gap-analysis

Data Room Gap Analysis skill for Datasite deal rooms. Use this skill whenever a sell-side deal team wants to audit what is missing, sparse, or incomplete in their data room before going live to buyers. Triggers include: "run a gap analysis", "what's missing from the data room", "check the data room coverage", "flag empty folders", "what haven't we uploaded yet", "data room readiness check", "find gaps before we go live", "are all the contracts in there", "check we have everything", or any request to assess completeness of the data room by section. Use this skill proactively whenever a deal team is preparing to launch a data room and wants to know what still needs to be uploaded or organised. Do not use for document quality issues such as PII or redaction (use document-quality-check), or for drafting Q&A responses (use bulk-qa-answers).

Quality

88%

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

77%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 workflow skill with a clear step sequence and explicit validation gates, weakened only by length and the absence of any progressive disclosure — everything lives in one large file with no reference bundle. Tightening redundant 'be specific' guidance and splitting the dashboard/section-expectation detail into reference files would lift both low dimensions.

Suggestions

Remove the duplicated 'be specific' guidance — keep it in Operating Principles and drop the overlapping Performance Notes bullet, or vice versa, to tighten conciseness.

Extract the Step 8b HTML dashboard / Excel export spec into a reference file (e.g. references/dashboard-template.md) and link to it one level deep, keeping SKILL.md as an overview, to improve progressive disclosure.

Move the 'Expected sections by deal type' and 'What counts as sparse' tables into a references/deal-expectations.md file referenced from Step 3, reducing inline bulk while preserving the actionable detail.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and the domain specifics (expected sections by deal type, sparse thresholds) earn their place, but the ~325-line body repeats guidance — 'Be specific, not vague' appears in both Operating Principles and Performance Notes — and the verbose Step 8b dashboard spec could be tightened, so it is not fully lean.	2 / 3
Actionability	Gives concrete, executable guidance throughout: named MCP calls with exact parameters ('listFolderContents' depth: 5, foldersOnly: true), example search queries ('customer list', 'client list'), precise status/severity definitions, and a fully specified Excel column layout and HTML dashboard structure — copy-paste ready for an instruction-only skill.	3 / 3
Workflow Clarity	A clearly sequenced 9-step process with explicit gating checkpoints — Step 5's Blueflame activation gate ('Do not generate the HTML dashboard or Excel output until after the user responds') and Step 8's output-offer gate — plus a Common Issues section providing error-recovery feedback loops for tool failures and MCP disconnects.	3 / 3
Progressive Disclosure	Well organized into labeled sections but monolithic: no bundle files exist in references/scripts/assets, and sizable self-contained specs (the Step 8b HTML/Excel template, expected-sections-by-deal-type tables) sit inline where one-level-deep reference files would reduce SKILL.md's weight, so it stops short of the 'clear overview with well-signaled references' anchor.	2 / 3
	Total	10 / 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 strong description: domain-specific, concrete in its actions, rich in natural trigger phrasings, and explicit about both when to use and when not to use it. Voice is third-person/imperative ('Use this skill whenever...'), consistent with the good examples rather than the penalized 'You can use this' phrasing.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'audit what is missing, sparse, or incomplete in their data room', 'flag empty folders', 'check the data room coverage', 'assess completeness of the data room by section' — rather than vague language, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what (audit missing/sparse/incomplete data room content) and when ('Use this skill whenever a sell-side deal team wants to audit... before going live to buyers', plus an explicit trigger list and a 'Use this skill proactively' clause), with the 'Do not use for...' anti-triggers adding clarity.	3 / 3
Trigger Term Quality	Provides extensive natural phrasings a deal-team user would actually say — 'run a gap analysis', "what's missing from the data room", 'flag empty folders', 'data room readiness check', 'find gaps before we go live', 'are all the contracts in there' — giving strong coverage of natural terms.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (Datasite sell-side data room gap analysis) with distinct triggers, and explicitly disambiguates from adjacent skills via 'Do not use for document quality issues such as PII or redaction (use document-quality-check), or for drafting Q&A responses (use bulk-qa-answers)', making wrong-skill triggering unlikely.	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
metadata_field	'metadata' should map string keys to string values	Warning

	Total	15 / 16 Passed

Repository: openai/plugins
Path: plugins/datasite/skills/gap-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.