specstory-yak

Analyze your SpecStory AI coding sessions in .specstory/history for yak shaving - when your initial goal got derailed into rabbit holes. Run when user says "analyze my yak shaving", "check for rabbit holes", "how distracted was I", or "yak shave score".

Install with Tessl CLI

npx tessl i github:specstoryai/agent-skills --skill specstory-yak

What are skills?

Review — 77%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Validation — 11 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

90%

79%

Yak Shave Weekly Retrospective

LLM summary before raw report

Criteria

Without context

With context

Summary before raw report

100%

Verdict one-liner

100%

Specific session callout

100%

Pattern identification

33%

100%

Actionable advice or joke

33%

100%

Uses analyze.py script

100%

3-5 sentence summary length

Data-driven summary

30%

100%

Without context: $0.6279 · 2m 55s · 29 turns · 28 in / 10,121 out tokens

With context: $0.6216 · 2m 4s · 30 turns · 279 in / 7,018 out tokens

90%

49%

January Productivity Audit

Date range and JSON output argument translation

Criteria

Without context

With context

Correct --from date

100%

Correct --to date

100%

JSON flag used

100%

Output saved to file

50%

100%

Output file is valid JSON

100%

JSON has required fields

90%

100%

date_range reflects January

100%

analyze.py invoked

100%

LLM summary present

80%

Without context: $0.2546 · 1m 29s · 8 turns · 9 in / 5,296 out tokens

With context: $0.5238 · 1m 33s · 28 turns · 62 in / 4,913 out tokens

82%

74%

Recent Session Focus Report

Modification time filter and top-N argument translation

Criteria

Without context

With context

--by-mtime flag used

100%

Correct --top value

100%

Correct --days value

100%

Output saved with -o flag

100%

Output file is markdown

100%

LLM summary before raw output

analyze.py invoked

100%

Without context: $0.6275 · 3m 6s · 24 turns · 21 in / 11,202 out tokens

With context: $0.6221 · 2m 16s · 25 turns · 1,781 in / 7,620 out tokens

Evaluated: about 19 hours ago
Agent: Claude Code

Table of Contents

Yak Shave Weekly Retrospective January Productivity Audit Recent Session Focus Report

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.