Jeden Skill in Manus ausführen
mit einem Klick

Jeden Skill in Manus mit einem Klick ausführen

sales-buffer

Sterne58

Forks7

Aktualisiert27. Juni 2026 um 15:27

Buffer (buffer.com) platform help — simple social media publishing/scheduling across 11 networks (Instagram, LinkedIn, TikTok, X, etc.) with queue scheduling, drafts, analytics, engagement, and link-in-bio. Two APIs: a current GraphQL developer API (Bearer key from publish.buffer.com/settings/api, plan-based rate limits, beta/free) and a deprecating legacy REST v1 (OAuth, 60/min); no webhooks. Use when building a Buffer API integration to auto-schedule posts or pull metrics, migrating a legacy v1 integration to the GraphQL API, hitting plan-based API rate limits, per-channel pricing exploding as you add accounts, the free plan's 3-channel or lifetime 8-connection cap, needing approval workflows (Team plan), Buffer lacking social listening, or choosing Free vs Essentials vs Team. Do NOT use for social media management strategy or tool selection across tools (use /sales-social-media-management), social listening (use /sales-social-listening), or influencer marketing (use /sales-influencer-marketing).

Installation

Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.

In Manus ausführen

Quelle

sales-skills

sales-skills/sales

GitHub-Repository öffnen Creator-Repositorys ansehen

Download

In Manus ausführen

Datei-Explorer

4 Dateien

SKILL.md

readonly

Mehr aus diesem Repository

gleiches Repository

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-buffer
description	Buffer (buffer.com) platform help — simple social media publishing/scheduling across 11 networks (Instagram, LinkedIn, TikTok, X, etc.) with queue scheduling, drafts, analytics, engagement, and link-in-bio. Two APIs: a current GraphQL developer API (Bearer key from publish.buffer.com/settings/api, plan-based rate limits, beta/free) and a deprecating legacy REST v1 (OAuth, 60/min); no webhooks. Use when building a Buffer API integration to auto-schedule posts or pull metrics, migrating a legacy v1 integration to the GraphQL API, hitting plan-based API rate limits, per-channel pricing exploding as you add accounts, the free plan's 3-channel or lifetime 8-connection cap, needing approval workflows (Team plan), Buffer lacking social listening, or choosing Free vs Essentials vs Team. Do NOT use for social media management strategy or tool selection across tools (use /sales-social-media-management), social listening (use /sales-social-listening), or influencer marketing (use /sales-influencer-marketing).
argument-hint	[describe what you need help with in Buffer]
license	MIT
version	1.0.0
tags	["sales","social-media-management","publishing","platform"]
github	https://github.com/bufferapp

Buffer 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 — auto-schedule posts, manage channels, pull post metrics
- B) Migrate a legacy v1 (api.bufferapp.com/1) integration to the new GraphQL API
- C) Fix API rate limits / auth (Bearer key vs legacy OAuth) / the 2026 media (Assets Input) change
- D) Understand pricing — the per-channel model, free-plan caps, Team-gated features
- E) Configure a module — Publish/queue, Create (Ideas), Analyze, Community, approvals, Start Page
- F) Decide if Buffer fits — vs needing social listening, agency scale, or deep collaboration
Which API? Build new on the GraphQL API; only touch REST v1 for an existing integration you're migrating. There are no webhooks — anything reactive must poll.

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...
Social media management strategy or tool selection across tools	`/sales-social-media-management {question}`
Social listening / monitoring (Buffer has none)	`/sales-social-listening {question}`
Influencer marketing	`/sales-influencer-marketing {question}`
Connecting Buffer to other tools generically (iPaaS)	`/sales-integration {question}`

When routing, give the exact command, e.g. "This is a tool-selection question — run: /sales-social-media-management Buffer vs Hootsuite for a 3-client agency".

Step 3 — Buffer platform reference

Read references/platform-guide.md for the full reference — the module map (what's API vs UI-only), the per-channel pricing model (free-plan 3-channel + lifetime 8-connection caps, Team-gated approvals, no social listening), the channel/post data model with JSON shapes, and quick-start recipes (auto-schedule via GraphQL; poll metrics into a dashboard; migrate v1→GraphQL).

Read references/buffer-api-reference.md for the integration surface — the GraphQL API (developers.buffer.com, Bearer key from publish.buffer.com/settings/api, createPost mutation, plan-based rate limits across 15-min/24-hr/30-day windows, the 2026-05 Assets-Input migration) and the legacy REST v1 (api.bufferapp.com/1/, OAuth, /updates/create.json, 60/min). Note: no webhooks on either.

