一键在 Manus 中运行任何 Skill

sales-ahrefs

星标58

分支7

更新时间2026年6月27日 15:13

Ahrefs (ahrefs.com) platform help — industry-leading SEO toolset: Site Explorer (backlinks, organic keywords, Domain Rating), Keywords Explorer, Rank Tracker, Site Audit, Content Explorer, and Brand Radar AI-visibility. REST API v3 (api.ahrefs.com/v3, Bearer key, metered API units; v2 discontinued 2025-11-01) plus an official MCP server (Claude/ChatGPT/Cursor, Lite+). Use when building an Ahrefs API integration, your API units or monthly credits keep running out, setting up the Ahrefs MCP server with Claude, migrating off the dead v2 API to v3, getting throttled or locked by the 'suspicious activity' system within your limits, pulling backlinks/keywords/DR into a warehouse or report, deciding if you need the paid API subscription vs Enterprise, or choosing Starter vs Lite vs Standard vs Advanced. Do NOT use for SEO strategy or tool selection across vendors (use /sales-seo), AI-search-visibility tracking strategy across tools (use /sales-ai-visibility), or content optimization strategy (use /sales-seo).

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

sales-skills

sales-skills/sales

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

文件资源管理器

4 个文件

SKILL.md

readonly

同仓库更多 Skills

同仓库

sales-do

sales-skills/sales

Routes any sales, marketing, ad, or GTM objective to the right specialized skill and outputs the install command for that skill plus a ready-to-paste prompt packed with the user's context. Asks clarifying questions when the objective is ambiguous, then hands back a copy-paste-runnable next step. Covers prospecting, outbound cadences, deals, proposals, forecasting, deliverability, enrichment, intent, content, coaching, CRO, SEO, launch directories, newsletters, email/SMS/push marketing, chatbots, influencer marketing, social media, employee advocacy, media relations, reviews, data hygiene, B2B advertising, retargeting, affiliate, loyalty, digital products, memberships, webinars, checkout, and platform-specific help. Use when the user has a sales or marketing question and isn't sure which skill to use, or wants a multi-skill sequence with a batch install command. Do NOT use to solve problems directly — this skill only routes.

2026-06-2858

sales-phantombuster

sales-skills/sales

PhantomBuster (phantombuster.com) platform help — code-free web/LinkedIn automation + scraping + lead-gen: 'Phantoms' (LinkedIn search export, scrapers, auto-connect, email finder), Flows that chain them, AI Agents + a cloud LinkedIn Leads database. Developer surface: a REST API (base phantombuster.com/api/v2, X-Phantombuster-Key-1 header) to launch agents (POST /agent/{id}/launch → container id) and fetch run results (/containers/fetch-result-object), plus the Leads storage and per-agent webhooks (secret param, 11s timeout) on run completion. Billed by execution time + slots; API on all paid plans. Use when launching a Phantom or fetching its scraped output via the API, wiring a run-finished webhook, handling the async agent→container model, managing slots/execution-time, or LinkedIn cookie/safety issues. Do NOT use for prospect-list / lead-sourcing strategy across tools (use /sales-prospect-list), enrichment strategy across vendors (use /sales-enrich), or outbound cadence strategy (use /sales-cadence).

2026-06-2858

sales-prospect-list

sales-skills/sales

Builds targeted B2B prospect lists for outbound campaigns from database providers (Apollo, ZoomInfo, Clay, Cognism). Use when you don't know who to target, your outbound list is too broad and response rates are low, you can't find the right decision-makers at target accounts, your ICP is vague, or your prospect list is full of bad-fit contacts. Do NOT use for enriching existing contacts with emails/phones (use /sales-enrich), interpreting buying signals (use /sales-intent), general Apollo platform help (use /sales-apollo), or hyperlocal / door-to-door / territory / route-based outbound to local SMBs that aren't on databases — restaurants, gas stations, salons, contractors, HVAC — (use /sales-field-sales).

