dm-respond
Skill17 starsChanged 7 months agoMITView on GitHub
Draft DM responses to inbound messages with categorization and appropriate tone — sales, support, collaboration, spam — and escalation rules for the founder.
- Reads credentials
In this repository40 other files it gives its agents.
- ab-test-analyzeSkill
- metrics-trackSkill
- performance-reportSkill
- caption-draftSkill
- cta-craftSkill
- hook-writeSkill
- post-createSkill
- thread-createSkill
- apology-draftSkill
- crisis-respondSkill
- impersonator-monitorSkill
- comment-replySkill
- engagement-pollSkill
- influencer-outreachSkill
- mention-monitorSkill
- cadence-timingSkill
- content-calendarSkill
- presence-refreshSkill
- profile-auditSkill
- cross-post-adaptSkill
- draft-reviewSkill
- schedule-queueSkill
- thread-structureSkill
- blog-to-threadSkill
- newsletter-to-postsSkill
- podcast-to-clipsSkill
- competitor-content-auditSkill
- prospect-social-auditSkill
- social-profile-discoverSkill
- brand-voice-systemSkill
- content-pillarsSkill
- crm-social-bridgeSkill
- positioning-statementSkill
- news-responseSkill
- trending-briefingSkill
- trend-monitorSkill
- asset-formatSkill
- image-promptSkill
- meme-createSkill
- visual-planSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 36
All new DMs across platforms
- Distinctive: line 96
All new DMs are categorized
- Distinctive: line 111
Read each draft. Does it sound human?
≈ “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
DM Respond
Triage and draft responses to direct messages across platforms. DMs are high-trust interactions — a good DM response can convert a prospect or save a customer. A bad or ignored DM erodes that trust permanently.
Purpose
The DM inbox is where real relationships happen. But it's also where spam, support tickets, sales inquiries, and fan mail all pile up together. This skill separates them, prioritizes them, and drafts appropriate responses so nothing falls through the cracks.
When to Use
- Daily DM inbox check (all platforms)
- New inbound message needs categorization
- Founder overwhelmed by DM volume
- Sensitive DM (angry customer, legal concern) — needs escalation
Inputs Required
- All new DMs across platforms
- Brand voice guide (DM voice should feel like the founder typing)
- Escalation contacts (founder, support email)
Quick Reference
| Category | Priority | Response Time | Tone | Escalate? |
| Sales inquiry | High | Within 2 hours | Helpful, informative | Route if high-value prospect |
| Support / complaint | Critical | Within 1 hour | Empathetic, solution-focused | If technical or account-specific |
| Collaboration | Medium | Within 24 hours | Professional, open, qualifying | Route with summary |
| Spam / irrelevant | Low | Ignore or block | N/A | No |
| Personal / founder connection | Medium | Within 24 hours | Warm, personal | Forward to founder |
| Press / media | High | Within 4 hours | Professional, prepared | Immediate escalation |
Procedure
- Review new DMs across all platforms daily (ideally 2x/day during business hours).
- Categorize each message using the Quick Reference table.
- Draft the response:
- Sales: acknowledge their interest, provide helpful info, offer next step. Collect context for routing.
- Support: acknowledge frustration first (not solution). Apologize if appropriate. Ask clarifying questions. Escalate if needed.
- Collaboration: thank them, ask qualifying questions. Don't commit in first reply. Route with summary.
- Spam: do not engage. Block/report if aggressive.
- Personal: flag for founder to reply. If unclear, ask gentle qualifying question.
- Apply brand voice. DM voice should feel human, not templated. Not overly casual, not stiff.
- Track status: Replied / Escalated / Pending / Ignored.
Output Format
# DM Inbox: [Date]
## Message 1
**Platform:** [X / LinkedIn / IG / TikTok]
**From:** @handle
**Category:** [Sales / Support / Collaboration / Spam / Personal / Press]
**Priority:** [Critical / High / Medium / Low]
**Message:** "[Full DM text]"
**Response Draft:**
[Full response text]
**Action:** [Send / Escalate / Ignore]
**If escalated — founder summary:** [Who, what they want, your recommendation]
---
## Daily Summary
- Total new: [N] | Replied: [N] | Escalated: [N] | Pending: [N] | Ignored: [N]
- Avg response time: [N] hoursDone Criteria
The skill is complete when:
- All new DMs are categorized
- Sales/support/collaboration DMs have response drafts
- Spam is identified and marked (no response drafted)
- Escalated DMs have a founder summary
- Response time priority is met (critical < 1 hour)
Pitfalls
- Templated responses that feel automated
- Responding to troll or spam DMs
- Sending a link without context (spammy)
- Ignoring support DMs (fastest way to create a public complainer)
Verification
Read each draft. Does it sound human? Would the founder feel good about this being sent in their name? For escalated DMs, is the founder summary enough to reply without reading the full thread?
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.

