prediction-market-risk-review

Review prediction-market, basket, oracle, and trading-agent workflows for compliance, safety, data-quality, privacy, and execution risk. Use before any workflow handles venue auth, user portfolio data, API keys, or trade planning.

Quality

83%

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

Quality

Content

80%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 lean and well-organized with concrete, actionable review directives and a clear output contract. Its main weakness is workflow clarity: the gates are categories rather than a sequenced process with explicit validation checkpoints or feedback loops.

Suggestions

Sequence the Review Gates into an explicit ordered workflow (e.g., 1. Advice Boundary -> 2. Venue/Regulatory -> 3. Data Quality -> 4. Security -> 5. Privacy) so the review follows a defined process rather than parallel categories.

Add an explicit validation/feedback loop, e.g., after producing pass/warn/fail findings, re-check that every blocked action has a required mitigation before declaring the review complete.

Include one short worked example of a pass/warn/fail finding against a sample execution-capable step to make the Output Contract concrete and copy-paste ready.

Dimension	Reasoning	Score
Conciseness	Lean bullet-list guidance that assumes Claude's competence; no padding and no explanations of concepts Claude already knows, so it matches the top anchor.	5 / 5
Actionability	Concrete, specific directives (remove buy/sell/hold/size recommendations, keep ITO_API_KEY out of logs, require circuit breakers/dry runs/human approval) and a numbered output contract, but lacks worked examples of pass/warn/fail findings, leaving it just below fully executable guidance.	4 / 5
Workflow Clarity	The review gates read as parallel categories rather than a sequenced workflow, and the Output Contract is a return list, not a validated sequence; there is no explicit validate-fix-retry checkpoint loop, which fits the mid anchor.	3 / 5
Progressive Disclosure	Under ~50 lines with no need for external references, organized into clearly labeled sections (Review Gates, Output Contract), matching the simple-skill exception for a top score.	5 / 5
	Total	17 / 20 Passed

Description

87%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 well-targeted: it answers both what and when with concrete trigger phrases, occupies a distinct niche, and uses third-person voice. The only mild gap is that the capability is expressed as a single review action rather than multiple distinct operations.

Dimension	Reasoning	Score
Specificity	Names the domain (prediction-market, basket, oracle, trading-agent workflows) and a comprehensive set of review dimensions (compliance, safety, data-quality, privacy, execution risk), but the action is a single verb ("Review...") rather than multiple distinct concrete actions, so it sits just below a 5.	4 / 5
Completeness	Clearly states what it does (review workflows for the listed risk categories) and an explicit concrete trigger ("Use before any workflow handles venue auth, user portfolio data, API keys, or trade planning"), matching the top anchor.	5 / 5
Trigger Term Quality	Good coverage of natural domain terms a user would say (prediction-market, basket, oracle, trading-agent, venue auth, portfolio data, API keys, trade planning), though it lacks synonyms or variations that would push it to a 5.	4 / 5
Distinctiveness Conflict Risk	A clear niche (prediction-market / trading-agent risk review) with distinct, specialized triggers and minimal overlap risk with generic skills.	5 / 5
	Total	18 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: skills/prediction-market-risk-review/SKILL.md
Commit: d8409a4

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.