check-forecast-signals

Retrieve probabilistic forecasts and their scorecard context. Use when the user asks what World Monitor is forecasting, how probabilities shifted, or how calibrated the forecasts are.

Quality

82%

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

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 a lean, highly actionable API skill with executable curl examples and clear error/flag handling. Structure is well-sectioned with shallow external references, though the inline API reference could be marginally tighter and the workflow checkpoints are implicit.

Suggestions

Tighten the response-shape block to only the fields referenced elsewhere, or move the full schema behind the already-linked OpenAPI URL to improve conciseness.

Add a short numbered call sequence (get-forecasts -> inspect degraded/stale/error -> project keeping flags -> retry on 429) to make validation checkpoints explicit rather than implied.

Consider splitting the parameter tables and JMESPath projection guidance into a short reference section or file so the overview stays scannable.

Dimension	Reasoning	Score
Conciseness	The body is API-specific and avoids explaining concepts Claude already knows, but sections like the full response-shape JSON and the JMESPath note retain minor padding that could be trimmed, fitting the 'efficient with minor over-explanation' anchor.	4 / 5
Actionability	Provides concrete endpoints, an exact auth-header format, parameter tables with shapes, and a copy-paste-ready curl worked example with a JMESPath projection — fully executable guidance covering the common case.	5 / 5
Workflow Clarity	The read-only single-action flow (call get-forecasts, check degraded/stale/error flags, keep flags when projecting, retry on 429) is unambiguous with implicit validation via status flags, though checkpoints are implicit rather than enumerated as a numbered sequence.	4 / 5
Progressive Disclosure	Well-organized into clear sections with one-level external references (OpenAPI, auth-matrix URLs) and no bundle files to navigate; the inline response-shape and parameter reference are sizable enough to leave minor organization gaps versus an ideal split.	4 / 5
	Total	17 / 20 Passed

Description

82%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 cleanly answers both what the skill does and when to use it, with concrete World-Monitor-specific triggers that make it highly distinct. The only soft spot is specificity, which lists just two retrieval actions rather than a comprehensive set.

Dimension	Reasoning	Score
Specificity	Quotes 'Retrieve probabilistic forecasts and their scorecard context' — names the domain plus two concrete actions (retrieve forecasts, retrieve scorecard context), matching the anchor for 1-2 concrete actions without comprehensive coverage.	3 / 5
Completeness	Explicitly states the what ('Retrieve probabilistic forecasts and their scorecard context') and the when ('Use when the user asks...') with concrete trigger phrases, mirroring the anchor-5 example.	5 / 5
Trigger Term Quality	Quotes 'what World Monitor is forecasting, how probabilities shifted, or how calibrated the forecasts are' — good natural keyword coverage with concrete trigger phrasing, though a few synonyms (e.g. 'prediction', 'scenarios') are absent.	4 / 5
Distinctiveness Conflict Risk	Tightly scoped to 'World Monitor' forecasts and calibration, a clear niche with distinct triggers and minimal overlap risk 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: koala73/worldmonitor
Path: public/.well-known/agent-skills/check-forecast-signals/SKILL.md
Commit: 23ab7d1

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.