CtrlK
BlogDocsLog inGet started
Tessl Logo

qveris

Paid capability marketplace for global multi-asset data; use it when free Vibe-Trading sources lack coverage, depth, or provider quality, and keep free sources as the default for routine OHLCV.

64

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./agent/src/skills/qveris/SKILL.md
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 well-structured, information-dense skill body: nearly all content is contract- and behavior-specific knowledge Claude cannot infer, the three-step workflow has genuine validation gating before paid calls, and detailed material is properly split into verified one-level-deep references. Remaining gaps are minor verbosity in the billing rationale and the lack of an example execute payload.

DimensionReasoningScore

Conciseness

The body is dense with QVeris-specific contract knowledge Claude cannot know (billing rules, mode gating, truncation behavior, measured provider quality variance) with almost no generic filler. A few passages run long — e.g. the quote_not_bounded rationale 'because its leading number is not the bill: 1 credits/result charged 9.66 credits for one stock-year' — keeping it at 'efficient; minor instances that could be trimmed' rather than the lean 5 anchor.

4 / 5

Actionability

Gives concrete tool names (qveris_search/inspect/execute), four example search queries, specific fields and defaults ('max_response_size', '20480' default, '-1'), and exact CLI commands ('vibe-trading data status'). For an instruction-only MCP-tool skill this is mostly executable guidance; it stops short of the 5 anchor because no example execute payload or call syntax is shown for the common case.

4 / 5

Workflow Clarity

The search -> inspect -> execute sequence is clearly numbered with a real validation checkpoint (inspect verifies required parameters, enums, and date formats before any paid call) and explicit gating ('only after the user has enabled QVeris and the tool has been inspected'). Failure behavior is documented (not_charged outcomes, truncation fallback via full_content_file_url), but there is no explicit error-recovery loop after a failed execute, so it sits at 'most checkpoints present; minor validation gaps' rather than 5.

4 / 5

Progressive Disclosure

The ~100-line body is an operational overview, with full API request/response schemas split into references/rest-api.md and provider coverage into references/coverage.md — both verified to exist, one level deep, and clearly signaled in a dedicated References section. This matches the top anchor: clear overview with well-signaled one-level-deep references and easy navigation.

5 / 5

Total

17

/

20

Passed

Description

75%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 with explicit what/when structure, concrete enumerated trigger conditions, and a clear default-behavior boundary. Its main weaknesses are the absence of concrete capability actions and thin natural-language synonym coverage for the data domains it serves.

Suggestions

Add 1-2 concrete capability actions to the description, e.g. 'search, inspect, and execute paid data capabilities' or name flagship datasets like options Greeks, analyst estimates, and China/HK market data.

Broaden trigger-term coverage with natural synonyms users would say, such as 'premium market data', 'financial data API', or 'options Greeks', rather than relying on internal terms like 'Vibe-Trading sources'.

DimensionReasoningScore

Specificity

Names the domain concretely ('Paid capability marketplace for global multi-asset data') and one conditional usage action ('use it when free Vibe-Trading sources lack coverage, depth, or provider quality'), but lists no concrete operations (e.g., search, inspect, execute paid data calls). Matches the anchor 'names domain and 1-2 concrete actions, but not comprehensive'; a 4 would require several specific actions.

3 / 5

Completeness

Explicitly answers what ('Paid capability marketplace for global multi-asset data') and when with three concrete enumerated conditions ('lack coverage, depth, or provider quality') plus an explicit default rule ('keep free sources as the default for routine OHLCV'). Matches the top anchor; a 4 would have a vaguer or less enumerated 'when' clause.

5 / 5

Trigger Term Quality

Contains relevant keywords ('coverage', 'depth', 'provider quality', 'OHLCV', 'multi-asset data') but misses the natural phrases a user would say when needing this skill ('options Greeks', 'analyst estimates', 'premium financial data', 'China A-share'). Fits 'some relevant keywords but missing common variations or synonyms'; not 4 because the synonym coverage is thin and partly internal jargon ('Vibe-Trading sources').

3 / 5

Distinctiveness Conflict Risk

It carves a clear niche — the paid escalation path explicitly scoped against free built-in sources — so it is unlikely to trigger for unrelated skills. Distinct trigger conditions and the OHLCV default rule give it minimal conflict risk, matching the 'clear niche with distinct triggers' anchor.

5 / 5

Total

16

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
HKUDS/Vibe-Trading
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.