irl-tracker

Information Request List (IRL) Tracker skill for Datasite deal rooms. Use this skill whenever a deal team wants to compare VDR content against a buyer's information request list, track document delivery status, or build a due diligence tracker dashboard. Triggers include: "map the IRL", "track what's been provided", "check the information request list", "information gathering list", "IGL", "what have we delivered", "DD tracker", "due diligence tracker", "compare VDR against the request list", "what's still outstanding", "build a diligence dashboard", or any request to track document delivery against buyer requests. Use proactively whenever a buyer has submitted a request list and the deal team needs to manage and track responses. Do not use for overall data room structural gap analysis — use gap-analysis for that.

Quality

88%

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 1-3

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

The body is highly actionable and the multi-step workflow is clearly sequenced with error-recovery feedback loops. The main weaknesses are conciseness (a redundant Performance Notes section) and progressive disclosure (a large dashboard spec kept inline that could be a referenced file). Splitting the dashboard spec into a reference and removing the duplicate notes would lift both.

Suggestions

Move the detailed dashboard specification (Views 1–7, CSV/PDF export) into a separate reference file such as DASHBOARD_SPEC.md and link to it from Step 5, so the always-needed matching workflow stays lean and the build spec loads only once the user confirms.

Delete the "Performance Notes" section — it restates "Content beats filename" and "AI matches are provisional" already covered in "Operating principles" and adds no new information.

Compress each dashboard view description into a compact spec (fields, columns, colors) rather than prose paragraphs to reduce token cost while preserving the actionable detail.

Dimension	Reasoning	Score
Conciseness	Mostly domain-specific and actionable with no basic-concept padding, but "Performance Notes" duplicates "Operating principles" ("Content beats filename", "AI matches are provisional") and the ~100-line inline dashboard spec inflates the file, so it could be tightened — matching the score-2 rather than the lean score-3 anchor.	2 / 3
Actionability	Provides copy-paste-ready guidance: concrete MCP calls with parameters (listFolderContents depth: 5, foldersOnly: false; searchDocuments decompose: true), a full JSON row schema, exact CSV columns, a filename pattern, and print CSS — matching the score-3 anchor for fully executable, specific instructions.	3 / 3
Workflow Clarity	Clear Step 1→6 sequence with sub-steps 3a–3f, a user-confirmation gate before dashboard build, an explicit Blueflame activation-link feedback loop, and a Common Issues error-recovery section — matching the score-3 anchor for explicit checkpoints and feedback loops.	3 / 3
Progressive Disclosure	No bundle files exist and the ~330-line skill is a well-sectioned monolith, but the dashboard build spec (Views 1–7, exports) needed only at Step 5 is inline rather than split into a one-level-deep reference, matching the score-2 anchor for content that should be separate being inline.	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: specific actions, extensive natural trigger terms, and explicit what/when guidance. The negative-trigger clause directing structural gap analysis elsewhere gives it excellent distinctiveness. No changes needed.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "compare VDR content against a buyer's information request list, track document delivery status, or build a due diligence tracker dashboard" — matching the score-3 anchor for listing several specific concrete actions.	3 / 3
Completeness	Explicitly answers both what (compare/track/build dashboard) and when ("Use this skill whenever a deal team wants...", a long trigger list, plus proactive-use guidance), matching the score-3 anchor; the when is stated, not merely implied.	3 / 3
Trigger Term Quality	Broad coverage of natural phrases a deal team would say ("map the IRL", "DD tracker", "due diligence tracker", "what's still outstanding", "build a diligence dashboard", "IGL"), matching the score-3 anchor rather than the partial coverage of a 2.	3 / 3
Distinctiveness Conflict Risk	Has a clear Datasite IRL/DD-tracking niche with distinct triggers and explicit conflict avoidance ("Do not use for overall data room structural gap analysis — use gap-analysis for that"), matching the score-3 anchor for a clear niche unlikely to conflict.	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/irl-tracker/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.