2026-06-2858

sales-intent

sales-skills/sales

Interprets buying signals and prioritize accounts for outreach. Use when drowning in intent data and not sure what matters, can't tell which accounts to prioritize, buying signals aren't translating to pipeline, job change alerts are noisy, intent topics feel too broad, lead scores don't match actual deal quality, or not sure how to act on signals in outreach. Do NOT use for building prospect lists (use /sales-prospect-list), enriching contacts (use /sales-enrich), ZoomInfo-specific intent config (use /sales-zoominfo), or general Apollo platform help (use /sales-apollo).

2026-06-2858

sales-syncgtm

sales-skills/sales

SyncGTM (syncgtm.com) platform help — AI-native GTM data engine that unifies buying signals (job changes, funding, hiring, LinkedIn posts, web-traffic, custom AI signals), waterfall enrichment (verified emails/mobiles, 40+ providers), AI lead scoring (0–100 vs ICP), AI research agents, and a no-code Workflow Builder. Developer surface: an MCP server (api.syncgtm.com/mcp, OAuth browser sign-in, free-plan — works with Claude Code/Cursor to enrich, find emails/phones, read signals), a REST API (api.syncgtm.com, API key), webhooks, and 40+ integrations (HubSpot/Salesforce/Slack/Attio). Use when connecting the MCP server to an AI agent, enriching contacts via the API, acting on buyer signals, scoring leads vs an ICP, building a signal→enrich→outreach workflow, or choosing SyncGTM vs Clay/Trigify. Do NOT use for intent-data strategy across tools (use /sales-intent), prospect-list building (use /sales-prospect-list), or enrichment strategy across vendors (use /sales-enrich).

2026-06-2858

sales-cadence

sales-skills/sales

Designs multi-channel outbound cadences with timing, A/B testing, and content. Use when outbound sequences getting low reply rates, unsure how many touchpoints or what spacing to use, cadence emails sound generic, prospects ignoring calls, A/B tests not moving the needle, sequence performance plateauing, or not sure which channels to include in outreach. Do NOT use for marketing cold email (use /cold-email), automated email flows (use /email-sequence), or general Salesloft platform help (use /sales-salesloft).

2026-06-2858

name	sales-ahrefs
description	Ahrefs (ahrefs.com) platform help — industry-leading SEO toolset: Site Explorer (backlinks, organic keywords, Domain Rating), Keywords Explorer, Rank Tracker, Site Audit, Content Explorer, and Brand Radar AI-visibility. REST API v3 (api.ahrefs.com/v3, Bearer key, metered API units; v2 discontinued 2025-11-01) plus an official MCP server (Claude/ChatGPT/Cursor, Lite+). Use when building an Ahrefs API integration, your API units or monthly credits keep running out, setting up the Ahrefs MCP server with Claude, migrating off the dead v2 API to v3, getting throttled or locked by the 'suspicious activity' system within your limits, pulling backlinks/keywords/DR into a warehouse or report, deciding if you need the paid API subscription vs Enterprise, or choosing Starter vs Lite vs Standard vs Advanced. Do NOT use for SEO strategy or tool selection across vendors (use /sales-seo), AI-search-visibility tracking strategy across tools (use /sales-ai-visibility), or content optimization strategy (use /sales-seo).
argument-hint	[describe what you need help with in Ahrefs]
license	MIT
version	1.0.0
tags	["sales","seo","content","platform"]
github	https://github.com/ahrefs

Ahrefs Platform Help

Step 1 — Gather context

If references/learnings.md exists, read it first for accumulated platform knowledge.

What are you trying to do?
- A) Build an API integration — pull backlinks, organic keywords, Domain Rating, rank data
- B) Set up the MCP server so Claude/ChatGPT can query your Ahrefs account by prompt
- C) Fix API units / monthly credits running out, overage fees, or "suspicious activity" throttling
- D) Migrate a dead v2 integration to v3
- E) Pick/understand a plan — Starter vs Lite vs Standard vs Advanced vs Enterprise; the credit + API-unit model
- F) Use a specific tool — Site Explorer, Keywords Explorer, Rank Tracker, Site Audit, Content Explorer, Brand Radar
REST or MCP? Scheduled pipelines/exports → REST API (tight select). Ad-hoc agent questions → the MCP server. Both spend the same API units.

