CtrlK
BlogDocsLog inGet started
Tessl Logo

specstory-organize

Organize SpecStory AI coding sessions in .specstory/history into year/month folders. Run when user says "organize my history", "clean up specstory", "sort my sessions", or "organize specstory files".

Install with Tessl CLI

npx tessl i github:specstoryai/agent-skills --skill specstory-organize
What are skills?

85

Does it follow best practices?

Validation for skill structure

SKILL.md
Review
Evals

Evaluation results

100%

22%

Clean Up SpecStory History Directory

History file organization and result reporting

Criteria
Without context
With context

Script invocation

0%

100%

YYYY/MM structure

100%

100%

Correct year/month assignment

100%

100%

Non-.md file skipped

100%

100%

Undated .md file skipped

100%

100%

Skipped files reported

100%

100%

Total count reported

100%

100%

Per-month breakdown

100%

100%

Runs from project root

0%

100%

notes.md handling

100%

100%

Without context: $0.2330 · 53s · 15 turns · 16 in / 3,194 out tokens

With context: $0.5604 · 1m 43s · 38 turns · 30 in / 6,044 out tokens

100%

27%

Audit SpecStory History Before Reorganizing

Dry-run preview mode

Criteria
Without context
With context

Uses --dry-run flag

25%

100%

Script invocation

0%

100%

Output captured to file

100%

100%

Would-move entries present

100%

100%

No-files-moved confirmation

100%

100%

Files remain unmoved

100%

100%

Skipped file noted

100%

100%

Runs from project root

100%

100%

Without context: $0.7572 · 2m 54s · 50 turns · 308 in / 9,908 out tokens

With context: $0.4730 · 1m 36s · 31 turns · 2,023 in / 4,378 out tokens

100%

7%

Bring SpecStory History Up to Date

Incremental re-organization and result presentation

Criteria
Without context
With context

Script invocation

30%

100%

Already-organized files untouched

100%

100%

New files organized

100%

100%

Correct YYYY/MM assignment

100%

100%

README.md skipped

100%

100%

Total moved count reported

100%

100%

Per-month breakdown in summary

100%

100%

Skipped file noted in summary

100%

100%

Runs from project root

100%

100%

Filename-based date used

100%

100%

Without context: $0.8423 · 3m 12s · 49 turns · 43 in / 11,664 out tokens

With context: $0.6295 · 1m 53s · 39 turns · 30 in / 6,766 out tokens

Evaluated
Agent
Claude Code

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.