quarter-clone

Clone the last quarter of the current conversation, discarding earlier context to reduce token usage while preserving recent work.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/quarter-clone/SKILL.md

Quality

Content

85%

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, executable five-step workflow with an explicit preview/verification checkpoint and no unnecessary file references. The only weakness is mild verbosity where bullets restate what the commands already show.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands, but several bullets explain behavior Claude can already infer from the command (e.g. 'Uses version sort to prefer the latest version' restates `sort -V`; 'This finds the script whether installed via plugin or manual symlink' restates `find`).	2 / 3
Actionability	Provides concrete, executable commands — the exact `tail \| jq` pipeline, the `find ... \| sort -V \| tail -1`, and `claude --resume <new-session-id>` — with each placeholder (`<script-path>`, `<session-id>`, `<project-path>`) concretely derivable from a prior step.	3 / 3
Workflow Clarity	A clear numbered 1-5 sequence with an explicit validation checkpoint at step 3 (preview to verify the session ID, and check that first/last messages match) before the mutating clone step at 4.	3 / 3
Progressive Disclosure	A simple single-purpose skill under 50 lines with no need for external bundle files (none exist in references/scripts/assets); its well-organized numbered steps satisfy the simple-skill allowance for a top score.	3 / 3
	Total	11 / 12 Passed

Description

60%

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 is specific and clearly explains what the skill does, but it lacks an explicit 'Use when' trigger clause and relies on skill-specific jargon ('last quarter', 'clone') rather than the wording users would naturally say.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the conversation is getting too long, token usage is high, or you want to keep only recent context.'

Add natural trigger variations users would say — 'trim', 'compact', 'shorten the conversation', 'context too long' — alongside 'reduce token usage'.

Differentiate more sharply from the sibling half-clone skill by naming the fraction explicitly in the trigger, e.g. 'Use when you want to keep only the last quarter (not half) of the conversation.'

Dimension	Reasoning	Score
Specificity	Lists several concrete actions in one sentence — 'Clone the last quarter of the current conversation', 'discarding earlier context', 'reduce token usage', 'preserving recent work' — matching the multiple-specific-actions anchor.	3 / 3
Completeness	Clearly states what the skill does but provides no explicit 'Use when...' trigger guidance, so per the judging guidelines completeness is capped at 2 even though the 'what' is strong.	2 / 3
Trigger Term Quality	Includes relevant natural phrases ('current conversation', 'earlier context', 'reduce token usage') but frames the task in the skill's own jargon ('last quarter', 'clone'), and omits common variations a user would actually say ('trim', 'compact', 'shorten', 'too long').	2 / 3
Distinctiveness Conflict Risk	The 'last quarter' framing is fairly specific, but the skill shares its domain and underlying script with a sibling 'half-clone' skill, so a user asking to 'clone the conversation' could reasonably trigger either.	2 / 3
	Total	9 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ykdojo/claude-code-tips
Path: skills/quarter-clone/SKILL.md
Commit: 31038b8

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.