moody-s-rating-analysis

Produce a Rating Pitch Report for a company using Moody's GenAI MCP tools, delivered as a self-contained HTML file saved to disk. Use this skill whenever the user asks to create a rating pitch, rating pitch deck, credit pitch, rating presentation, rating pitch report, or rating HTML report. Also trigger when they ask for a comprehensive credit overview combining sector analysis, company financials, SWOT, peer comparison, and ESG into a single report or presentation. Trigger even if they just name a company and say "pitch deck", "rating deck", "credit deck", or "rating report".

Quality

82%

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

65%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A thorough, highly actionable skill body with concrete commands, a full payload schema, and strong output-contract enforcement. Its weaknesses are redundancy (several rules restated multiple times and a Tips section that echoes earlier steps), a missing validation gate on the batch data-gathering, and a referenced builder script that does not exist in the bundle.

Suggestions

Add an explicit payload-validation checkpoint before running build_html.py (e.g., 'verify every commentary field is a JSON array of strings and scorecard values rows have length len(companies)+1') so the batch peer-gathering step has a verification gate.

De-duplicate the scorecard companies/values[row][0] rule (currently in Step 3, the Payload schema, and Tips) and the oldest→newest chart-ordering rule into a single canonical statement.

Restore or remove the missing scripts/build_html.py reference — the 'Bundled files' section and Step 4 cite it, but it is not present in scripts/, so the one-level reference does not resolve.

Dimension	Reasoning	Score
Conciseness	The body is dense with skill-specific gotchas (the character-iteration commentary bug, scorecard 1-indexing trap, period-label anchoring) rather than basic-concept padding, but the scorecard companies/values[row][0] rule is restated three times, the oldest→newest chart rule twice, and the Tips section largely repeats Steps 2–4, so not every token earns its place.	2 / 3
Actionability	Provides copy-paste commands ('python3 …/build_html.py …', 'python3 --version', 'open …'), a complete JSON payload schema, and exact tool parameters including filterCriteria: {excludeInterimData: true} — fully executable guidance.	3 / 3
Workflow Clarity	A clear 4-step sequence (Resolve → parallel Gather → Synthesize → Build) with a scorecard pre-write checklist and partial-failure handling, but the batch parallel peer gathering has no per-batch validation gate and no payload-completeness verification before the build, so the batch-operation cap applies.	2 / 3
Progressive Disclosure	References are clearly signaled one level deep via the 'Bundled files' section, but a referenced bundle file (scripts/build_html.py) is absent from the scripts/ directory (only requirements.txt is present), and the full payload schema is a heavy inline block rather than split out.	2 / 3
	Total	9 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 high-quality description that concisely states the deliverable (a self-contained HTML rating pitch report via Moody's GenAI MCP tools) and enumerates a rich set of natural trigger phrases. It cleanly answers both 'what' and 'when' with minimal padding.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions and components — 'Produce a Rating Pitch Report… delivered as a self-contained HTML file… combining sector analysis, company financials, SWOT, peer comparison, and ESG' — matching the multiple-specific-actions anchor.	3 / 3
Completeness	Explicitly answers both what ('Produce a Rating Pitch Report… self-contained HTML file saved to disk') and when ('Use this skill whenever the user asks to create a rating pitch…'), with an explicit 'Use when' trigger clause.	3 / 3
Trigger Term Quality	Gives broad natural coverage users would actually say — 'rating pitch, rating pitch deck, credit pitch, rating presentation, rating pitch report', plus bare 'pitch deck', 'rating deck', 'credit deck', 'rating report'.	3 / 3
Distinctiveness Conflict Risk	The Moody's rating-pitch niche with terms like 'credit pitch' and 'rating deck' is clearly distinct and unlikely to trigger for the wrong skill.	3 / 3
	Total	12 / 12 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
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	15 / 16 Passed

Repository: openai/plugins
Path: plugins/moody-s/skills/moody-s-rating-analysis/SKILL.md
Commit: 11c74d6

Reviewed: 17 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.