validate-contribution

Validate geographic data contributions against the CSC database schema. Use this skill whenever you encounter a PR that adds, modifies, or deletes data in the contributions/ directory. Trigger on: validate, check, review, verify, audit, inspect, or assess any data contribution, PR review requests, schema compliance checks, field validation, or when someone says "is this correct", "check my data", "validate this", or "review my PR". Also use when asked about required fields, allowed values, or data format rules. Read schema-rules.md in this directory for the complete field specification.

Quality

88%

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

85%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-structured, token-efficient validation procedure with concrete constraints and a clear PASS/FAIL output format. Its two real weaknesses are the dangling schema-rules.md reference that both the body and the description rely on, and unspecified data sources for the cross-reference and bounds checks in Steps 5-6.

Suggestions

Ship the referenced schema-rules.md file in the skill bundle (e.g. under references/) or inline the field specification it is meant to hold — currently Step 3 and the description both point to a file that does not exist, breaking the skill's authoritative reference.

State the concrete locations of countries.json and states.json in Step 5 (e.g. a repository path) so the cross-reference checks can actually be executed instead of guessed.

Give Step 6 a practical bounds-checking method (e.g. a bounding-box table per country, or an explicit 'use the referenced country's bounding box if available, otherwise skip') so 'geographic bounds' is actionable rather than aspirational.

Dimension	Reasoning	Score
Conciseness	The body is a lean checklist: each step states rules without explaining concepts Claude already knows (no 'what is ISO 3166' padding), and the output template is pure structure. Every token carries a constraint or instruction, matching the anchor-5 'lean and efficient; every token earns its place' example.	5 / 5
Actionability	Mostly concrete and executable: exact required-field lists per entity type, exact formats ('exactly 2 uppercase letters (ISO 3166-1 alpha-2)', '-90 and 90', 'Q followed by digits'), a 5km duplicate threshold, and a fill-in output template. Minor gaps keep it below anchor 5: Step 5 says 'Load the existing countries.json and states.json files' without paths, and Step 6's 'geographic bounds of the specified country' names no source for those bounds.	4 / 5
Workflow Clarity	Seven explicitly ordered steps with validation built in throughout: errors vs. warnings are distinguished ('flag as an error and instruct the contributor to remove them'; 'Report potential duplicates as warnings'), and the skill culminates in a PASS/FAIL checklist with an overall verdict — a feedback artifact for the contributor. This is a read-only validation skill, so the destructive/batch cap does not apply, and it matches the anchor-5 pattern of clear sequence, explicit checkpoints, and a checklist.	5 / 5
Progressive Disclosure	The intent is right — SKILL.md as a concise process overview pointing one level deep to 'schema-rules.md in this directory' for the authoritative field spec — but that file does not exist anywhere in the bundle (no references/, scripts/, or assets/ directories, and no schema-rules.md alongside SKILL.md). The clearly signaled reference is broken, so navigation actually fails; this sits between anchor 3 and 4, and the missing file is a real defect rather than a minor organization gap.	3 / 5
	Total	17 / 20 Passed

Description

86%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 with explicit what/when structure and unusually thorough natural trigger phrases. Its main weakness is modest capability breadth (a single 'validate' action) and a few over-broad trigger terms that could collide with general code-review skills.

Dimension	Reasoning	Score
Specificity	The description names the domain precisely ('Validate geographic data contributions against the CSC database schema') but lists only that single capability action; the remaining space is spent on triggers rather than enumerating what the validation actually covers (required fields, cross-referencing, duplicate detection). This matches anchor 3 ('names domain and 1-2 concrete actions, but not comprehensive') and falls short of anchor 4's 'several specific actions'.	3 / 5
Completeness	Explicitly answers both questions: 'what' via the opening capability statement and 'when' via 'Use this skill whenever you encounter a PR that adds, modifies, or deletes data in the contributions/ directory' plus quoted user trigger phrases. This mirrors the anchor-5 example structure almost exactly.	5 / 5
Trigger Term Quality	Comprehensive natural-language coverage including direct synonyms ('validate, check, review, verify, audit, inspect, assess') and verbatim user phrases ('is this correct', 'check my data', 'validate this', 'review my PR'), plus contextual keyword forms ('schema compliance checks', 'field validation'). Matches the anchor-5 example's breadth of synonyms and natural terms.	5 / 5
Distinctiveness Conflict Risk	The core niche is distinct (CSC schema, contributions/ directory, geographic data), but broad trigger phrases like 'review my PR', 'review', and 'is this correct' create minor overlap with general PR-review skills. Fits anchor 4 ('mostly distinct; minor overlap risk with closely related skills') rather than 5, whose niche triggers would not collide with adjacent skills.	4 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: dr5hn/countries-states-cities-database
Path: .github/skills/validate-contribution/SKILL.md
Commit: 66b45ee

Reviewed: 9 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.