create-yourself

Why distill others when you can distill yourself? Deconstruct your chat history, diaries, and photos into a runnable digital self. | 与其蒸馏别人，不如蒸馏自己。欢迎加入数字永生！

1.29x

Quality

35%

Does it follow best practices?

Impact

93%

1.29x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./SKILL.md

Quality

Content

62%

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

This is a highly actionable and well-structured skill with clear workflows, concrete commands, and good error recovery paths. However, it suffers significantly from verbosity — the full bilingual duplication alone roughly doubles the token cost, and there's unnecessary explanation throughout. The progressive disclosure is partially achieved through external prompt file references but undermined by the monolithic main file.

Suggestions

Eliminate the inline duplication by keeping one primary language version in SKILL.md and moving the other to a separate file (e.g., SKILL_EN.md or SKILL_ZH.md), with a one-line reference at the top.

Trim the guided prompt templates (emoji question lists, menu displays) — these are presentation details Claude can generate on the fly and don't need to be specified verbatim.

Move the detailed per-source parsing instructions (WeChat, QQ, photos, etc.) into a separate SOURCES.md reference file, keeping only the tool command table in the main skill.

Dimension	Reasoning	Score
Conciseness	The content is extremely verbose at ~300+ lines, with the entire skill duplicated in both Chinese and English. Much of the content explains things Claude already knows (what EXIF data is, what WeChat is). The guided prompts like emoji-decorated question lists and menu-style option displays add significant bloat.	1 / 3
Actionability	The skill provides fully concrete, executable commands with specific tool paths, bash scripts, JSON schemas, and exact file paths. Every step has copy-paste ready code blocks with clear variable placeholders. The fallback mechanisms (script fails → manual Write tool) are well-specified.	3 / 3
Workflow Clarity	The 5-step creation flow is clearly sequenced with explicit checkpoints (Step 4 preview/confirm before Step 5 write). Evolution mode has numbered steps with backup-before-edit validation. The fallback chain (script → manual write → manual combine) provides error recovery. Destructive operations (delete) require confirmation.	3 / 3
Progressive Disclosure	The skill references external prompt files (intake.md, self_analyzer.md, persona_builder.md, etc.) which is good progressive disclosure, but the main file itself is monolithic with both full Chinese and English versions inline. The English version is a condensed duplicate rather than a proper reference, and the detailed parsing options could be split into separate files.	2 / 3
	Total	9 / 12 Passed

Description

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description reads as a marketing tagline rather than a functional skill description. It fails to specify concrete actions, lacks natural trigger terms, and provides no guidance on when Claude should select this skill. The bilingual presentation adds flavor but does not compensate for the absence of actionable detail.

Suggestions

Replace the poetic language with concrete actions, e.g., 'Parses chat logs, diary entries, and photo metadata to construct a persona profile or conversational agent.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user wants to create a digital clone, build a persona from personal data, or analyze their chat history/diaries/photos for self-modeling.'

Rewrite in third person voice ('Deconstructs chat history...') and remove rhetorical questions to match expected skill description conventions.

Dimension	Reasoning	Score
Specificity	The description uses abstract, marketing-style language ('distill yourself', 'digital self', '数字永生') without listing any concrete actions. There are no specific capabilities like 'parse chat logs', 'extract diary entries', or 'build a persona model'.	1 / 3
Completeness	The 'what' is extremely vague ('deconstruct...into a runnable digital self') and there is no 'when' clause or explicit trigger guidance whatsoever. Both dimensions are weak or missing.	1 / 3
Trigger Term Quality	While 'chat history', 'diaries', and 'photos' are mentioned, they are buried in poetic phrasing. The dominant terms ('distill', 'digital self', '数字永生') are not natural keywords a user would type when seeking this functionality. Missing practical terms like 'persona', 'clone', 'profile', 'memory extraction'.	1 / 3
Distinctiveness Conflict Risk	The concept of creating a 'digital self' from personal data is somewhat niche and unlikely to directly conflict with common skills like PDF processing or code generation. However, the vagueness means it could overlap with any skill involving chat history analysis or photo processing.	2 / 3
	Total	5 / 12 Passed

Validation

81%

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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
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

	Total	9 / 11 Passed

Repository: notdog1998/yourself-skill
Path: SKILL.md
Commit: 9deb1a8

Reviewed: about 14 hours 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.