CtrlK
BlogDocsLog inGet started
Tessl Logo

ljg-roundtable

一个议题,一场圆桌:主持人请来 3-5 位真实人物,定义开场,逐轮交锋, 每轮收一张 ASCII 结构图,用户用指令控节奏(可/止/深入此节/引入新人物), 散场后全文存入 org 笔记。Use when user says "圆桌讨论", "圆桌", "roundtable", "辩论", or wants to explore a topic through multi-perspective structured debate.

77

Quality

96%

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

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.

A lean, highly actionable instruction body with concrete formats, an explicit round structure, and a single well-signaled reference. The only gap is a missing validation checkpoint in the file-archive step.

Suggestions

In stage 六 (存档), add a verification step: confirm the file was created at the reported path (e.g., check existence / re-read it) and handle the case where ~/Context/ does not exist before writing.

For the 引入新人物 command, state explicitly whether the new participant is appended to the persisted participant list in the org archive, so archiving stays consistent.

Consider a one-line guard for the case where a user issues 止 before any 综述 round, so the 收场 summary and global network diagram still have defined behavior.

DimensionReasoningScore

Conciseness

Dense and efficient throughout—no padding explaining what a debate or ASCII chart is, and it assumes Claude's competence; even the org template block earns its place as executable spec.

5 / 5

Actionability

Provides copy-paste-ready guidance: an exact speech format, six enumerated action tags, the 可/止/深入此节/引入新人物 command menu, a real timestamp command, and a concrete org file path and structure.

5 / 5

Workflow Clarity

Six sequenced stages with an explicit per-round 发言/综述/等指令 loop are clear, but the archiving step (六) has no validation checkpoint that the org file was written successfully or that the target directory exists.

4 / 5

Progressive Disclosure

A single well-signaled one-level reference (「先读 references/original-prompt.org」) is pointed to up front, and the body is cleanly sectioned; the bundle structure (one reference file) matches an ideal overview-to-detail split.

5 / 5

Total

19

/

20

Passed

Description

100%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, specific description that names concrete actions, provides rich bilingual trigger terms, and explicitly couples the 'what' with a 'Use when' clause. Conflict risk is low given the niche framing.

DimensionReasoningScore

Specificity

Lists multiple concrete actions—「定义开场,逐轮交锋」「每轮收一张 ASCII 结构图」「用户用指令控节奏(可/止/深入此节/引入新人物)」「散场后全文存入 org 笔记」—comprehensively covering the roundtable flow rather than vague abstraction.

5 / 5

Completeness

Explicitly answers both 'what' (a structured multi-round roundtable producing ASCII diagrams and an org archive) and 'when' via a concrete 'Use when user says...' clause with trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural trigger coverage with synonyms in both languages—「圆桌讨论」「圆桌」「roundtable」「辩论」—exactly the phrases a user would say to invoke this skill.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (structured multi-perspective debate with moderator/ASCII/org-archive) with distinctive triggers; minimal realistic overlap with other skills.

5 / 5

Total

20

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
lijigang/ljg-skills
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.