deal-desk-create-plugin
Skill1 starsChanged 6 months agoMITView on GitHub
Design DealDesk integrations and workflow extensions for PE sourcing, diligence, contact enrichment, intermediary coverage, and reporting. Use when connecting external data sources, adding DealDesk tools, or shaping a plugin that improves acquisition-target workflow.
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- design-guideSkill
- deal-desk-converting-plans-to-tasksSkill
- deal-desk-create-agentSkill
- deal-desk-devSkill
- deal-desk-outreachSkill
- deal-deskSkill
- diagnose-why-work-stoppedSkill
- para-memory-filesSkill
- terminal-bench-loopSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. About 0 are common, 13 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈13
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 15
Use this skill when the user asks to add a DealDesk tool, data integration, workflow extension, or plugin-like capability.
- Distinctive: line 30
Avoid building a plugin when a small DealDesk route, seed, field, or UI addition solves the job.
- Distinctive: line 59
Never store raw secrets in DealDesk records.
- Distinctive: line 60
Do not send outreach automatically without explicit authorization.
- Distinctive: line 62
Keep confidence separate from facts.
- Distinctive: line 63
Prefer staged/draft outputs for anything partner- or counterparty-facing.
- Distinctive: line 69
Add or update the server route under the DealDesk API.
- Distinctive: line 70
Add validation and company scoping.
- Distinctive: line 71
Update the DB schema/migration if new persisted fields are needed.
- Distinctive: line 72
Add UI affordances only where operators need to inspect or approve the output.
- Distinctive: line 73
Add tests around company boundaries, dedupe, and error states.
- Distinctive: line 77
Keep the integration package isolated.
- Distinctive: line 81
Verify install, runtime execution, and reload behavior.
≈ “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
DealDesk Integration Skill
Use this skill when the user asks to add a DealDesk tool, data integration, workflow extension, or plugin-like capability.
The focus is PE workflow value, not generic platform extension. Every integration should improve sourcing, diligence, contact quality, intermediary coverage, or partner reporting.
Good Integration Candidates
- Company data providers.
- Contact enrichment sources.
- LinkedIn or web research workflows.
- CRM imports/exports.
- Outreach draft repositories.
- Intermediary/deal database connectors.
- Data-room or diligence document summarizers.
- Portfolio or thesis reporting exports.
Avoid building a plugin when a small DealDesk route, seed, field, or UI addition solves the job.
Discovery Questions
Answer these before proposing implementation:
- Which DealDesk object is affected: thesis, target, contact, intermediary, outreach draft, or report?
- Is the integration read-only, draft-only, or allowed to mutate records?
- What external credentials or secrets are required?
- What is the dedupe key?
- What provenance must be stored?
- What approval boundary applies?
- What failure state should the user see?
Integration Contract
Any new DealDesk integration should define:
- Input schema.
- Output schema.
- Record mapping.
- Source/citation behavior.
- Idempotency and dedupe behavior.
- Permission and approval boundary.
- Logging or audit trail.
- Retry/failure behavior.
Data Safety
- Never store raw secrets in DealDesk records.
- Do not send outreach automatically without explicit authorization.
- Tag imported or enriched data with its source.
- Keep confidence separate from facts.
- Prefer staged/draft outputs for anything partner- or counterparty-facing.
Implementation Guidance
For a small in-app workflow:
- Add or update the server route under the DealDesk API.
- Add validation and company scoping.
- Update the DB schema/migration if new persisted fields are needed.
- Add UI affordances only where operators need to inspect or approve the output.
- Add tests around company boundaries, dedupe, and error states.
For a true plugin-style integration:
- Keep the integration package isolated.
- Declare only the capabilities required.
- Keep UI self-contained.
- Store credentials through the app’s secret/config mechanism.
- Verify install, runtime execution, and reload behavior.
Done Criteria
The integration is ready when:
- It improves a specific DealDesk workflow.
- It writes structured records or draft outputs, not just prose.
- It can be re-run without duplicate records.
- It exposes source provenance.
- It fails visibly and recoverably.
- It respects company boundaries and approval requirements.
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.

