track-unrest-events

Retrieve seeded protest, riot, strike, and civil unrest events. Use when the user asks whether social unrest is occurring in a country or over a recent time window.

Quality

83%

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

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.

A well-built, highly actionable API skill body: copy-paste-ready example, explicit error handling, honest caveats about empty results, a content-safety section, and a 'When NOT to use' section for disambiguation. The only real weaknesses are a duplicated health-check caveat and implicit rather than enumerated workflow sequencing.

Suggestions

State the health-check guidance once (e.g., in Errors) and reference it from the Response shape section to remove the near-duplicate paragraph and tighten conciseness.

Add a brief numbered call sequence (set WM_API_KEY, curl with filters, interpret events, on empty check /api/health?compact=1) to make the workflow order explicit rather than implied by section order.

Dimension	Reasoning	Score
Conciseness	The body is lean and every section carries API-specific facts with no padding about concepts Claude already knows; however, the health-check caveat ("Read `problems` and `summary.warn` there, not the top-level `status`...") appears nearly verbatim in both the Response shape and Errors sections and could be consolidated, which is why it is not anchor 5.	4 / 5
Actionability	Everything is executable: a concrete endpoint URL, the exact auth header with an example key and provisioning link, a complete parameter table, a full response JSON, and a copy-paste-ready curl/jq worked example covering the common case — matching the 'fully executable, copy-paste ready' anchor.	5 / 5
Workflow Clarity	The workflow (set key, call endpoint, interpret response, handle errors) is coherent and error recovery is explicit per status code (401/403/429) plus an empty-events health-check/retry loop, but the sequence is conveyed through section ordering rather than an explicit step list — matching anchor 4, not 5.	4 / 5
Progressive Disclosure	No bundle files exist and the single ~100-line body is cleanly sectioned with clearly signaled one-level-deep external references (OpenAPI, auth matrix); structure is good but the full inline response shape keeps it at anchor 4 rather than a model 5.	4 / 5
	Total	17 / 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: explicit 'what' and 'when' with concrete, naturally phrased triggers and a clear niche. The main gaps are a single-verb action list and a missing common synonym ('demonstrations').

Suggestions

Add one or two more concrete actions (e.g., filter events by country, time window, and severity; sort by recency) to raise specificity beyond a single retrieve verb.

Include 'demonstrations' and possibly 'rallies' in the trigger clause so natural phrasing variations users say are all covered.

Dimension	Reasoning	Score
Specificity	"Retrieve seeded protest, riot, strike, and civil unrest events" names the domain and enumerates event types, but the action set reduces to a single verb (retrieve), matching 'names domain and 1-2 concrete actions' rather than the several distinct actions of anchor 4.	3 / 5
Completeness	It explicitly answers both: what ("Retrieve seeded protest, riot, strike, and civil unrest events") and when ("Use when the user asks whether social unrest is occurring in a country or over a recent time window"), with concrete trigger phrases matching the anchor-5 example structure.	5 / 5
Trigger Term Quality	Natural terms like "protest, riot, strike", "social unrest", "country", and "recent time window" give good coverage, but common synonyms such as "demonstrations" (which the body uses) are missing from the description, so it falls short of anchor 5's comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	The civil-unrest niche with distinct triggers is mostly distinguishable, but there is minor overlap risk with closely related skills (conflict events, news digests) — overlap the body's 'When NOT to use' section itself acknowledges.	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/track-unrest-events/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.