Form Radar
Skill8 starsChanged 5 months agoMITView on GitHub
Show where every form you sent stands — the sent → opened → completed funnel, who started but didn't finish (nudge them), who never opened it and is going stale (chase), and what completed this week. Hottest follow-ups first.
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
- 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 DocumentsSkill
- 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
Files
Form Radar
Owners send intake/onboarding forms and then don't notice the client who opened it, started, and bailed — or the one who never opened it at all. This is the check-up on every submission.
The buckets that matter:
- Started but not completed — opened or in-progress, never submitted. A short nudge usually finishes them.
- Sent but never opened, going stale — chase or resend.
Source of truth: knowledge/form-method.md
— §4 (the submission lifecycle) and §5 (automating it).
Step 1 — Fetch the digest
python ~/.claude/bos-run.py form-radarOne call: lists every submission, computes the funnel, buckets the follow-ups
(started-not-completed, sent-never-opened-stale, recently completed),
oldest-first. --stale-days N tunes the stale threshold (default 5).
Fallback if it can't run: mcp__trustpager__list_form_submissions — raw list,
no funnel; prefer the script.
Step 2 — Present, follow-ups first
📋 22 forms out — 12 completed, 4 started (not finished), 5 sent (unopened), 1 expired
✏️ STARTED — NOT FINISHED (4) ← a nudge usually closes these
→ "New Client Intake" — opened 3d ago, in progress. → nudge / draft a reminder
→ "Onboarding Questionnaire" — opened 6d ago, not submitted. → follow up
⏳ SENT — NEVER OPENED, going stale (5)
→ "Intake — Northside" — sent 8d ago, never opened. → resend or call
✅ Completed this week: 12 (PDFs auto-archived to their opportunities)Step 3 — Offer the follow-up actions (with approval)
One at a time, with a yes:
- Resend an unopened-stale submission →
mcp__trustpager__resend_form_submission(submission_id). - Draft a nudge to a started-not-finished recipient → hand to
/draft-reply("saw you got started on the form — anything I can help with to finish it?"). - Void a dead/duplicate submission →
void_form_submission(submission_id)— name it, get a yes.
For "nudge automatically whenever someone opens but doesn't finish", hand to
/automate-this on the form_opened trigger.
What to never do
- ❌ Don't dump all submissions flat — bucket by follow-up urgency.
- ❌ Don't auto-resend or auto-void — offer, get a yes, one at a time.
- ❌ Don't chase
completedones — count them, move on. - ❌ Don't chase a submission the operator voided on purpose.
Output shape
Headline funnel tally, then STARTED-NOT-FINISHED, then SENT-UNOPENED-STALE, then the completed count — and the single most valuable follow-up 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.

