CtrlK
BlogDocsLog inGet started
Tessl Logo

session-summary

Generate a session summary for Langfuse tracing — capture what happened, decisions made, and metrics for observability.

56

Quality

64%

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

Fix and improve this skill with Tessl

tessl review fix ./devflow-plugin/skills/session-summary/SKILL.md

The canonical home for this skill is session-summary in AndreJorgeLopes/devflow

SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

The body is a tight, well-structured instruction skill with a concrete output template, clear step sequence, and no concept over-explanation. It performs solidly across all dimensions, with the only notable gap being the absence of explicit validation checkpoints and a slightly long inline template.

DimensionReasoningScore

Conciseness

The body is efficient and assumes Claude's competence — it never explains what Langfuse or a session is — using terse bullet lists and a template; only minor wording in the intro and 'Important' section could be trimmed.

4 / 5

Actionability

It supplies a concrete, fill-in structured template (Actions table, Decisions, Errors, Metrics, Quality Score, Tags) plus explicit MCP-logging instructions, leaving only small gaps such as how to compute the short hash in the Session ID.

4 / 5

Workflow Clarity

Six numbered steps are clearly sequenced with a conditional fallback ('If Langfuse tools are not available...'), and the 'Important' section acts as a soft checklist; there are no hard validation checkpoints, but the task is non-destructive so that is not disqualifying.

4 / 5

Progressive Disclosure

Content is well-organized under clear section headers with a self-contained template; no bundle files exist so there is no nested-reference problem, though the large inline template could arguably live in a reference file for a skill over 50 lines.

4 / 5

Total

16

/

20

Passed

Description

53%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 clearly states what the skill does and ties it to a distinct niche (Langfuse observability), but it omits any explicit "when to use" trigger guidance and relies on somewhat generic capture actions, leaving it mid-range across most dimensions.

Suggestions

Add an explicit 'Use when...' trigger clause naming the natural phrases users say, e.g. 'Use when wrapping up a coding session, reviewing what was done, or logging a session to Langfuse.'

Replace generic verbs ('capture what happened') with more specific capabilities like 'extract goal, outcome, actions, and quality metrics into a structured Langfuse trace'.

Include natural synonyms and trigger variations (e.g. 'session recap', 'trace this session', 'observability summary') to improve trigger-term coverage.

DimensionReasoningScore

Specificity

Names the domain ("session summary for Langfuse tracing") and a few concrete actions ("capture what happened, decisions made, and metrics for observability"), but the actions are generic capture/extraction verbs rather than a comprehensive, specific list.

3 / 5

Completeness

The "what" is clear (generate a session summary for Langfuse tracing), but there is no "Use when..." clause or equivalent explicit "when" guidance, which caps completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

Includes some relevant natural keywords ("session summary", "Langfuse", "observability", "metrics") but lacks common variations and has no explicit trigger phrase a user would naturally utter.

3 / 5

Distinctiveness Conflict Risk

The Langfuse-specific framing carves a clear niche with minimal conflict risk, though generic "session summary" wording could mildly overlap with other reflection/summary skills.

4 / 5

Total

13

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
AndreJorgeLopes/devflow
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.