Sales · head-to-head
sales-plugin vs gtm-skills
Install sales-plugin if you want the daily loop and nothing to evaluate: nine skills for account research, outreach drafts, call prep and summaries, pipeline review, forecasting and competitive intel, published by Anthropic under Apache-2.0 and wired to HubSpot, Close, Clay, ZoomInfo and Fireflies connectors if you have them. Install gtm-skills when the question is how to run a motion you have not run before — ABM tiering, a win-loss programme, waterfall enrichment, product-led growth — and you want the named framework and an output checker rather than an improvised answer. The trade is real: one is official and narrow, the other is 211 skills published by a B2B data vendor that ranks itself first in its own provider tables.
Pick sales-plugin
You are an AE or founder running a pipeline now and want research, drafts, call prep and forecasting without evaluating anything.
Pick gtm-skills
You need the actual procedure for a motion your team has not run before, and you can read a vendor’s rankings critically.
Side by side
How they differ
| sales-plugin | gtm-skills | |
|---|---|---|
| Skills | 9, one motion end to end | 211 across 25 categories |
| Provenance | Official (Anthropic) | Verified org (LeadMagic, a B2B data vendor) |
| Licence | Apache-2.0 | MIT |
| Vendor neutrality | Connector-agnostic | Ranks its own product first in its provider tables |
| Ships an output checker | No | Yes — every skill has a deliverable checker |
| CRM writes | Only via attached connectors | No — the skills are prompt-only |
| Install | Plugin marketplace | npx skills add, per skill or --all |
Skills
- sales-plugin
- 9, one motion end to end
- gtm-skills
- 211 across 25 categories
Provenance
- sales-plugin
- Official (Anthropic)
- gtm-skills
- Verified org (LeadMagic, a B2B data vendor)
Licence
- sales-plugin
- Apache-2.0
- gtm-skills
- MIT
Vendor neutrality
- sales-plugin
- Connector-agnostic
- gtm-skills
- Ranks its own product first in its provider tables
Ships an output checker
- sales-plugin
- No
- gtm-skills
- Yes — every skill has a deliverable checker
CRM writes
- sales-plugin
- Only via attached connectors
- gtm-skills
- No — the skills are prompt-only
Install
- sales-plugin
- Plugin marketplace
- gtm-skills
- npx skills add, per skill or --all
Open sales-plugin or gtm-skills for the composite score, license, and exact install commands, or browse the full Sales category.
Verdict
The bottom line
These are not competitors so much as different layers. sales-plugin is the one to install first: it is official, it is nine skills rather than 211 to route between, and it covers the work that recurs daily. Add gtm-skills when you hit a motion the nine do not cover — the library is genuinely deep and every skill names the framework it is applying, which is exactly what you want when you are running something for the first time. Read its provider comparisons as a vendor’s, not a benchmark.
FAQ
Common questions
Does 211 skills mean gtm-skills is better value?
Count is not the metric. What makes gtm-skills worth listing is that its median skill body runs about 9 kB with a named framework, an output template and a deliverable checker, and 168 of its 211 descriptions carry an explicit trigger. A 244-skill GTM repo with more stars was rejected from this catalog in the same review because its median body was 1.3 kB of bullet points.
Can either of them write to my CRM?
Not on their own. sales-plugin acts through whatever connectors you attach — HubSpot, Close, Clay, ZoomInfo, Fireflies — and its own entry says CRM actions depend on those. gtm-skills is prompt-only. For CRM operations specifically, hubspot-agent-skills is the first-party option.
Do they overlap?
Yes, on outreach and account research. In practice the descriptions route sensibly: a request phrased as daily pipeline work reaches sales-plugin, and one phrased as a named GTM motion reaches gtm-skills. If you install both, expect that overlap rather than conflict.
Related
More head-to-head comparisons
- firecrawl vs browser-use
firecrawl for hosted, JavaScript-rendered extraction at scale; browser-use for driving a real browser through logins, forms, and multi-step flows.
- supabase-skill vs planetscale-skills
supabase-skill for Postgres with row-level security, auth, and realtime; planetscale-skills for MySQL with Git-style schema branching at scale.
- stripe-best-practices vs paddle-agent-skills
stripe-best-practices for maximum control over payment flows (you own tax); paddle-agent-skills for merchant-of-record billing (Paddle handles global sales tax and VAT).
- docling vs pdf
docling for reading and converting documents an agent cannot open — including scanned PDFs and RAG chunking; the Anthropic pdf skill for producing and manipulating real PDFs.
- semgrep vs trail-of-bits
semgrep runs a real static-analysis engine and writes custom rules; trail-of-bits brings a security firm's review method to a diff. Findings versus judgement.
- playwright-cli vs Browserbase browser
playwright-cli for a local browser you fully control and an existing Playwright suite; Browserbase browser for hosted sessions with CAPTCHA solving and residential proxies.
- postgres vs supabase-skill
The postgres skill for engine-level decisions — types, indexes, partitioning, extensions; supabase-skill for the platform layer — row-level security, auth, realtime.
- drawio vs mermaid-diagrams
drawio produces an editable .drawio file someone can rearrange later; mermaid keeps the diagram as text inside the document it belongs to.
- Stripe Connect vs Paddle
Stripe Connect for control over multi-party payment flows you operate yourself; Paddle for handing global tax and compliance to a merchant of record.
- hyperframes vs remotion-best-practices
hyperframes renders video from plain HTML and CSS under Apache-2.0; remotion-best-practices teaches idiomatic Remotion, which is React-based and proprietary. The licence and the authoring language are the two decisions that matter.
- chrome-devtools vs playwright-cli
chrome-devtools is for diagnosing a page — performance, accessibility, memory, network; playwright-cli is for automating and testing one. Google’s tool asks why it is broken, Microsoft’s asserts that it works.
- liteparse vs docling
liteparse pulls a specific value out of a document cheaply and locally; docling converts whole documents — including scanned ones — into structured Markdown or JSON. Both MIT, both local: the split is lookup versus conversion.
- vibe-prospecting vs gtm-eng-skills
One buys coverage from a single provider; the other chains many providers and makes you own the routing. Managed B2B data against enrichment engineering.
Browse all best-skill guides or the full directory.