CtrlK
BlogDocsLog inGet started
Tessl Logo

specstory-session-summary

Summarize recent SpecStory AI coding sessions in standup format. Use when the user wants to review sessions from .specstory/history, prepare for standups, track work progress, or understand what was accomplished.

91

3.55x
Quality

87%

Does it follow best practices?

Impact

96%

3.55x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Evaluation results

100%

84%

Dev Team Standup Preparation

Standup summary output format

Criteria
Without context
With context

Completed emoji

0%

100%

Research emoji

0%

100%

Title from goal, not filename

50%

100%

Filenames only, not full paths

0%

100%

Goal field present

0%

100%

Outcome field present

0%

100%

Files field present

12%

100%

None for research files

50%

100%

Patterns section present

0%

100%

Unfinished section present

36%

100%

100%

50%

End-of-Day Standup Summary

Today argument date filtering

Criteria
Without context
With context

Only today's sessions

100%

100%

Yesterday excluded

100%

100%

Both today's sessions present

100%

100%

Completed emoji used

0%

100%

Blocked emoji used

0%

100%

Goal field present

0%

100%

Outcome field present

0%

100%

Patterns section present

0%

100%

Unfinished section present

0%

100%

88%

71%

Sprint Retrospective Session Report

Multi-task session format

Criteria
Without context
With context

Tasks format used

0%

100%

At least 2 tasks listed

66%

100%

Outcome emoji per task

0%

100%

Minor tasks grouped

0%

0%

Overall theme title

60%

100%

Files field present

12%

100%

Filenames only

0%

100%

Patterns section present

0%

100%

Unfinished section present

0%

100%

Repository
specstoryai/agent-skills
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

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.