blind-spot-review
Skill7 starsChanged 19 days agoMITView on GitHub
Pressure-test a draft for blind spots before pre-send review. Say "find blind spots", "what am I missing", or "review for risk". Runs nine fixed review categories covering evidence, risk, timing, relationships, data, upside, and walkaway planning. Read-only.
In this repository100 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- notion-package/CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- add-handsSkill
- add-mouthSkill
- add-voiceSkill
- approval-gatesSkill
- auditSkill
- backupSkill
- bottleneck-diagnosticSkill
- brain-logSkill
- brain-passSkill
- brain-snapshotSkill
- brand-interviewSkill
- brand-voice-interviewSkill
- business-context-loaderSkill
- campaign-from-themeSkill
- capture-sweepSkill
- catch-upSkill
- client-updateSkill
- connectSkill
- content-repurposerSkill
- content-startSkill
- context-persistenceSkill
- cross-linkSkill
- data-securitySkill
- decision-frameworkSkill
- decisions-startSkill
- delivery-startSkill
- email-drafterSkill
- employee-reviewSkill
- finance-importSkill
- forcing-questionsSkill
- founder-coachingSkill
- founder-next-moveSkill
- founder-os-setupSkill
- founder-reviewSkill
- founder-scope-challengeSkill
- github-opsSkill
- handoff-protocolSkill
- hireSkill
- historySkill
- housekeepingSkill
- ingestSkill
- knowledge-captureSkill
- legal-complianceSkill
- linkedin-brand-directionSkill
- linkedin-network-scanSkill
- linkedin-postSkill
- linkedin-power-auditSkill
- linkedin-startSkill
- linkedin-warm-revivalSkill
- lintSkill
- list-prunerSkill
- log-archiveSkill
- log-replySkill
- meeting-prepSkill
- memory-passSkill
- menuSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
12 rules. About 0 are common, 11 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈11
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 30
If any input is missing, stop and name the gap.
- Distinctive: line 38
Check ownership, licenses, registrations, names, contracts, claims, and any rights the deliverable assumes.
- Distinctive: line 42
Check pending proposals, signed contracts, vendor terms, partner terms, employment or contractor terms, and anything that changes if the …
- Distinctive: line 46
Check unpaid invoices, loans, deposits, deferred pay, refund exposure, or anyone who must be paid before value is split.
- Distinctive: line 50
Check audiences, email lists, CRM records, customer data, content libraries, social accounts, group chats, and consent boundaries.
- Distinctive: line 54
Check co-founders, team members, family, friends, partners, investors, and anyone whose position changes because of the recommendation.
- Distinctive: line 58
Check renewal dates, tax dates, filing deadlines, permit windows, launch dates, meeting dates, campaign timing, or any dated constraint.
- Distinctive: line 62
Check whether the other party has been prepared, whether a written pre-brief is needed, and what silence before the meeting may signal.
- Distinctive: line 66
Check what happens if the other party responds well, offers more than expected, or helps design the solution.
- Distinctive: line 70
Check what the founder or client does if the meeting fails, the deal stalls, or the recommendation is rejected.
- Very specific: line 101
If any category is marked GAP, the verdict is FIX THEN RE-REVIEW unless the founder explicitly accepts the risk.
- Distinctive: line 103
No em dashes, no en dashes, no banned words.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Blind-Spot Review
Runs on: reasoning - reads your files and reasons; any capable agent can run this.
The first draft of an advisory deliverable is rarely the safe final draft. This skill runs a second pass against nine fixed categories so the founder can decide what to add, what to accept, and what to leave out.
When To Run
- A proposal, brief, playbook, meeting-prep note, client update, or decision document has a complete first draft.
- The founder asks what is missing.
- A deliverable is about to run through
pre-send-check. - The stakes include external trust, legal exposure, financial terms, client expectations, or relationship damage.
Inputs Required
- Path to the deliverable.
- Source material used to create it: transcript, notes, client context, prior decision, or brief.
- The external party or audience.
- Intended send channel and date, if known.
If any input is missing, stop and name the gap. Do not review a deliverable without source context.
The Nine Categories
For each category, mark ADDRESSED, GAP, or NOT APPLICABLE with a one-line reason.
1. Legal and IP Status
Check ownership, licenses, registrations, names, contracts, claims, and any rights the deliverable assumes.
2. Contracts In Flight
Check pending proposals, signed contracts, vendor terms, partner terms, employment or contractor terms, and anything that changes if the advice is followed.
3. Creditor and Payment Positions
Check unpaid invoices, loans, deposits, deferred pay, refund exposure, or anyone who must be paid before value is split.
4. Community and Data Assets
Check audiences, email lists, CRM records, customer data, content libraries, social accounts, group chats, and consent boundaries.
5. Relationship Externalities
Check co-founders, team members, family, friends, partners, investors, and anyone whose position changes because of the recommendation.
6. Regulatory and Timing Issues
Check renewal dates, tax dates, filing deadlines, permit windows, launch dates, meeting dates, campaign timing, or any dated constraint.
7. Pre-Meeting Communication
Check whether the other party has been prepared, whether a written pre-brief is needed, and what silence before the meeting may signal.
8. Upside Scenarios
Check what happens if the other party responds well, offers more than expected, or helps design the solution. Good outcomes need a plan too.
9. Walkaway Plan
Check what the founder or client does if the meeting fails, the deal stalls, or the recommendation is rejected.
Output Format
# Blind-spot review on `<deliverable-name>` - <YYYY-MM-DD>
## Categories addressed
1. Legal and IP status: ADDRESSED / GAP / NOT APPLICABLE - <one-line specifics>
2. Contracts in flight: ADDRESSED / GAP / NOT APPLICABLE - <one-line specifics>
3. Creditor and payment positions: ADDRESSED / GAP / NOT APPLICABLE - <one-line specifics>
4. Community and data assets: ADDRESSED / GAP / NOT APPLICABLE - <one-line specifics>
5. Relationship externalities: ADDRESSED / GAP / NOT APPLICABLE - <one-line specifics>
6. Regulatory and timing issues: ADDRESSED / GAP / NOT APPLICABLE - <one-line specifics>
7. Pre-meeting communication: ADDRESSED / GAP / NOT APPLICABLE - <one-line specifics>
8. Upside scenarios: ADDRESSED / GAP / NOT APPLICABLE - <one-line specifics>
9. Walkaway plan: ADDRESSED / GAP / NOT APPLICABLE - <one-line specifics>
## Additions to fold back into the deliverable
- <specific change, with section or file location>
## Verdict
READY FOR pre-send-check | FIX THEN RE-REVIEWRules
- Review only. Do not edit the deliverable in this skill.
- If any category is marked GAP, the verdict is
FIX THEN RE-REVIEWunless the founder explicitly accepts the risk. - Name the highest-risk gap first if the user is under time pressure.
- No em dashes, no en dashes, no banned words.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

