is vague — 'Use the appropriate Langfuse tracing tool' without specifying which tool, what API calls, or what the trace payload looks like. There's no executable code for the actual Langfuse logging step, which is the core purpose of the skill. | 2 / 3 |
Workflow Clarity | The steps are clearly sequenced (review → catalog → assess → generate → log → present), but there are no validation checkpoints. Step 5 mentions logging to Langfuse but provides no verification that the trace was successfully sent, no error handling for failed API calls, and no feedback loop for retry. The fallback to manual logging is mentioned but loosely. | 2 / 3 |
Progressive Disclosure | For a skill of this size and scope (single-purpose, no bundle files), the content is well-organized with clear sections (Steps, Important, template). The reference to `/reflect-session` for deeper reflection is a clean one-level-deep pointer. No monolithic walls of text or deeply nested references. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- AndreJorgeLopes/devflow
- Commit
b0b1bb6
- 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.