New: Earn 20% as an AgentAlley affiliate. Share your link and earn on every sale you refer. Join now New: Earn 20% as an affiliate. Join now

Running a Quora answering program run as a lead generation

Quora authority answering

by swan-gtm · MIT license · ★ 159 on GitHub · updated Sep 23

Quora authority answering cover

Use this skill when running a Quora answering program run as a lead generation channel: answer these Quora questions", "write Quora answers for our founder", "our Quora answers read like AI", "how do we get leads from Quora", "which of…

---
name: quora-authority-answering
title: Quora authority answering
description: |
  Use this skill when running a Quora answering program run as a lead generation channel:
  "answer these Quora questions", "write Quora answers for our founder", "our Quora
  answers read like AI", "how do we get leads from Quora", "which of these questions
  should we answer". Produces linkless answers that survive moderation, earn upvotes
  on the collapsed preview, and convert readers into profile visits, plus the triage
  and posting order for a batch.
category: AEO
tags: [Marketing, Demand Gen]
---

# Quora authority answering

Applies to a personal expert profile answering questions in a commercial category. Produces batches of paste-ready answers, ordered for posting, that teach real methodology and never pitch.

Overview

Applies to a personal expert profile answering questions in a commercial category. Produces batches of paste-ready answers, ordered for posting, that teach real methodology and never pitch.

Manual install (npx, ZIP)
Claude Codenpx skills add swan-gtm/gtm-skills --skill quora-authority-answering -g -a claude-code
Claude Code (manual)mkdir -p ~/.claude/skills && curl -sL https://codeload.github.com/swan-gtm/gtm-skills/tar.gz/e65d97205fd2 \ | tar -xz -C ~/.claude/skills --strip-components=3 gtm-skills-e65d97205fd2/skills/vesselin-malev/quora-authority-answering
Windows (PowerShell)New-Item -ItemType Directory -Force "$HOME\.claude\skills" | Out-Null; Invoke-WebRequest "https://m.agentalley.io/zip/e0bd12a80ad6e0e91a73/quora-authority-answering.zip" -OutFile "$env:TEMP\quora-authority-answering.zip"; Expand-Archive "$env:TEMP\quora-authority-answering.zip" -DestinationPath "$HOME\.claude\skills" -Force
Claude.ai / desktopDownload the ZIP and upload it under Settings → Capabilities → Skills.
Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

  • SKILL.md6.8 KB
  • references/4 files · 13.6 KB
Read the files here
swan-gtm/e65d9725 files
SKILL.md
Show the full text86 lines

Quora authority answering

Applies to a personal expert profile answering questions in a commercial category. Produces batches of paste-ready answers, ordered for posting, that teach real methodology and never pitch.

Most traffic arrives from search months or years after an answer posts, so an answer is an appreciating asset on a permanent URL. The credential line above every answer does all the selling. That is why the answer itself never has to, and why it outperforms the answers that do.

Set up the account before answer one

Answer from a personal profile, never a branded one. Company-voiced accounts read as ads and get collapsed. A credentialed human gets read.

Set a credential line per topic cluster — role, company, one clause on what the company does for whom — and build the profile bio and links before writing anything. In linkless mode the profile is the only destination. Both assets are specified in references/credential-and-profile.md.

Triage the batch

Answer everything in a pasted batch unless the client says otherwise. Raise concerns as flags delivered alongside the work, never as withheld work.

Four conditions get flagged and still get written: off-position questions, vendor-seeded clusters, tool questions where the tool is unknown, and regulatory questions. Near-duplicate threads are the one deliberate exception — pick the thread with the better traffic and skip the twin, per the triage reference. Each carries its own handling and its own effect on posting order — read references/triage-flags.md before sequencing a batch.

Pace the posting

Ten to twenty answers a day is safe. The platform cap sits far higher, near fifty per rolling day, and the count is not what flags accounts — velocity, link density, and thin answers are.

Spread posts across the day. Fifteen in one sitting looks automated. Ramp a cold account at three to five a day for the first two weeks with no links at all, then scale once there is upvote history.