Skip-ahead rule: if the user's prompt already provides enough context, skip to Step 2.

Step 2 — Route or answer directly

If the question is about...	Route to...
SEO strategy, tool selection, or content optimization across vendors	`/sales-seo {question}`
AI-search-visibility (Brand Radar–style) tracking strategy across tools	`/sales-ai-visibility {question}`
Connecting Ahrefs data to other tools generically (iPaaS/warehouse)	`/sales-integration {question}`

When routing, give the exact command, e.g. "This is an SEO-tool-selection question — run: /sales-seo Ahrefs vs Semrush for a small content team on a budget".

Step 3 — Ahrefs platform reference

Read references/platform-guide.md for the full reference — the module map (what's API vs MCP vs UI-only), the pricing model (the credit system on lower tiers, API-units allocation vs the paid API subscription/Enterprise for heavy use, $199/$99 add-ons, no free trial), the data model with JSON shapes, and quick-start recipes (pull competitor keywords unit-aware; wire the MCP into Claude; bulk-score domains with batch-analysis).

Read references/ahrefs-api-reference.md for the integration surface — base https://api.ahrefs.com/v3, Bearer auth (keys from Account → API keys, owners/admins, 1-yr expiry), the API-units cost model (min 50 units, scales with rows × fields, free endpoints), the endpoint groups (Site Explorer, Keywords Explorer, Rank Tracker, Site Audit, Batch Analysis, limits-and-usage), and the official MCP server setup.

Answer using only the relevant section. Don't dump the full reference.

Step 4 — Actionable guidance

Focus on the user's specific situation:

Budget units like money. Every data call costs ≥50 units, scaling with rows × fields. Always pass select (only needed fields), cap limit, prefer batch-analysis for many targets, cache, and poll /subscription-info/limits-and-usage. This single discipline prevents most "ran out" pain.
v3 only. v2 was fully shut off 2025-11-01 — any v2 tutorial/endpoint is dead. New keys + v3 paths.
Use the MCP for agents, REST for pipelines. The official MCP (Lite+) lets Claude/ChatGPT pull data by prompt; it draws on the same unit budget, so keep agent queries specific.
Pace automated calls. Ahrefs' anti-abuse "suspicious activity" system throttles bursty access even within plan limits — add jitter/backoff, don't hammer in parallel.
Know the real cost. Lower tiers meter credits (1 per report); heavy API use needs a paid API subscription (~$500–$10k/mo) or Enterprise; Brand Radar/AI Content Helper/Report Builder are paid add-ons.
It's read-only. No write API, no event webhooks — pull data out, push it into your own systems.

If you discover a gotcha, workaround, or tip not covered in references/learnings.md, append it there.

Gotchas

Best-effort from research (2026-06) — review these, especially pricing/credits and the unit model, which change often.

API units run out fast if you don't select. Min 50/request and it scales with rows × fields. Request only the fields and rows you need; use batch-analysis and cache.
API v2 is dead (since 2025-11-01). Build only on v3 with a fresh key; old v2 integrations have no data access.
"Suspicious activity" lockouts hit legit users. Aggressive anti-abuse throttling can restrict you even inside plan limits — pace and back off automated calls.
Credits ≠ API units. The in-app credit system (1 per report, e.g. 500/mo on Lite) is separate from the API-unit allocation. Both can be exhausted; both cause overage/limits.
Heavy API use is expensive. The included unit allocation suits light use; production volume needs a paid API subscription ($500–$10k/mo) or Enterprise.
No free trial; Starter is the cheap eval path. Don't expect a trial — Starter ($29) is the lowest-cost way to evaluate.
Add-ons stack. Brand Radar ($199), AI Content Helper ($99), Report Builder ($99) are billed on top of the base plan.
No affiliate program and no webhooks. Don't look for either — Ahrefs is a read-only research tool that deliberately runs no affiliate program.