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

Step 4 — Actionable guidance

Focus on the user's specific situation:

Build on GraphQL; v1 is sunsetting. New work uses the GraphQL API with a Bearer API key from publish.buffer.com/settings/api. Touch REST v1 only to migrate an existing integration.
There are no webhooks — poll. For "did it publish?" / metrics, poll on a cadence that respects the 15-min/24-hr/30-day rate windows (e.g. hourly), and cache. Don't tight-loop.
Mind the 2026 media change. The Assets Input format changed 2026-05-25; the legacy media format now fails. Update media submission per the migration guide.
Cost is per channel. Each connected account is billed — 10 channels on Essentials ≈ $600/yr. For many accounts/clients, weigh flat-rate tools (route to /sales-social-media-management).
Know the free-plan traps. 3 active channels, 10 queued posts/channel, and a lifetime cap of 8 unique channel connections (counts every account ever connected, even if disconnected).
Buffer doesn't do listening. If they need monitoring/sentiment, that's a separate tool (/sales-social-listening); approvals/collaboration need the Team plan.

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 and the API beta status, which change.

No webhooks. Both APIs are pull-only — reactive flows must poll within the rate windows. Don't promise event pushes.
Two APIs, build on GraphQL. The current developer API is GraphQL (Bearer key); the legacy REST v1 (api.bufferapp.com/1, OAuth, 60/min) is being deprecated.
2026-05-25 Assets Input migration. The old media-submission format now fails — update to the new Assets Input or image/video posts break.
Per-channel pricing compounds. $5 (Essentials) / $10 (Team) per channel/mo — agencies with many accounts pay a lot; model the real cost before committing.
Free-plan caps are sneaky. 3 active channels, 10 queued posts/channel, and a lifetime 8-unique-connection ceiling that counts disconnected channels too.
Approvals & some scheduling features are Team-gated. Approval workflows, first-comment scheduling, and hashtag manager aren't on lower tiers.
No social listening. Buffer is publish + light engagement/analytics only — pair with a listening tool for monitoring.
Network APIs break features. Auto-publishing Stories/Reels/first-comments depends on each network's API — features can stop working when Instagram/TikTok/X change theirs.

Related skills

/sales-social-media-management — Social media management strategy and tool selection across tools (Buffer vs Hootsuite/Later/Agorapulse; per-channel cost trade-offs)
/sales-social-listening — Social listening/monitoring strategy (Buffer has none — pair a dedicated tool)
/sales-influencer-marketing — Influencer discovery, vetting, and campaign strategy
/sales-integration — Connecting Buffer to other tools via Zapier/Make (no native 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: Auto-schedule posts from my app (developer/automation)

User says: "When I publish a blog post, I want it auto-scheduled to my Buffer channels via the API." Skill does: Walks Recipe 1 — POST a GraphQL createPost mutation to the Buffer API with channelIds, text, scheduledAt, and status: scheduled, authenticated with a Bearer API key from publish.buffer.com/settings/api. Flags building on GraphQL (not the deprecating REST v1), the new Assets Input format for media (legacy fails since 2026-05-25), and that there are no webhooks, so confirm publish status by polling. Result: Blog posts auto-schedule to Buffer.

Example 2: My agency's Buffer bill keeps climbing

User says: "We manage 12 client accounts in Buffer and the cost keeps going up — is there a cheaper way?" Skill does: Explains Buffer prices per channel ($5–$10/channel/mo), so 12+ accounts compound fast, and approvals are Team-gated. Suggests auditing active vs idle channels and weighing flat-rate alternatives, then routes the comparison: "run: /sales-social-media-management Buffer per-channel cost vs flat-rate tools for a 12-client agency." Result: User understands the cost driver and gets a path to the selection decision.

Example 3: Can Buffer tell me what people are saying about my brand?

User says: "Does Buffer do social listening so I can track brand mentions?" Skill does: Clarifies Buffer has no social listening — it's publishing + light engagement/analytics. Recommends pairing a dedicated listening tool and routes: "run: /sales-social-listening track brand mentions and sentiment." Notes Buffer's Community module only handles comments on your own posts, not monitoring. Result: User sets the right expectation and gets pointed to the right tool.

Troubleshooting

My API calls fail with auth errors

Symptom: 401/unauthorized, or a v1 token doesn't work on the new API. Cause: Mixing the two APIs — the GraphQL API uses a Bearer API key (from publish.buffer.com/settings/api), while legacy v1 uses OAuth access_token (and the auth code is valid only 30 seconds). They aren't interchangeable. Solution: For new builds use the GraphQL API with Authorization: Bearer YOUR_KEY. For v1, complete the OAuth exchange quickly (code expires in 30s) and pass ?access_token=. Don't reuse a v1 token against GraphQL.

My image/video posts started failing

Symptom: Media posts that worked before now error. Cause: The Assets Input migration (2026-05-25) — mutations using the legacy assets input format now fail. Solution: Update media submission to the new Assets Input format per Buffer's migration guide. Re-test image, video, and threaded posts after switching.

I'm hitting rate limits / can't get real-time updates

Symptom: Rate-limit errors, or you want instant publish/engagement events. Cause: The API meters requests per 15-min/24-hr/30-day windows (and caps API keys/OAuth clients 1–5 by plan), and Buffer has no webhooks. Solution: Poll on a cadence that fits the windows (e.g. hourly for metrics, not every minute), cache results, and back off on errors. If you need higher limits, move up a plan; there is no webhook option, so design around polling.