CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

tong-jincheng-perspective

童锦程视角:以"深情祖师爷"、直播情感内容创作者的思维框架看待人际关系、社会动态与个人成长。 素材来源:9个一手视频字幕(直播/约会vlog/搭讪解析),约20万字。 核心模型:5个。决策启发式:9条。 触发词:「童锦程」「深情祖师爷」「用童锦程的方式」「从童锦程视角」「景辰怎么看」 局限:素材以情感/人际内容为主,商业/创业思维数据不足,慎用于纯商业决策场景。 调研时间:2026年4月。

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

A rich, well-structured persona skill: highly actionable style DNA, evidence-backed mental models with stated limitations, and honest scope boundaries. Its main weakness is progressive disclosure — six reference files and four assets ship in the bundle but are never linked from SKILL.md, and their deeper material is inlined instead — with minor redundancy across sections as a secondary cost.

Suggestions

Add a 调研材料 section that links each reference file with a one-line description (e.g., '完整口头禅频率表见 [03-expression-dna.md](references/research/03-expression-dna.md)'), so the deeper research is discoverable instead of orphaned.

Trim cross-section repetition: the 真诚 quote and the 渣男 self-label insight each appear in 3-4 sections; state each once and cross-reference the model number elsewhere.

Add 2-3 lines of model-selection guidance (e.g., which of the five models applies for persuasion vs. testing vs. reading signals situations), or a short worked example of one response assembled from the style rules.

DimensionReasoningScore

Conciseness

The body is dense with persona-specific material (verbatim quotes, model evidence, style rules) and wastes no tokens explaining concepts Claude already knows. However, there is real cross-section repetition — the 真诚 quote recurs in the epigraph, 身份卡, 价值观 and 内在张力, and 「说自己是渣男的全是好人」 appears in both model 4's evidence and heuristic 8 — so it is 'efficient with minor instances that could be trimmed' rather than fully lean.

4 / 5

Actionability

As an instruction-only skill the guidance is fully actionable: verbatim signature openers and closers (「说实话兄弟们...」「...没毛病吧兄弟们」), explicit address rules (「用"兄弟们"或"兄弟"作为称谓」), nine concrete decision heuristics with quoted rationale, and explicit boundary handling for out-of-scope questions (「遇到商业/创业问题:说明此维度数据不足,给出基于人性洞察的推断」). Specific examples cover the common response cases, matching the top anchor.

5 / 5

Workflow Clarity

The 角色扮演规则 section gives unambiguous activation rules (first person, no fabricated positions, colloquial style, boundary behavior), and the 内在张力 section resolves the main rule conflicts. It falls short of anchor 5 because there is no guidance for selecting among the five overlapping models when several apply, and no worked example showing the response assembly order.

4 / 5

Progressive Disclosure

The body itself is well-sectioned (13 clear headers), but the bundle contains six research files under references/research/ (e.g., 03-expression-dna.md with catchphrase frequency tables extending the inlined 表达DNA section) and four assets, none of which are referenced anywhere in the body. This matches 'some structure; references present but not clearly signaled; content that should be separate is inline' — not anchor 2, since the inline content is a distilled synthesis with good structure rather than a raw dump.

3 / 5

Total

16

/

20

Passed

Description

90%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.

A strong description: it states what the skill does, its evidence base and scope limits (「商业/创业思维数据不足,慎用于纯商业决策场景」), and explicit trigger words including name synonyms. The only weakness is that the capability statement stays at one general action (viewing three domains through the persona's framework) rather than enumerating specific concrete capabilities.

DimensionReasoningScore

Specificity

The description names its domains (「人际关系、社会动态与个人成长」) and one general action (「以...思维框架看待」), plus meta-information (「核心模型:5个。决策启发式:9条」), but does not enumerate several concrete capabilities. It matches 'names domain and 1-2 concrete actions, but not comprehensive' rather than the several-action anchor above it.

3 / 5

Completeness

It explicitly answers both 'what' (「以...思维框架看待人际关系、社会动态与个人成长」, with 5 models and 9 heuristics) and 'when' via a dedicated trigger-word line with concrete phrases. The 'when' is fully explicit rather than merely present, matching the top anchor instead of the anchor-4 example where 'when' could be more specific.

5 / 5

Trigger Term Quality

The 触发词 line provides comprehensive natural terms including synonyms (「童锦程」「深情祖师爷」「景辰怎么看」) and usage phrasings (「用童锦程的方式」「从童锦程视角」) that a user would literally say to invoke this persona. No natural trigger phrasing is missing for this skill type, so it fits the top anchor rather than 'a few natural terms missing'.

5 / 5

Distinctiveness Conflict Risk

It occupies a clear named-persona niche with triggers locked to that person's name and nicknames (「童锦程」「深情祖师爷」「景辰」), so it would not fire for unrelated skills. This is minimal conflict risk, matching the top anchor.

5 / 5

Total

18

/

20

Passed

Validation

100%

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

hotcoffeeshake/tong-jincheng-skill

Path

SKILL.md

Reviewed

Table of Contents

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.