half-clone

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

Quality

66%

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

72%

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, actionable 5-step workflow with executable commands and a sensible preview-before-clone validation step. Its main gaps are a duplicated opening line and a missing error-recovery branch for the destructive discard step.

Suggestions

Drop the opening line that repeats the frontmatter description; the steps are self-explanatory and the duplicate costs tokens.

Add an explicit recovery branch after step 3, e.g. "If the first/last messages do not match, re-check the session ID from history before proceeding — do not run the clone."

Tighten the step 2 sub-bullets by keeping only the version-sort note and folding the plugin/symlink rationale into a single concise line.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and command-driven, but the opening line duplicates the frontmatter description and a few explanatory sub-bullets (e.g. version-sort rationale) pad beyond what Claude could infer, keeping it just short of the every-token-earns-its-place anchor.	2 / 3
Actionability	Steps 1, 2, and 5 give fully executable bash/CLI commands, and the <script-path>, <session-id>, <project-path> placeholders are concrete values resolved earlier in the workflow, so the guidance is copy-paste ready rather than pseudocode.	3 / 3
Workflow Clarity	The 5-step sequence is clear and step 3 is an explicit preview/verification checkpoint, but because the operation discards earlier context (destructive) there is no stated error-recovery feedback loop (what to do if the preview does not match), which the 3-anchor expects.	2 / 3
Progressive Disclosure	The skill is under 50 lines, needs no external references, and is well-organized as numbered steps with sub-bullets, satisfying the simple-skill allowance for a top progressive-disclosure score.	3 / 3
	Total	10 / 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 action-oriented but lacks an explicit "Use when..." trigger clause and richer natural-language trigger variations, capping both completeness and trigger quality at 2. Distinctiveness is moderate because the niche is real but trigger guidance is absent.

Suggestions

Add an explicit "Use when..." clause, e.g. "Use when a conversation has grown long and you want to continue with only recent context to reduce token usage."

Broaden natural trigger terms with user-phrased variations such as "copy the conversation", "trim context", or "start fresh from recent messages".

Sharpen distinctiveness by naming the unique trigger condition (a too-long conversation where earlier context is no longer needed) so it is less likely to fire for general session management.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions/effects — "Clone the later half", "discarding earlier context", "reduce token usage", "preserving recent work" — matching the multi-action anchor rather than the single-domain anchor at 2.	3 / 3
Completeness	It clearly states what the skill does but provides no "Use when..." clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Terms like "clone", "conversation", "reduce token usage", and "preserve recent work" are reasonably natural but offer limited variation and lean slightly technical, so coverage is partial rather than rich.	2 / 3
Distinctiveness Conflict Risk	The half-clone operation is a fairly specific niche, but without explicit triggers and with generic-ish terms ("clone conversation", "reduce token usage") it could still overlap with general session/conversation management skills.	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/half-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.