CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

quant-cn-debate

Use when the user asks for Chinese stock bull/bear debate, risk adjudication or the balanced/quality/event research recipes.

Quality

74%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/quant-cn-debate/SKILL.md
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.

The content is an exemplary lean operational skill: concrete executable commands, a clearly sequenced workflow with a preview checkpoint, strong anti-fabrication verification rules, and a clean single external reference. The only meaningful gap is the absence of an explicit error-recovery loop for a failed preview.

DimensionReasoningScore

Conciseness

The ~17-line body is dense with operational instructions and contains zero padding or explanation of concepts Claude already knows, matching 'Lean and efficient; assumes Claude's competence; every token earns its place'. Even the long step-5 sentence is essential domain-specific anti-fabrication guidance, not verbosity.

5 / 5

Actionability

Commands are copy-paste ready ('python egs/skills.py preview --config <task.yaml>', 'run --config <task.yaml> --format jsonl', 'providers --probe', 'show/events/files/cancel'), with exact file paths and a pointed-to example YAML. This matches 'Fully executable; copy-paste ready code or commands' with no material gaps.

5 / 5

Workflow Clarity

Five clearly ordered steps with an explicit preview-before-run checkpoint, a conditional provider probe, and verification rules for actual output ('Do not fabricate AR/IC/drawdown... retain failed-run evidence'). It falls short of 5 because there is no explicit fix-and-retry loop if the preview step fails, matching 'Clear sequence with most checkpoints present; minor validation gaps'.

4 / 5

Progressive Disclosure

The body is a concise, well-organized overview with a single clearly-signaled one-level-deep reference ('See [the shared execution guide]... for provider limits, data fields and research gates' — the reference's contents are named) plus the example YAML path. Per the simple-skill note (under 50 lines, no bundle files), this matches the score-5 anchor.

5 / 5

Total

19

/

20

Passed

Description

43%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.

The description has a strong, explicit trigger clause and occupies a distinct niche, but it omits any statement of what the skill actually does and lacks natural synonyms users might say. It reads as half of a good description — the 'when' without the 'what'.

Suggestions

Add a leading 'what' clause naming the concrete actions performed, e.g. 'Runs the platform's multi-agent bull/bear debate workflow for Chinese stocks, producing debate transcripts, an adjudicated risk verdict and an HTML research report. Use when...'

Include natural trigger synonyms such as A股, A-shares, China equities, or long/short debate so the skill fires on the phrasings users actually say.

State the concrete outputs (debate transcript, risk adjudication, research report path) so the 'what' is explicit rather than implied by the trigger.

DimensionReasoningScore

Specificity

The description names a specific domain ('Chinese stock bull/bear debate, risk adjudication or the balanced/quality/event research recipes') but lists no concrete actions the skill performs. It matches the anchor 'Names the domain but actions are minimal or generic' rather than 3, which requires 1-2 concrete actions.

2 / 5

Completeness

An explicit 'Use when...' trigger clause is present, but the description never states what the skill does — only 'when' without 'what', matching the score-2 anchor exactly. Score 3 requires a clear 'what', and per the guidelines capabilities cannot be inferred from the trigger.

2 / 5

Trigger Term Quality

'Chinese stock' and 'bull/bear debate' are natural user phrases, but 'risk adjudication' and 'balanced/quality/event research recipes' are internal jargon, and common synonyms (A股, A-shares, China equities, long/short debate) are absent. This fits 'Some relevant keywords but missing common variations or synonyms' rather than 4, since whole synonym families are missing.

3 / 5

Distinctiveness Conflict Risk

The combination of 'Chinese stock bull/bear debate', 'risk adjudication' and platform-specific recipe names forms a clear niche with distinct triggers and minimal conflict risk with other skills. It clearly matches the score-5 anchor.

5 / 5

Total

12

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository

charliedream1/ai_quant_trade

Path

.agents/skills/quant-cn-debate/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.