sales-crm-selection
CRM comparison, selection, and migration strategy for startups — evaluates Attio, HubSpot, Salesforce, Folk, Pipedrive, Close, Zoho, and spreadsheets. Use when choosing a first CRM, deciding if you've outgrown spreadsheets, comparing CRMs for a small team, planning a CRM migration, figuring out when to upgrade from free tier, or evaluating whether you need Salesforce yet. Do NOT use for Attio-specific config or API (use /sales-attio), CRM data cleanup (use /sales-data-hygiene), or outbound sequences (use /sales-cadence).
What this skill does
# CRM Comparison & Selection for Startups
Help startups choose, evaluate, and migrate to the right CRM — from spreadsheets through Attio, HubSpot, Folk, Pipedrive, Close, Zoho, and Salesforce.
## Step 1 — Gather context
If `references/learnings.md` exists, read it first for accumulated knowledge.
Ask the user:
1. **What's your situation?**
- A) Choosing a first CRM (currently using spreadsheets or nothing)
- B) Evaluating CRMs — have a shortlist, need help deciding
- C) Outgrowing current CRM — considering a switch
- D) Migrating between CRMs — need a plan
- E) Deciding if I even need a CRM yet
- F) Other — describe it
2. **Team and stage?**
- A) Solo founder / 1-2 people
- B) Small team (3-10 people)
- C) Growth stage (10-50 people)
- D) Scaling (50+ people)
3. **Sales motion?**
- A) Inbound-led (marketing drives leads)
- B) Outbound-led (SDRs/founders do cold outreach)
- C) Product-led growth (self-serve signups)
- D) Hybrid / not sure yet
4. **Budget per user/month?**
- A) Free only
- B) Under $30/user/mo
- C) $30-$100/user/mo
- D) Enterprise budget ($100+/user/mo)
**Skip-ahead rule**: if the user's prompt already provides most context, skip to Step 2. Lead with your best-effort answer using reasonable assumptions (stated explicitly), then ask 1-2 critical clarifying questions.
## Step 2 — Route or answer directly
| Problem domain | Route to |
|---|---|
| Attio-specific setup, config, API, or troubleshooting | `/sales-attio {user's question}` |
| HubSpot-specific setup, config, workflows, API, or pricing | `/sales-hubspot {user's question}` |
| Salesforce-specific setup, Flows, Apex, admin, API, or editions | `/sales-salesforce {user's question}` |
| CRM data cleanup, deduplication, record matching | `/sales-data-hygiene {user's question}` |
| Building outbound sequences across platforms | `/sales-cadence {user's question}` |
| Contact enrichment for CRM records | `/sales-enrich {user's question}` |
| Connecting CRM to other tools | `/sales-integration {user's question}` |
When routing, provide the exact command.
## Step 3 — CRM comparison reference
**Read `references/platforms.md`** for the full CRM comparison — positioning, feature matrices, pricing guidance, decision frameworks, migration paths.
Answer the user's question using only the relevant section. Don't dump the full reference.
## Step 4 — Actionable guidance
You no longer need the comparison reference — focus on the user's specific situation.
### Quick decision framework
- **Solo founder, free, simple pipeline**: HubSpot Free or Attio Free
- **Small team (3-10), inbound-led, wants marketing+sales in one tool**: HubSpot
- **Small team, outbound-heavy, call-driven**: Close or Pipedrive
- **Small team, relationship-focused, lightweight outreach**: Folk
- **Startup wanting custom data model, API-first, modern UX**: Attio
- **Growth stage, needs marketing automation + CRM + service**: HubSpot (paid tiers)
- **Enterprise, complex org, dedicated admin available, 50+ reps**: Salesforce
- **Budget-conscious, need breadth of features**: Zoho CRM
### Spreadsheet-to-CRM transition signals
You need a CRM when any of these are true:
- More than 5 people touch customer data
- More than 50-100 active accounts
- Follow-ups are getting dropped
- No visibility into what others discussed with a prospect
- You're copy-pasting between sheets to get a pipeline view
Most startups switch 3-6 months after raising initial capital. Start with a free tier to build habits before paying.
