create-ex

Distill an ex-partner into an AI Skill. Import WeChat history, photos, social media posts, generate Relationship Memory + Persona, with continuous evolution. | 把前任蒸馏成 AI Skill，导入微信聊天记录、照片、朋友圈，生成 Relationship Memory + Persona，支持持续进化。

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./SKILL.md

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with concrete commands and templates and a well-sequenced main flow, but it is token-heavy due to full bilingual duplication, lacks validation feedback loops around destructive delete operations, and references bundle files that are not present.

Suggestions

Collapse the bilingual duplication: keep one primary language inline and link to the other rather than restating the entire workflow twice.

Provide the referenced bundle files (tools/*.py, prompts/*.md, create-ex/docs/EXPORT_GUIDE.md) or remove the references so the skill is self-contained.

Add a validation/verification step before destructive commands (e.g. confirm the slug resolves to an existing ex directory and show what will be removed before running `rm -rf`).

Dimension	Reasoning	Score
Conciseness	Mostly efficient and actionable, but the entire skill is duplicated across Chinese and English, roughly doubling the token cost — the English version restates the Chinese flow rather than adding new information.	2 / 3
Actionability	Provides fully concrete, copy-paste-ready guidance: exact `python3 …/tools/*.py` invocations with flags, directory-creation commands, a full meta.json template, and a complete generated-SKILL.md template.	3 / 3
Workflow Clarity	Steps are clearly sequenced (Step 1–5, evolution modes) with a preview confirmation in Step 4, but destructive operations like `/delete-ex` (`rm -rf exes/{slug}`) have only a user confirmation and no validation/verification checkpoint, capping workflow clarity at 2.	2 / 3
Progressive Disclosure	References to prompts/ and tools/ files are clearly signaled one level deep, but none of those bundle files actually exist in the skill, and the main body is monolithic — all prompt templates and the full bilingual duplicate live inline rather than being split out.	2 / 3
	Total	9 / 12 Passed

Description

67%

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, distinct, and concrete about what the skill does, but it lacks an explicit 'when to use it' trigger clause and relies on domain terms rather than the phrases users naturally say.

Suggestions

Add an explicit 'Use when…' clause, e.g. 'Use when the user wants to recreate or talk to an ex-partner from their chat history and photos.'

Surface the natural trigger phrasings already in the body (e.g. 'create an ex skill', 'distill an ex', 'talk to my ex again') into the description so it matches what users actually say.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Distill an ex-partner into an AI Skill', 'Import WeChat history, photos, social media posts', 'generate Relationship Memory + Persona, with continuous evolution' — rather than vague language.	3 / 3
Completeness	Clearly answers 'what' (distill, import, generate, evolve) but provides no explicit 'Use when…' trigger guidance, capping completeness at 2 per the rubric guidelines.	2 / 3
Trigger Term Quality	Contains relevant domain keywords ('ex-partner', 'WeChat history', 'photos', 'social media posts') but omits the natural phrasings a user would actually say ('create an ex skill', 'chat with my ex again'), so coverage of common variations is incomplete.	2 / 3
Distinctiveness Conflict Risk	A very specific niche — distilling an ex-partner from WeChat/photo/social data — with distinct triggers that would not reasonably conflict with other skills.	3 / 3
	Total	10 / 12 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (504 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 missing, 1 deeper-than-1-level	Warning

	Total	12 / 16 Passed

Repository: therealXiaomanChu/ex-skill
Path: SKILL.md
Commit: a7c0638

Reviewed: 5 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.