Related skills

/sales-seo — SEO strategy and tool selection across vendors (Ahrefs vs Semrush vs cheaper suites), content + technical SEO
/sales-ai-visibility — AI-search-visibility tracking strategy across tools (Brand Radar is Ahrefs's add-on for this)
/sales-semrush — Semrush platform help (the closest all-in-one competitor)
/sales-integration — Connecting Ahrefs data to a warehouse/other tools (read-only pulls, no webhooks)
/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 -a claude-code

Examples

Example 1: Pull a competitor's top keywords without blowing my units (developer/automation)

User says: "I want to export competitor.com's top 100 organic keywords from Ahrefs via the API." Skill does: Walks Recipe 1 — GET /api/v3/site-explorer/organic-keywords?target=competitor.com&country=us&limit=100&select=keyword,volume,position,traffic with Authorization: Bearer. Stresses the unit math (min 50/request, scales with rows × fields), so a tight select + limit is essential, and to check /subscription-info/limits-and-usage first. Notes v3 only (v2 is dead) and keys come from Account → API keys (owners/admins). Result: A unit-efficient keyword export.

Example 2: Let Claude query Ahrefs directly

User says: "Can I connect Ahrefs to Claude so I can just ask for backlink data?" Skill does: Points to the official Ahrefs MCP server (Recipe 2), available on Lite+: claude mcp add --transport http ahrefs "https://mcp.ahrefs.com" --header "Authorization: Bearer $KEY" (verify the hosted URL in the MCP docs). Warns that MCP queries spend the same API units as REST, so keep prompts specific. Frames MCP as best for ad-hoc exploration vs REST for scheduled pipelines. Result: Claude pulls Ahrefs SEO data by prompt, unit-aware.

Example 3: My Ahrefs bill/credits keep blowing up

User says: "I'm constantly hitting credit limits and overage fees on Ahrefs — is it just overpriced, or am I doing it wrong?" Skill does: Separates the two meters — in-app credits (1 per report, 500/mo on Lite) vs API units — and gives concrete savings (use select/limit, batch-analysis, cache, monitor usage; upgrade tier or buy the API subscription only if genuinely needed). For the broader "is Ahrefs worth it vs Semrush/cheaper tools" decision, routes: "run: /sales-seo Ahrefs credit limits — is a cheaper SEO suite enough for me." Result: User cuts usage waste and gets a path to the tool-selection decision.

Troubleshooting

My API calls fail or return "out of units"

Symptom: Requests error with a limits/units message, or stop returning data mid-month. Cause: You've exhausted the monthly API-unit allocation — min 50 units/request scaling with rows × fields — or you're on a plan whose allocation suits only light use. Solution: Add select to fetch only needed fields, lower limit, switch many single calls to batch-analysis, cache results, and watch /subscription-info/limits-and-usage. For sustained volume, move to a paid API subscription or Enterprise. Confirm you're on v3 (v2 was shut off 2025-11-01).

I keep getting throttled/locked even though I'm within my plan

Symptom: Restrictions or "suspicious activity" blocks despite staying within limits. Cause: Ahrefs' anti-abuse system flags bursty/automated access patterns, sometimes catching legitimate API or heavy UI usage. Solution: Pace requests (add delay + jitter), avoid heavy parallelism, back off on 429, and spread large jobs over time. If a legitimate workflow is blocked, contact Ahrefs support with your use case.

My old Ahrefs API integration stopped returning data

Symptom: A previously working integration now returns nothing/errors. Cause: It was built on API v2, which was fully discontinued 2025-11-01 — v2 integrations no longer have data access. Solution: Rebuild on API v3 (base https://api.ahrefs.com/v3, Bearer key from Account → API keys), update endpoint paths to the v3 groups, and adopt the API-units discipline (select, limit, batch). For AI agents, consider the MCP server instead.