external-resource-context

Records where resources outside the repository live (design source, design system, API schema, IaC source, secret store) and how design, implementation, and verification reach them. Use when work depends on an external resource, or when the user mentions design source, design system, API schema, IaC source, secret store, or canonical source.

Quality

81%

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

78%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, lean instruction skill: clear storage model, a concrete reference protocol with a fallback, and exemplary progressive disclosure with real, well-labeled reference files. The main limitation is that key workflow detail and validation are delegated to reference files rather than surfaced in the body.

Suggestions

Surface a brief validation/quality checkpoint inline in the Reference Protocol (e.g., 'confirm the recorded access method resolves before proceeding') rather than deferring all checks to hearing.md.

Tighten the Purpose and Resources paragraph — the enumerated resource list partially duplicates the description; consider moving the full enumeration to a reference and keeping the body to the access-method framing.

Add one short inline example of a feature-tier table row (label + feature-specific identifier) so the two-tier model is immediately actionable without opening template.md.

Dimension	Reasoning	Score
Conciseness	The body is efficient — compact tables for storage tiers, a short numbered reference protocol, and a tight references list — and assumes Claude's competence without explaining basic concepts. Not a 5 because the Purpose/Resources paragraph carries some framing that could be trimmed, but clearly above the 3 anchor's unnecessary explanation.	4 / 5
Actionability	Gives concrete, executable guidance: exact file path ('docs/project-context/external-resources.md'), fixed section names ('External Resources Used'), and a numbered read/use protocol. Not a 5 because the capturing workflow delegates substantial detail to reference files rather than stating it inline, but well above the 3 anchor.	4 / 5
Workflow Clarity	The Reference Protocol is a clear 3-step sequence with an explicit fallback ('When the file is absent or the resource is unreachable, continue from...evidence'), and the hearing workflow is routed to a conditions table in hearing.md. Not a 5 because validation/quality checkpoints live in the reference rather than the body, but clearly above the 3 anchor's implicit checkpoints.	4 / 5
Progressive Disclosure	SKILL.md is a concise overview that signals one-level-deep references inline and lists all six reference files (hearing, frontend, backend, api, infra, template) with descriptions in a References section; the referenced files are real and each covers a distinct domain. Matches the 5 anchor for clear overview with well-signaled one-level-deep references and easy navigation.	5 / 5
	Total	17 / 20 Passed

Description

83%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, well-constructed description: third-person voice, explicit what/when structure, and good concrete trigger terms anchored to specific resource types. Minor room to widen trigger synonyms and sharpen the action vocabulary.

Dimension	Reasoning	Score
Specificity	Names the external-resource domain and enumerates several concrete resource types (design source, design system, API schema, IaC source, secret store), with concrete actions ('Records where resources...live', 'how...reach them'), though the action vocabulary itself is limited to two verbs. Not a 5 because it does not list multiple distinct concrete actions, but clearly above the 3 anchor that names only 1-2 actions.	4 / 5
Completeness	Explicitly answers both 'what' ('Records where resources...live...and how design, implementation, and verification reach them') and 'when' ('Use when work depends on an external resource, or when the user mentions...'), with concrete trigger phrases, matching the 5 anchor exactly.	5 / 5
Trigger Term Quality	The 'Use when...the user mentions design source, design system, API schema, IaC source, secret store, or canonical source' clause provides good coverage of natural domain terms a user would say. Not a 5 because some specific synonyms/users' phrasings (e.g., Figma, OpenAPI, Terraform) are absent, but well above the 3 anchor's generic single-term coverage.	4 / 5
Distinctiveness Conflict Risk	The specific enumerated resource categories give it a clear niche with mostly distinct triggers and minimal conflict risk, but it could still overlap with general context-gathering skills. Not a 5 because the niche is somewhat broad ('external resource'), but clearly above the 3 anchor.	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: shinpr/claude-code-workflows
Path: dev-skills/skills/external-resource-context/SKILL.md
Commit: 9b7f687

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.