risk-analysis

Risk measurement and stress testing — VaR/CVaR/max drawdown calculation, Monte Carlo simulation, extreme-value tail-risk analysis, and historical scenario stress testing.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./agent/src/skills/risk-analysis/SKILL.md

Quality

Content

82%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 an actionable, well-organized reference with executable examples and genuinely non-obvious domain gotchas; its main weaknesses are a few padded comparison/definition rows and a main analysis workflow whose validation checkpoints are implicit rather than explicit.

Suggestions

Tighten the VaR-vs-CVaR comparison table by dropping the regulation/subadditivity rows unless they drive a concrete decision, and merge the bare 'Definition' lines into the prose.

Make the Analysis Steps sequence's validation explicit — e.g. insert a checkpoint after VaR/CVaR ('verify cvar >= var') and after GPD fitting ('confirm shape_xi is stable across nearby threshold_pct').

Consider splitting the large historical-scenario table and STRESS_SCENARIOS dict into a references/ file to shorten the main SKILL.md and aid progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is dense and high-signal, focusing on non-obvious gotchas (sign convention, parametric-vs-historical gap, the 2σ tail-type rule) rather than basics Claude already knows, though the VaR/CVaR comparison table (Basel/subadditivity rows) and a few 'Definition' lines could be trimmed.	4 / 5
Actionability	Provides copy-paste-ready executable code with real signatures, arguments, return-dict keys, array shapes, and error conditions across every method, covering the common cases fully.	5 / 5
Workflow Clarity	A clear 7-step Analysis Steps sequence plus a 4-step stress-test procedure with an 'assess adequacy' checkpoint, and embedded checks (CVaR >= VaR, threshold stability, sign discipline) act as checkpoints; minor validation gaps remain in the main sequence.	4 / 5
Progressive Disclosure	No bundle files exist, so the self-contained ~290-line body is scored on its own structure: clear top-level sections (Overview, Risk Measurement Methods, Stress-Testing Framework, Tail-Risk Analysis, Analysis Framework, Output Format, Notes) with easy header navigation and no nested references, though some detailed tables/scenario dicts could arguably be split out.	4 / 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.

The description is specific and well-targeted to a distinct quantitative-risk niche, but it omits any explicit 'when to use' trigger guidance, which caps its completeness. Adding a Use-when clause naming the natural trigger scenarios would raise the score.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user asks for VaR/CVaR, stress testing, Monte Carlo risk simulation, or tail-risk analysis on return or equity series.'

Include common synonyms such as 'expected shortfall (ES)' and 'value at risk' spelled out to broaden natural trigger coverage.

Optionally name the inputs the skill expects (return series / equity curve / portfolio weights) so the trigger is even more concrete.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'VaR/CVaR/max drawdown calculation, Monte Carlo simulation, extreme-value tail-risk analysis, and historical scenario stress testing' — covering the risk-measurement domain comprehensively, matching the anchor for multiple specific concrete actions.	5 / 5
Completeness	The 'what' is clear and concrete, but there is no 'Use when...' clause or equivalent trigger guidance; per the guidelines a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	Strong natural terms a quant user would actually say ('VaR/CVaR', 'stress testing', 'Monte Carlo', 'max drawdown', 'tail risk'), but a few common synonyms are missing ('expected shortfall', 'value at risk' spelled out, 'scenario analysis').	4 / 5
Distinctiveness Conflict Risk	Occupies a clear, specialized niche (quantitative risk measurement and stress testing) with distinct triggers like VaR/CVaR and EVT tail analysis, giving minimal overlap with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: HKUDS/Vibe-Trading
Path: agent/src/skills/risk-analysis/SKILL.md
Commit: 1907e47

Reviewed: 1 day 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.