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

89%

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

Quality

Content

96%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.

A lean, highly actionable API skill: exact auth, endpoints, parameters, a runnable worked example, and thoughtful degradation semantics with no padding. The only structural note is that the inline response schema could live in a reference file if the skill grows.

Dimension	Reasoning	Score
Conciseness	The body is tables, code blocks, and API-specific semantics only (e.g. "degraded: true means the forecast backend could not read the canonical cache"); it assumes competence and never explains curl, JMESPath, or REST basics, so every token earns its place.	5 / 5
Actionability	Fully executable: exact endpoints, an API-key header spec, a copy-paste curl with URL-encoded params and jq, a parameter table with shapes, and error codes with retry guidance cover the common cases.	5 / 5
Workflow Clarity	This single-purpose read-only skill has unambiguous routing ("Start with get-forecasts; use the scorecard when the user asks whether the forecast system has been accurate") plus explicit degradation and error checkpoints; no destructive or batch operations apply.	5 / 5
Progressive Disclosure	Sections are clearly organized with one-level external pointers (OpenAPI spec, auth matrix) in a References section, but the full response schema and parameter tables are inlined in SKILL.md rather than split out, leaving minor organization gaps relative to the fully split anchor.	4 / 5
	Total	19 / 20 Passed

Description

78%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.

A strong description: concrete domain, explicit third-person capability statement, and an explicit 'Use when' clause with natural trigger phrases. It is slightly thin on action coverage and misses a few common synonyms such as 'forecast accuracy'.

Suggestions

Add one or two more concrete capability verbs (e.g. 'Filter forecasts by domain and region, project responses with JMESPath') to lift specificity beyond two actions.

Include common trigger synonyms such as 'forecast accuracy', 'prediction confidence', or 'scenario odds' so the natural-phrase coverage is comprehensive.

Name the scorecard's purpose more concretely (e.g. 'retrieve calibration/accuracy scorecard') so the second capability reads as an action rather than a vague noun phrase.

Dimension	Reasoning	Score
Specificity	"Retrieve probabilistic forecasts and their scorecard context" names the domain and two concrete actions, matching the 'Processes PDF files and extracts content' level of two-actions-not-comprehensive; it does not list several specific actions, so it is not a 4.	3 / 5
Completeness	It explicitly answers both what ("Retrieve probabilistic forecasts and their scorecard context") and when ("Use when the user asks what World Monitor is forecasting, how probabilities shifted, or how calibrated the forecasts are") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	"what World Monitor is forecasting", "how probabilities shifted", and "how calibrated the forecasts are" are natural user phrasings, but common synonyms such as "forecast accuracy" or "prediction" are missing, keeping it below comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	The "World Monitor" anchor and the calibration framing give it a clear niche with minimal conflict risk, but probabilistic forecasts mildly overlap with prediction-market-style skills, so it is mostly distinct rather than fully distinct.	4 / 5
	Total	16 / 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: da33e7a

Reviewed: 3 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.