Win the collapsed preview

The preview shows roughly the first two lines, and that is where the upvote decision starts. Line one carries the whole thesis, stated the way nobody else in the thread will state it.

Every opener does one of two things: names a target — who is lying, who is getting paid, who is being played — or turns the knife on the reader or on the writer's own industry. Self-implication is the strongest move available. Contrarian alone is cheap on this platform; contrarian while holding the knife toward yourself reads as credible. Register, the capitalization device, and the openers that fail the bar are in references/opener-craft.md.

Build the body

Pick one thing per answer to be genuinely worked up about and give it most of the words. Everything else gets a clause. Even, balanced coverage is the loudest machine tell in this format.

Let paragraph endings fall flat — a kicker on every one produces a rhythm no human sustains. Vary the shape across a batch: an instruction, a refusal of the question's framing, a caveat. Three answers sharing a skeleton reads as templated. Leave loose ends. Keep length deliberately unequal, roughly 90 to 400 words, because a five-line answer standing among eighty long ones is the only thing on that page nobody has to scroll.

Run references/machine-tells.md over the batch before delivery.

Carry real method

Generic operator wisdom is the failure mode. "Do direct outreach" and "focus on quality" teach nothing, and they read as machine-written precisely because they carry no knowledge.

Every answer holds at least one mechanic only a practitioner knows — how a signal-based list gets built against a database export, what personalization off a job posting looks like next to flattery, how sending infrastructure gets separated across domains and mailboxes, what the operator's own testing turned up. Name real tools where the tool is the answer, and withhold any the client has flagged as unmentionable.

Keep it linkless

Zero links. Zero calls to action. The credential line and the profile carry the commercial load, and that is what keeps answers out of the moderation queue.

One exception, on "which company is best" questions only: disclose the stake, refuse to rank anyone including themselves, offer free advice by direct message. It works once as a pattern — the sequence and the reason it fails elsewhere are in references/credential-and-profile.md.

Deliver the batch

One file per batch, answers numbered in posting order: unanswered and freshly-followed questions first, crowded and stale threads last. Note where a batch exceeds a day's quota so the poster splits it rather than dumping it.

What good looks like

The best operator judges a draft on the collapsed preview alone, because that is the only part most readers ever see, and treats a flat first line as a failed answer no matter how good the body is. The mediocre version is an answering service: every question covered evenly, every answer polished to the same length and shape, every paragraph closed with a tidy line — a batch that is individually competent and collectively obviously automated.

The output is good when no two answers in a batch share a skeleton or a length, every answer carries at least one mechanic a competitor in the same thread could not have written, nothing was published on a subject the profile has already answered, and the commercial ask appears nowhere but the credential line.

