geopolitical-risk

Geopolitical risk analysis: quantify crisis signals, identify precursors, and build event-driven strategies for war, sanctions, and supply disruption scenarios.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A rich, highly actionable skill with executable code and a clear phased strategy framework, weakened by verbosity, missing validation checkpoints, and a monolithic structure with no external references.

Suggestions

Trim encyclopedic background facts Claude already knows and tighten toy-model docstrings to reduce token cost.

Add explicit validation/feedback steps (e.g. verify data downloads, sanity-check stress-test inputs/outputs) to the phased and scenario workflows.

Split the asset-class mapping tables, data-source API reference, and backtest code into separate reference files and link them from a leaner overview, improving progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The ~910-line body is mostly structured and actionable but includes encyclopedic background Claude already knows (e.g. TSMC capacity share, Russia as top gas exporter) and verbose toy-model docstrings, so it earns the "could be tightened" anchor rather than the lean "every token earns its place" anchor.	2 / 3
Actionability	Concrete, executable Python (GPR loader, signal generation, war/gold premium, Bayesian update, GDELT/ACLED queries, stress test, backtest) with specific tickers, URLs, and thresholds is copy-paste ready, matching the fully-executable anchor.	3 / 3
Workflow Clarity	Sequenced phases (positioning / trading / mean reversion) and numbered scenario flows are present, but validation/verification checkpoints and feedback loops are absent for batch and portfolio operations, capping this at the "validation gaps" anchor per the rubric.	2 / 3
Progressive Disclosure	No bundle files exist and all content sits in one large inline SKILL.md; sections are organized, but asset mappings, data-source code, and backtests that could be split into reference files are inline, matching the "content that should be separate is inline" anchor.	2 / 3
	Total	9 / 12 Passed

Description

82%

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 specific, well-targeted description with concrete actions and natural trigger terms, but it lacks an explicit "Use when..." clause, which caps its completeness score.

Suggestions

Add an explicit usage trigger, e.g. "Use when the user asks about war, sanctions, supply disruption, or geopolitical risk to markets and portfolios."

Optionally include a couple of common phrasings users might say (e.g. "crisis hedging", "event-driven macro") to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "quantify crisis signals", "identify precursors", "build event-driven strategies" — matching the multi-action anchor rather than the partial-coverage anchor below.	3 / 3
Completeness	The "what" is explicit but there is no "Use when..." clause or equivalent explicit trigger guidance, so per the rubric guideline completeness is capped at 2 rather than reaching the explicit-triggers anchor of 3.	2 / 3
Trigger Term Quality	Natural user-facing terms like "war", "sanctions", and "supply disruption" appear alongside "geopolitical risk" and "crisis signals", giving good coverage rather than only some relevant keywords.	3 / 3
Distinctiveness Conflict Risk	"Geopolitical risk analysis" scoped to "war, sanctions, and supply disruption scenarios" carves a clear niche with distinct triggers unlikely to collide with other skills.	3 / 3
	Total	11 / 12 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
skill_md_line_count	SKILL.md is long (917 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: HKUDS/Vibe-Trading
Path: agent/src/skills/geopolitical-risk/SKILL.md
Commit: 8643fcd

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.