Best Claude Skills for Sales (2026)
Most "best skills" lists are copied README summaries. This one isn't: we installed all 41 sales skills in our catalog, ran each against a baseline and scored four criteria. 13 passed cleanly, average score 9.2/10. The one to start with: Lead Research.
Ranked by SkillProof Score · how we score
- 1
Lead Research
Account/contact research: trigger events, org-chart power mapping, ICP scoring -- honest about what it can't verify.
From our test: Given a fictional Series B account and asked to build a brief, it did not invent a plausible VP-of-Sales name the way an unguided baseline would -- it flagged that it can't access LinkedIn Sales Nav…
- 2
Discovery Call
Discovery/first-call prep: SPIN-derivative question bank, PACT qualification scoring, multi-stakeholder tactics.
From our test: Its own description scopes it to first/discovery calls, and that held up in testing: a 'prep for a QBR with an existing customer' prompt correctly did not trigger it, confirming the card's own…
- 3
Pipeline Review
Weighted deal scoring, zombie-deal detection, and forced disqualification for pipeline reviews -- works on pasted deal data, not a live CRM.
From our test: Given two toy deals, it correctly flagged the 70-day-old, single-threaded, three-weeks-silent one as a zombie with a one-week resurrect-or-kill deadline, versus a baseline that just said 'follow up…
- 4
Proposal & Pricing
Proposal/SOW structure, three-tier outcome-named pricing, and a Mutual Action Plan -- outputs text/markdown, not a formatted document.
From our test: Produces a markdown/text proposal with three-tier, outcome-named pricing and a Mutual Action Plan timeline, but it does not generate a DOCX or call the docx skill itself -- so the old card's claim…
- 5
Objection Handling
ACRC-framework objection playbook and live/email scripts for B2B reps — covers price, ghosting, and champion-relayed objections, not just pricing pushback.
From our test: Tested it on a champion-relayed objection ('my legal team has concerns about data handling') instead of the SKILL's own worked example — it correctly combined the Team-Based Objection Handling…
- 6
Sales Enablement
Turns feature lists into decks, one-pagers, and objection docs reps actually use.
From our test: Ran a real one-pager task: the skill turned a generic feature dump into a problem-first, champion-targeted leave-behind with a named proof metric and a 30-second-scan structure — baseline output was…
- 7
Account Research Brief
Turns a company name into a sourced 1-page pre-outreach brief: overview, decision makers, tech stack, signals, engagement angles.
From our test: Live-researched Modern Treasury: the plain-prompt answer was a one-paragraph 'they do payments infra' summary with no sources; following the skill surfaced actual conflicting public info on who the…
- 8
Forward Deployed Selling
Enterprise sales doctrine that gates every deal action through movement diagnosis and a hard ethics layer.
From our test: Ran a live before/after on a value-provocation draft: the unguided baseline asserted an invented '30% average fraud savings' as fact and opened with a meeting ask; the doctrine-guided version…
- 9
B2B Local Outreach
End-to-end B2B cold-outreach pipeline: source, score, personalize, comply, track.
From our test: Applied the v2 weighted scoring formula by hand to a sample hotel lead (180 reviews, 4.6★, SSL+mobile, no ads/hiring) and got Priority-B 43/100 with a full breakdown — the baseline attempt with no…
- 10
B2B Lead Hunter
Evidence-gated foreign-trade B2B lead research, decision-maker discovery, and controlled SMTP outreach.
From our test: Ran the real dedupe_leads.py + export_leads.py + validate_artifact.py pipeline on synthetic leads: it correctly merged two duplicate-domain candidates, rejected a B2C-only lead, and caught a genuine…
How this ranking works
Each skill gets a fresh install in Claude Code, three trigger phrasings, and the same task run with and without it. Scores: installation (5), trigger reliability (5), output vs baseline (10), documentation honesty (5) — normalized to a 10-point SkillProof Score. Full rubric on the methodology page. Queue-verdict skills sit at the bottom until testing completes.
New here? Start with how to install Claude skills — or grab the whole setup in one command with a curated pack ($10).
On a different AI tool? These tested instructions adapt: see our conversion guides for Cursor rules, Copilot instructions, Windsurf and Custom GPTs.