half-clone

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

Quality

70%

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/half-clone/SKILL.md

Quality

Content

93%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 content is an exceptionally lean, executable, well-sequenced workflow that assumes Claude's competence and provides copy-paste-ready commands with a preview checkpoint. The only gap is the absence of an explicit error-recovery loop if the preview fails to match.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: each step is a single command with minimal, purposeful notes, and no background concepts (e.g. what session IDs are) are over-explained. Every token earns its place.	5 / 5
Actionability	Steps provide fully executable, copy-paste-ready commands with concrete arguments and exact output handling ('New session: <id>', the precise `claude --resume <new-session-id>` command), covering the common case completely.	5 / 5
Workflow Clarity	There is a clear five-step sequence with a preview-then-verify checkpoint before the destructive clone and explicit handling of the new session ID; however, there is no 'if the preview does not match, stop' recovery loop, which leaves a minor validation gap rather than the explicit error-recovery feedback loop of the top anchor.	4 / 5
Progressive Disclosure	This is a short single-purpose skill with no bundle files and no need for external references; the content is well-organized into a numbered step list, which per the simple-skills note can score 5 without external file references.	5 / 5
	Total	19 / 20 Passed

Description

46%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 states a clear, specific 'what' but omits any 'Use when...' trigger guidance, capping completeness at 3. Trigger terms are operational rather than the natural phrases a user would say.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the conversation is getting long and you want to continue recent work with fewer tokens.'

Include natural user-facing trigger phrases such as 'conversation too long', 'reduce context', or 'split conversation' so users would naturally say them.

Optionally mention a synonym (e.g. 'copy the second half') to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	It names a concrete action ('Clone the later half of the current conversation') and the explicit outcomes (discarding earlier context, reducing token usage, preserving recent work), but offers a single action rather than the several concrete actions characteristic of higher anchors.	3 / 5
Completeness	The 'what' is clearly stated, but there is no 'Use when...' clause or equivalent trigger guidance, which the rubric requires to exceed a score of 3.	3 / 5
Trigger Term Quality	The only natural user-facing phrase is 'reduce token usage'; the operative terms ('clone', 'later half', 'discarding earlier context') are operational rather than the natural trigger phrases a user would say, and no synonyms or trigger clause are given.	2 / 5
Distinctiveness Conflict Risk	The operation ('clone the later half of the conversation') is a fairly distinct niche with limited overlap risk against other skills; it lacks fully explicit triggers but is specific enough to avoid most conflicts.	4 / 5
	Total	12 / 20 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/half-clone/SKILL.md
Commit: 2da5305

Reviewed: 7 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.