tear-sheet

Generate professional company tear sheets using S&P Capital IQ data via the Kensho LLM-ready API MCP server. Use this skill whenever the user asks for a tear sheet, company one-pager, company profile, fact sheet, company snapshot, or company overview document — especially when they mention a specific company name or ticker. Also trigger when users ask for equity research summaries, M&A company profiles, corporate development target profiles, sales/BD meeting prep documents, or any concise single-company financial summary. This skill supports four audience types: equity research, investment banking/M&A, corporate development, and sales/business development. If the user doesn't specify an audience, ask. Works for both public and private companies.

Quality

96%

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

92%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 high-quality, highly actionable skill body with executable code, a well-sequenced workflow, and strong validation/feedback loops for a data-heavy generation task. The only weakness is mild verbosity from the Style Configuration prose duplicating the enforced Component Functions.

Suggestions

Tighten or condense the Style Configuration prose now that the Component Functions enforce the same rules; keep only what the functions do not already encode (e.g. per-template overrides and audience-specific header field lists).

Trim editorializing assertions like 'the single most important visual signal' and 'Quiet math errors destroy credibility' — the surrounding mandatory rules already convey the intent.

Consider moving the ~230-line Component Functions JS block into a bundled scripts/ file referenced from the body, reducing SKILL.md token load while preserving the copy-into-generated-script mandate.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence (exact docx-js APIs, DXA values, color constants), but the Style Configuration prose partially duplicates what the Component Functions already enforce, and a few editorializing lines ('the single most important visual signal') could be trimmed. Not a 5 because of this light duplication and padding.	4 / 5
Actionability	Fully copy-paste-ready: complete docx-js component functions (createHeaderBanner, createSectionHeader, createTable, createBulletList, createFooter), exact bash commands, CSV schemas with columns, and worked example rows — covering the common generation cases.	5 / 5
Workflow Clarity	Clear numbered sequence (Steps 1 → 3c → 4) with explicit validation checkpoints and a feedback loop in Step 3b ('If a validation fails: attempt recalculation... If still inconsistent, flag the metric as N/A') plus a Step 3c verification summary that surfaces missing files before generation.	5 / 5
Progressive Disclosure	SKILL.md is an overview with one-level-deep references to real, present files (references/equity-research.md, ib-ma.md, corp-dev.md, sales-bd.md) mapped clearly per audience, and an external docx reference; audience-specific detail is appropriately split out with easy navigation.	5 / 5
	Total	19 / 20 Passed

Description

100%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.

An exemplary description: third person, concise yet comprehensive, with concrete capabilities, natural trigger synonyms, and explicit when-to-use guidance. Both the 'what' and 'when' are unambiguously stated.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'Generate professional company tear sheets', 'supports four audience types: equity research, investment banking/M&A, corporate development, and sales/business development', and 'Works for both public and private companies' — covering the capability space comprehensively.	5 / 5
Completeness	Explicitly answers both what ('Generate professional company tear sheets using S&P Capital IQ data via the Kensho LLM-ready API MCP server') and when ('Use this skill whenever the user asks for...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage with synonyms — 'tear sheet, company one-pager, company profile, fact sheet, company snapshot, or company overview document' — plus audience-specific phrases and the 'specific company name or ticker' cue users would actually say.	5 / 5
Distinctiveness Conflict Risk	Clear niche (single-company tear sheets) with distinct, specific trigger phrases unlikely to fire for unrelated skills; minimal conflict risk.	5 / 5
	Total	20 / 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
skill_md_line_count	SKILL.md is long (522 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: anthropics/financial-services
Path: plugins/partner-built/spglobal/skills/tear-sheet/SKILL.md
Commit: 69cbc81

Reviewed: 8 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.