bulk-qa-answers

Bulk Q&A Answers skill for Datasite deal rooms. Use this skill whenever a sell-side deal team wants to answer multiple buyer questions at once, generate AI draft responses from VDR content, produce a Q&A tracker spreadsheet, or build a Q&A management dashboard. Triggers include: "answer the Q&A", "draft responses to buyer questions", "process the question list", "generate Q&A tracker", "answer all questions", "bulk answer", "Q&A management dashboard", "respond to diligence questions", or any request to systematically work through a list of buyer questions using data room content as the source. Use this skill proactively whenever a buyer has submitted questions and the deal team wants AI-assisted drafting. Do not use for individual one-off questions outside a structured Q&A process. Do not draft answers from general knowledge — all responses must come from the data room.

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%

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

A well-structured, highly actionable multi-step workflow with strong sequencing and validation, held back by redundancy across the step guidance and operating/performance sections and by a missing referenced file. Tightening the repeated guidance and providing the dashboard-spec reference would lift the weaker dimensions.

Suggestions

Collapse Operating Principles and Performance Notes into Step 3 (or remove the lines that restate 3a/3e/3f) to remove redundancy and improve conciseness.

Create the referenced references/dashboard-spec.md file (or remove the 'Read references/dashboard-spec.md' instruction and the inline section summary) so progressive disclosure has a real, one-level-deep reference.

Move the detailed Excel formatting rules from Step 5b into a references file to keep SKILL.md an overview and improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and domain-specific, but Operating Principles and Performance Notes restate Step 3 guidance (e.g. 'Read the documents, don't just locate them' ≈ 3a, 'Source everything' ≈ 3f, 'Mark questions Open rather than guessing' ≈ 3e) and the Blueflame guard repeats in Common Issues, so not every token earns its place.	2 / 3
Actionability	Highly concrete for an instruction-only skill — named tools (searchDocuments, getProjectOverview, listFolderContents), the decompose:true parameter, an exact 6-column tracker spec with hex colors and widths, a file-name pattern, and citation examples like 'FY2024 Annual Report (VDR 3.1), p.14'.	3 / 3
Workflow Clarity	Steps 1–7 are clearly sequenced with sub-steps 3a–3f and explicit checkpoints (confirm column mappings, stop on activation-link gate, per-question status assignment, mark Open when no source), plus Common Issues error-recovery guidance including resuming from the last completed step.	3 / 3
Progressive Disclosure	No bundle files exist and the one referenced path (references/dashboard-spec.md) is missing, while detailed specs such as the Excel formatting rules and dashboard sections are inlined; section organization is good (not a 1) but a broken reference and unsplit detail fit the 'could be better organized' anchor.	2 / 3
	Total	10 / 12 Passed

Description

100%

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, specific description with explicit trigger guidance, natural keyword coverage, and clear negative scoping. Voice is third-person/imperative with no first- or second-person pronouns, so no voice penalty applies.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'answer multiple buyer questions at once, generate AI draft responses from VDR content, produce a Q&A tracker spreadsheet, or build a Q&A management dashboard' — matching the anchor for multiple specific concrete actions rather than a partial domain-only description.	3 / 3
Completeness	Explicitly answers both what (the four drafting/output actions) and when ('Use this skill whenever…', 'Triggers include: …', 'Use this skill proactively whenever…'), so the explicit-trigger requirement is met and completeness is not capped at 2.	3 / 3
Trigger Term Quality	Provides broad natural-language triggers users would actually say ('answer the Q&A', 'draft responses to buyer questions', 'process the question list', 'bulk answer', 'respond to diligence questions'), giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Occupies a tight niche (Datasite sell-side M&A Q&A from VDR content) with distinct triggers and explicit negative guidance ('Do not use for individual one-off questions', 'Do not draft answers from general knowledge'), making conflicts unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: openai/plugins
Path: plugins/datasite/skills/bulk-qa-answers/SKILL.md
Commit: 11c74d6

Reviewed: about 9 hours 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.