### Migration checklist
1. **Export and audit** — clean data before importing (use `/sales-data-hygiene`)
2. **Map fields** — align old fields to new CRM's data model
3. **Test with a subset** — import 50-100 records first, verify
4. **Reconnect integrations** — email sync, calendar, Zapier/Make flows
5. **Train the team** — adoption beats features; schedule 1-hour walkthrough
6. **Run parallel for 2 weeks** — keep old system read-only as fallback
If you discover a gotcha, workaround, or tip not covered in `references/learnings.md`, append it there.
## Gotchas
> *Best-effort from research — review these, especially pricing which changes frequently.*
1. **70% of CRM implementations fail** — the #1 cause is unclear goals, not bad software. Define what you need before evaluating tools.
2. **HubSpot's free tier is genuinely useful, but the jump to paid is steep.** The free plan covers unlimited users and contacts. But the moment you need marketing automation, custom reporting, or sequences, you're looking at $45-$800+/mo depending on tier. Plan for this before you're locked in.
3. **"We'll need Salesforce eventually" is usually wrong for startups.** Most SaaS startups don't need Salesforce until past $5M ARR and 50+ employees. Starting on Salesforce too early means paying for admin overhead you can't afford and complexity you don't need.
4. **CRM data quality degrades ~30% per year.** People change jobs, emails bounce, companies rebrand. Budget for ongoing enrichment and cleanup regardless of which CRM you pick.
5. **Switching CRMs is painful but not as painful as staying on the wrong one.** The real cost isn't data migration — it's retraining workflows and losing historical context. Export notes and activity history, not just contact records.
## Before recommending a specific platform skill
This skill covers a strategy domain across many platforms. **Before pointing the user to any specific platform skill** (any `/sales-{platform}` listed in `## Related skills`, e.g., `/sales-mailshake`, `/sales-klaviyo`, `/sales-apollo`), read that platform skill's actual `SKILL.md` first. The 1-line description in `## Related skills` is enough to *identify* a candidate — it's not enough to *commit* to it or to write a prompt that invokes it well.
**How to read it:**
- If `~/.claude/skills/{skill-name}/SKILL.md` exists locally, `Read` it.
- For `sales-*` skills, `WebFetch` directly from this repo: `https://raw.githubusercontent.com/sales-skills/sales/main/skills/{skill-name}/SKILL.md` — e.g., for `sales-mailshake`: `https://raw.githubusercontent.com/sales-skills/sales/main/skills/sales-mailshake/SKILL.md`.
- For non-`sales-*` skills (third-party), look up `{org}/{repo}` in `~/.claude/skills/sales-do/references/skill-sources.md` if installed and fetch the same `skills/{skill-name}/SKILL.md` path under that repo.
**After reading,** ground your recommendation in something concrete from the SKILL.md (its scope, a sub-flow, its `argument-hint` shape, or a "Do NOT use for..." negative trigger). Align any generated invocation with the platform skill's `argument-hint`. If the platform skill turns out not to fit the user's situation, swap to another or handle the question here directly rather than recommending a poor fit.
## Related skills
- `/sales-hubspot` — HubSpot platform help — Smart CRM, Marketing/Sales/Service Hubs, workflows, sequences, API
- `/sales-salesforce` — Salesforce platform help — Sales/Service/Marketing Cloud, Flows, Apex, AppExchange, API
- `/sales-attio` — Attio platform help — custom objects, deal pipelines, automations, email sequences, AI, API
- `/sales-data-hygiene` — CRM data quality — deduplication, record matching, enrichment automation
- `/sales-enrich` — Contact enrichment — emails, phones, company data, bulk enrichment
- `/sales-cadence` — Outbound sequence design — multi-channel cadences across platforms
- `/sales-integration` — Connecting CRM to other tools — webhooks, Zapier, Make, native connectors
- `/sales-lead-score` — Lead scoring model design — dimensions, weights, MQL/SQL thresholds
- `/sales-lead-routing` — Lead routing and assignment — round-robin, territory, score-based
- `/sales-forecast` — Revenue forecasting — pipeline coverage, commit validation
- `/sales-do` — Not sure which skill to use? The router matches any sales objective to the right skill. Install: `npx skills add sales-skills/sales --skill sales-do`
## ExampleRelated in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.