Outstanding Documents
Skill8 starsChanged 5 months agoMITView on GitHub
Per client, what supporting documents you asked for versus what's actually arrived, so you chase exactly the right thing. Reads the file-upload fields on the forms you sent plus the files on the record, builds a received/missing checklist per client, and ranks the chase by how overdue. Document-level; /form-radar is form-level.
In this repository101 other files it gives its agents.
- templates/CLAUDE.mdCLAUDE.md
- Add a FieldSkill
- Assemble Content PackSkill
- Assemble PackSkill
- Audit My AutomationsSkill
- Audit My DataSkill
- automate-thisSkill
- Brand My WorkspaceSkill
- Break Down A ChannelSkill
- Build Brand StrategySkill
- Build Customer VoiceSkill
- Build DocumentSkill
- Build FormSkill
- Build Knowledge Base From DocsSkill
- Build My ProofSkill
- Build My VoiceSkill
- Build Social StrategySkill
- Build SpreadsheetSkill
- Build Work Order ProcessSkill
- Cash Flow ForecastSkill
- Coach My CallsSkill
- Compare DocumentsSkill
- Connect A ToolSkill
- Delegate This WorkSkill
- Describe A ProductSkill
- Design My ScenesSkill
- Design Nurture SequenceSkill
- draft-replySkill
- Email Me A ReportSkill
- Estimate My BASSkill
- Extract DocumentSkill
- Find My Next MoveSkill
- Five Day ChallengeSkill
- Follow-up RadarSkill
- Form RadarSkill
- Get Found OnlineSkill
- Grill Me On This DecisionSkill
- import-from-anywhereSkill
- lead-triageSkill
- Learn My BusinessSkill
- Lint DocumentSkill
- Lint FormSkill
- Lint Nurture SequenceSkill
- log-this-callSkill
- make-it-happenSkill
- Make My VideoSkill
- Make Product DemoSkill
- Make Social PostSkill
- Make ThumbnailSkill
- missed-call-recoverySkill
- Nurture HealthSkill
- Onboard Team MemberSkill
- Outstanding InvoicesSkill
- Package My VideoSkill
- Plan My AdsSkill
- Plan My ContentSkill
- Plan My RoadmapSkill
- Plan My YouTubeSkill
- Prep For CallSkill
- Price My WorkSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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
- Very specific: line 85
Resend the form: if the request went via a form → resend_form_submission(submission_id).
≈ “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
Outstanding Documents
A broker (or anyone collecting supporting docs — insurance, legal, accounting) loses deals to the two payslips that never arrived. This is the document-level check-up: for each client, what did we ask for, what's in, and what's still missing — so the chase names the exact document, not "your form's incomplete".
How this differs from /form-radar: form-radar tracks the form's submission
status (sent → opened → completed). This tracks the documents themselves — the
individual file-upload requests inside those forms plus what's been uploaded to
the record — so a "completed" form can still have a missing document, and a
client with no form can still owe docs.
Step 1 — Scope it
One opportunity (ask which) or all active opportunities. For "all", keep it to opportunities in stages where documents are being collected — don't scan won/lost.
Step 2 — Work out requested vs received, per client
For each opportunity:
Requested — the documents we asked this client for:
- The file-upload fields on the forms we sent them.
list_form_submissions(?deal_id=)to find their forms, thenget_form_submission(submission_id)to read each field; a file-upload field with no file is a document still outstanding. Confirm the field shape withdescribe_resource("form")if unsure how an empty file field reads. - Plus any document checklist the operator keeps on the record (a notepad, a custom field). If no requirement is recorded anywhere, say so for that client rather than guessing what they "should" have sent.
Received — what's actually arrived:
list_opportunity_files(deal_id)— uploaded documents and files on the record (portal uploads land here).- File-upload fields that now hold a file.
Match received against requested by what the document is (payslip, ID, rates notice), not by exact filename.
Step 3 — Present, chase-first
Per client, a tight checklist; clients with the most-overdue missing docs at the top:
📄 Outstanding documents — 4 clients still owe you something
🔴 Smith refinance — asked 6d ago
✓ Driver licence ✓ Rates notice
✗ Payslip (2 of 2) ✗ Bank statements
→ chase: draft a reminder / resend the form
🟠 Nguyen purchase — asked 3d ago
✓ Application form
✗ Deposit evidence
→ chase
✅ Fully supplied this week: 3 (no action)Step 4 — Offer the chase (with approval)
One client at a time, with a yes:
- Draft a reminder naming the exact missing docs → hand to
/draft-reply("just chasing your last 2 payslips and bank statements to keep things moving"). - Resend the form if the request went via a form →
resend_form_submission(submission_id). - For "remind clients automatically when a doc is still missing after N days",
hand to
/automate-this.
Hard rules
- ❌ Never auto-send a chase — offer, get a yes, one client at a time.
- ❌ Don't guess a document is required when no requirement is recorded — say "no checklist on this one" and move on.
- ❌ Don't list clients who've supplied everything — count them, don't chase them.
- ❌ Don't confuse this with form completion — a completed form can still have a missing document.
- ✅ Name the exact missing documents in every chase, never "your form's incomplete".
Output shape
A per-client ✓ received / ✗ missing checklist, ordered most-overdue first, then the count of fully-supplied clients, and the single most valuable chase to make first.
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.

