mcpbeat Sign in

CRM Cleanup Skill for Claude

Scans HubSpot for stale deals, duplicate contacts, and missing fields, then fixes what the owner approves. Accepts optional scope argument for deals, contacts, or all.

672 tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
23273
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/anthropics/knowledge-work-plugins --skill crm-cleanup

What it tells the agent to use

found in the instruction text
WebFetch fetches pages from the network

The instruction itself

7 sections, as written by the author

Run a HubSpot hygiene pass using the crm-maintenance skill cleanup workflow. Act immediately — the user typed /crm-cleanup, so skip the intent-detection step.

Parse arguments:

  • --scope (default: all) — deals for deal audit only, contacts for contact dedup only, all for both

Step 1 — Scan for stale deals

If scope includes deals:

  • Pull all open deals from HubSpot.
  • Flag deals with no activity (email, call, meeting, note) in the last 14 days.
  • For each stale deal: show deal name, stage, last activity date, associated contacts, and amount.
  • Propose actions per deal: update next-step, change stage, add a note, or close-lost.

Present the full stale-deals list before making any changes.

Step 2 — Scan for duplicate contacts

If scope includes contacts:

  • Search HubSpot contacts for likely duplicates (same email, similar names, same company + similar name).
  • For each duplicate set: show both records side-by-side — name, email, company, deals, last activity.
  • Propose which record to keep and which fields to merge.

Present all duplicate sets before merging anything.

Step 3 — Scan for missing required fields

  • Check all open deals for missing fields: close date, amount, deal stage, associated contact, next-step/notes.
  • Check contacts associated with open deals for missing fields: email, company, phone.
  • Present a table of records with missing fields and what's missing.

Step 4 — Apply approved fixes

  • Walk through each finding from Steps 1-3.
  • Apply only the changes the owner explicitly approves.
  • Report each change as it's made with a HubSpot link.

Connector failures

If HubSpot is unreachable, stop — this command requires HubSpot as the data source. Tell the owner: "HubSpot isn't connected. Connect it in Cowork settings, then rerun /crm-cleanup."

Approval gates

  • Never delete records. Not contacts, not deals, not activities. If the user asks, say the skill cannot and direct them to HubSpot.
  • Never change deal stage or close a deal without explicit approval. Even if evidence is strong. Flag and defer.
  • Never auto-merge duplicate contacts. Show side-by-side and wait for approval per pair.
  • Side-by-side diffs for all changes. Show current value and proposed value; wait for approval per item.

Output

End with a summary: X deals updated, Y contacts merged, Z fields filled. Include links to the affected records.

Other skills for the same job

different authors, same section of the catalogue
Protocolsio Integration
by christophacham
×4

Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.

16k tokens
Tailored Resume Generator
by frostant
×4

Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances

3k tokens
Excalidraw Diagram Generator
by github
vendor ×3

Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.

36k tokens scripts
Expo Dev Client
by openai
vendor ×3

Build and distribute Expo development clients locally or via TestFlight

961 tokens
Executing Plans
by ZhanlinCui
×3

Use when you have a written implementation plan to execute in a separate session with review checkpoints

542 tokens
Anndata
by christophacham
×3

Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.

16k tokens
Benchling Integration
by christophacham
×3

Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.

14k tokens
Biopython
by christophacham
×3

Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.

24k tokens

How to use it

Copy the folder

Take anthropics/crm-cleanup from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.