custom-index-eval

Evaluates Fusion MCP search quality against eval/index domain files. USE FOR: eval core, eval all, validate MCP index recall, check search freshness, verify documented framework patterns. DO NOT USE FOR: authoring eval patterns, editing docs, CI automation, or application-development search answers.

Quality

85%

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

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 concise, actionable, and clearly sequenced with sensible verification for a read-only evaluation task. Its main weakness is that the referenced 'agents/query-judge.md' sub-agent file is not present in the bundle, though an inline fallback is provided.

Suggestions

Add an 'agents/query-judge.md' file to the bundle (or restructure so the judging rubric lives in a real reference file) so the 'Prefer the agents/query-judge.md sub-agent' instruction points to an existing artifact.

Make the per-query verification checkpoint explicit in the Workflow (e.g., a 'Validate: confirm each verdict maps to a must/should bullet before reporting' step) to push workflow clarity toward 5.

Optionally include one concrete MCP call example (tool name + example query argument) to move actionability from mostly-executable to copy-paste-ready.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-organized with no concept explanations Claude already knows (no 'what is MCP' padding); every section earns its place, matching the 5 'lean and efficient' anchor.	5 / 5
Actionability	Provides concrete executable guidance — file-path mapping ('eval/index/<domain>.md'), named MCP tools ('mcp_fusion_search_framework', 'mcp_fusion_search'), and defined verdict vocabulary — but as an instruction-only skill it lacks copy-paste-ready code, so it is mostly rather than fully executable per the 4 anchor.	4 / 5
Workflow Clarity	A clear four-step sequence (resolve, parse, judge, report) with embedded verification (pass/partial/fail verdicts, must/should satisfaction counts, and an explicit 'Stop clearly if MCP is unavailable or rate-limited' checkpoint); the operation is read-only and non-destructive, so the batch-validation cap does not apply, but a couple of validation checkpoints are implicit rather than explicit, fitting 4 over 5.	4 / 5
Progressive Disclosure	Well-organized sections with one-level-deep, clearly signaled references to 'assets/report-template.md' (which exists in the bundle) and 'agents/query-judge.md' (absent, but with an inline fallback), so structure is good with minor organization gaps, matching 4 over the cleanly-split 5.	4 / 5
	Total	17 / 20 Passed

Description

87%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 is strong: it states a concrete capability, provides explicit USE-FOR trigger phrases, and adds a DO-NOT-USE-FOR boundary clause that sharply reduces conflict risk. Minor gaps in trigger-term synonyms keep specificity and trigger quality at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Names the domain ('Evaluates Fusion MCP search quality against eval/index domain files') and lists several concrete actions — 'eval core', 'eval all', 'validate MCP index recall', 'check search freshness', 'verify documented framework patterns' — with only minor coverage gaps, fitting the 4 anchor better than the comprehensive 5.	4 / 5
Completeness	Clearly answers 'what' ('Evaluates Fusion MCP search quality against eval/index domain files') and 'when' via an explicit 'USE FOR:' clause with concrete trigger phrases, matching the 5 anchor exactly; not the 4 anchor because both halves are explicit and concrete.	5 / 5
Trigger Term Quality	Explicit natural triggers users would say ('eval core', 'eval all', 'validate MCP index recall', 'check search freshness') give good keyword coverage, but a few common synonyms/variations are missing, so it sits below the comprehensive 5 anchor.	4 / 5
Distinctiveness Conflict Risk	A clear niche (Fusion MCP search-index evaluation) plus an explicit 'DO NOT USE FOR' boundary clause (authoring eval patterns, editing docs, CI automation, application-development search) minimizes conflict risk, matching the 5 anchor.	5 / 5
	Total	18 / 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
metadata_field	'metadata' should map string keys to string values	Warning

	Total	15 / 16 Passed

Repository: equinor/fusion-framework
Path: .agents/skills/custom-index-eval/SKILL.md
Commit: 5b70066

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.