expert-panel

Score, evaluate, and iteratively improve any content or strategy using an auto-assembled panel of domain experts. Handles copy, sequences, landing pages, strategy docs, titles, charts, recruiting evaluations, or anything else that needs a quality gate. Recursively iterates until all scores hit 90+ (max 3 rounds). Use when asked to: "expert panel this", "score this", "rate these variants", "quality check this", "panel review", "which version is better", "expert score", "evaluate this copy/strategy/page", or when another skill needs a quality gate on its output. Also triggers on: "score this landing page", "expert panel these email variants", "rate this headline", "panel these charts".

Quality

86%

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

77%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 a clear, well-sequenced orchestrator with strong workflow checkpoints and concrete directives. Its main weakness is progressive disclosure: several referenced files do not exist in the bundle and the included scripts are not surfaced anywhere in the skill.

Suggestions

Reconcile the Reference Files table with the actual bundle: either add the missing experts/, scoring-rubrics/, and telemetry/ files or remove the references to them.

Surface the five scripts/ Python files (e.g., content-quality-gate.py, content-quality-scorer.py, content-transform.py) in the body or Reference Files table so they are discoverable and their purpose is stated.

Trim the redundant output-format blocks in Step 5 (e.g., the placeholder runner-up example) to tighten conciseness without losing the format definition.

Dimension	Reasoning	Score
Conciseness	Mostly directive and efficient ('Build a panel of 7-10 experts', 'Cap at 10 experts'), with minor padding in repeated output-format blocks and the placeholder runner-up example that could be trimmed.	4 / 5
Actionability	Concrete directives (panel size, 1.5x humanizer weighting, 90/100 target, max 3 rounds, explicit file pointers) give mostly executable guidance, with a minor gap in how the weighted aggregate is computed.	4 / 5
Workflow Clarity	A clear 7-step sequence with an explicit scoring feedback loop ('If aggregate < 90: revise -> next round', 'If aggregate >= 90: finalize', 'After 3 rounds: return best version') and explicit stop conditions.	5 / 5
Progressive Disclosure	The Reference Files table signals one-level-deep references well in intent, but the bundle does not match: referenced paths (experts/humanizer.md, scoring-rubrics/*.md, telemetry/) are absent, while five scripts/ files are never referenced.	3 / 5
	Total	16 / 20 Passed

Description

96%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 that crisply states capabilities, enumerates trigger phrases comprehensively, and answers both 'what' and 'when'. The only soft spot is the very broad scope language ('or anything else that needs a quality gate') which raises minor overlap risk.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('Score, evaluate, and iteratively improve', 'auto-assembled panel of domain experts', 'Recursively iterates until all scores hit 90+') and enumerates many content types, matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers both what ('Score, evaluate, and iteratively improve... Recursively iterates until all scores hit 90+') and when ('Use when asked to...', 'Also triggers on...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases with synonyms ('expert panel this', 'score this', 'rate these variants', 'which version is better', 'panel review') plus an explicit 'Also triggers on' list, matching the full-coverage anchor.	5 / 5
Distinctiveness Conflict Risk	The 'expert panel' framing and panel-specific triggers are mostly distinct, but the broad 'or anything else that needs a quality gate' scope creates minor overlap risk with other eval/content skills.	4 / 5
	Total	19 / 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: ericosiu/ai-marketing-skills
Path: content-ops/SKILL.md
Commit: 2eb0f34

Reviewed: 7 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.