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.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./agent/src/skills/qveris/SKILL.md

Quality

Content

67%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 body is well-structured, actionable, and workflow-gated with billing/truncation specifics that respect Claude's intelligence. The critical flaw is broken reference paths: both inline links use a 'qveris/' prefix that does not exist in the bundle, leaving the progressive-disclosure navigation non-functional.

Suggestions

Fix the broken reference links so they point to the actual bundle paths: change 'qveris/references/rest-api.md' → 'references/rest-api.md' and 'qveris/references/coverage.md' → 'references/coverage.md' (the qveris/ directory does not exist).

Add one executable example showing a minimal qveris_search → qveris_inspect → qveris_execute payload (e.g., a sample parameters object and expected fields) to move actionability from 4 to 5.

Add an explicit fix-and-retry feedback loop for failed execute calls (e.g., on status=not_charged / missing-parameter, re-inspect the schema, correct parameters, then re-execute) to lift workflow_clarity to 5.

Dimension	Reasoning	Score
Conciseness	The body is dense with operational specifics (tool params, billing rules, truncation behavior) and largely avoids teaching concepts Claude already knows; minor redundancy between the intro paragraph and the 'Choosing a Capability'/'Billing and Modes' sections keeps it from a 5.	4 / 5
Actionability	Provides concrete tool names (qveris_search/inspect/execute), named parameters (tool_id, parameters, max_response_size, session_id), and concrete example queries, but there is no copy-paste executable code block showing an actual call payload, which is the gap versus a 5.	4 / 5
Workflow Clarity	A clear numbered discover→inspect→execute sequence with explicit gating ('only after the user has enabled QVeris and the tool has been inspected') and validation-ish checkpoints (verify required params/enum/date formats before paid calls); missing an explicit fix-and-retry feedback loop for failed/charged calls, so it sits at 4 rather than 5.	4 / 5
Progressive Disclosure	The two reference links point to 'qveris/references/rest-api.md' and 'qveris/references/coverage.md', but those paths do not exist — the actual bundle files live at 'references/rest-api.md' and 'references/coverage.md' (no qveris/ prefix), so the signaled navigation is broken and references do not resolve.	2 / 5
	Total	14 / 20 Passed

Description

76%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 is complete and specific with a clear 'what' and 'when' plus a useful default-routing boundary. Its main weakness is trigger-term quality: it leans on product/jargon terms rather than the natural phrases users would say.

Suggestions

Reframe trigger terms toward natural user phrasing (e.g., 'options Greeks', 'analyst estimates', 'macro/CPI series', 'HK/CN market data') so users' requests match without knowing the 'QVeris' brand.

Consider whether 'Paid capability marketplace for global multi-asset data' could be stated as concrete actions (search, inspect, execute paid data capabilities) to lift specificity from 4 to 5.

Tighten the Vibe-Trading internal framing so the description reads as a standalone capability rather than referencing the host product.

Dimension	Reasoning	Score
Specificity	Names the concrete capability ('paid capability marketplace for global multi-asset data') and several specific data domains (market, fundamental, macro, derivatives, crypto, China/HK, news, filings, alt-data), though it describes one marketplace action rather than a list of several distinct operations.	4 / 5
Completeness	Explicitly answers both 'what' (paid capability marketplace for global multi-asset data) and 'when' with concrete trigger guidance ('use it when free Vibe-Trading sources lack coverage, depth, or provider quality'), plus a clear default rule for routine OHLCV.	5 / 5
Trigger Term Quality	Includes some relevant natural terms (OHLCV, free sources, China/HK coverage) but is framed around internal product names ('QVeris', 'Vibe-Trading') and jargon ('capability marketplace', 'provider quality') rather than the plain phrases a user would naturally say; no file extensions or common synonyms beyond OHLCV.	3 / 5
Distinctiveness Conflict Risk	The niche (paid multi-asset data marketplace vs the free built-in loader chain) is mostly distinct with explicit fallback boundary, but the data-source category and 'Vibe-Trading' framing leave minor overlap risk with adjacent free-source skills.	4 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 missing, 2 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: HKUDS/Vibe-Trading
Path: agent/src/skills/qveris/SKILL.md
Commit: 99e84ab

Reviewed: 2 days 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.