Rules

  • MUST answer from a personal profile with a credential line matched to the topic cluster.
  • MUST carry at least one practitioner-level mechanic in every answer.
  • MUST deliver flagged questions as written answers with the flag attached, never as withheld work — except near-duplicate twins, which are skipped by design with the skip noted.
  • MUST vary opener shape and answer length deliberately across a batch.
  • MUST space a vendor-seeded cluster across days rather than answering it in one sitting.
  • NEVER include a link or a call to action, outside the disclosed "which company is best" pattern.
  • NEVER claim experience with a named product the writer has not used.
  • NEVER post two answers on the same subject from one profile.
  • NEVER answer incoherent or auto-generated questions — that is what farming profiles do.
1---
2name: quora-authority-answering
3title: Quora authority answering
4description: |
5 Use this skill when running a Quora answering program run as a lead generation channel:
6 "answer these Quora questions", "write Quora answers for our founder", "our Quora
7 answers read like AI", "how do we get leads from Quora", "which of these questions
8 should we answer". Produces linkless answers that survive moderation, earn upvotes
9 on the collapsed preview, and convert readers into profile visits, plus the triage
10 and posting order for a batch.
11category: AEO
12tags: [Marketing, Demand Gen]
13---
14 
15# Quora authority answering
16 
17Applies to a personal expert profile answering questions in a commercial category. Produces batches of paste-ready answers, ordered for posting, that teach real methodology and never pitch.
18 
19Most traffic arrives from search months or years after an answer posts, so an answer is an appreciating asset on a permanent URL. The credential line above every answer does all the selling. That is why the answer itself never has to, and why it outperforms the answers that do.
20 
21## Set up the account before answer one
22 
23Answer from a personal profile, never a branded one. Company-voiced accounts read as ads and get collapsed. A credentialed human gets read.
24 
25Set a credential line per topic cluster — role, company, one clause on what the company does for whom — and build the profile bio and links before writing anything. In linkless mode the profile is the only destination. Both assets are specified in `references/credential-and-profile.md`.
26 
27## Triage the batch
28 
29Answer everything in a pasted batch unless the client says otherwise. Raise concerns as flags delivered alongside the work, never as withheld work.
30 
31Four conditions get flagged and still get written: off-position questions, vendor-seeded clusters, tool questions where the tool is unknown, and regulatory questions. Near-duplicate threads are the one deliberate exception — pick the thread with the better traffic and skip the twin, per the triage reference. Each carries its own handling and its own effect on posting order — read `references/triage-flags.md` before sequencing a batch.
32 
33## Pace the posting
34 
35Ten to twenty answers a day is safe. The platform cap sits far higher, near fifty per rolling day, and the count is not what flags accounts — velocity, link density, and thin answers are.
36 
37Spread posts across the day. Fifteen in one sitting looks automated. Ramp a cold account at three to five a day for the first two weeks with no links at all, then scale once there is upvote history.
38 
39## Win the collapsed preview
40 
41The preview shows roughly the first two lines, and that is where the upvote decision starts. Line one carries the whole thesis, stated the way nobody else in the thread will state it.
42 
43Every opener does one of two things: names a target — who is lying, who is getting paid, who is being played — or turns the knife on the reader or on the writer's own industry. Self-implication is the strongest move available. Contrarian alone is cheap on this platform; contrarian while holding the knife toward yourself reads as credible. Register, the capitalization device, and the openers that fail the bar are in `references/opener-craft.md`.
44 
45## Build the body
46 
47Pick one thing per answer to be genuinely worked up about and give it most of the words. Everything else gets a clause. Even, balanced coverage is the loudest machine tell in this format.
48 
49Let paragraph endings fall flat — a kicker on every one produces a rhythm no human sustains. Vary the shape across a batch: an instruction, a refusal of the question's framing, a caveat. Three answers sharing a skeleton reads as templated. Leave loose ends. Keep length deliberately unequal, roughly 90 to 400 words, because a five-line answer standing among eighty long ones is the only thing on that page nobody has to scroll.
50 
51Run `references/machine-tells.md` over the batch before delivery.
52 
53## Carry real method
54 
55Generic operator wisdom is the failure mode. "Do direct outreach" and "focus on quality" teach nothing, and they read as machine-written precisely because they carry no knowledge.
56 
57Every answer holds at least one mechanic only a practitioner knows — how a signal-based list gets built against a database export, what personalization off a job posting looks like next to flattery, how sending infrastructure gets separated across domains and mailboxes, what the operator's own testing turned up. Name real tools where the tool is the answer, and withhold any the client has flagged as unmentionable.
58 
59## Keep it linkless
60 
61Zero links. Zero calls to action. The credential line and the profile carry the commercial load, and that is what keeps answers out of the moderation queue.
62 
63One exception, on "which company is best" questions only: disclose the stake, refuse to rank anyone including themselves, offer free advice by direct message. It works once as a pattern — the sequence and the reason it fails elsewhere are in `references/credential-and-profile.md`.
64 
65## Deliver the batch
66 
67One file per batch, answers numbered in posting order: unanswered and freshly-followed questions first, crowded and stale threads last. Note where a batch exceeds a day's quota so the poster splits it rather than dumping it.
68 
69## What good looks like
70 
71The best operator judges a draft on the collapsed preview alone, because that is the only part most readers ever see, and treats a flat first line as a failed answer no matter how good the body is. The mediocre version is an answering service: every question covered evenly, every answer polished to the same length and shape, every paragraph closed with a tidy line — a batch that is individually competent and collectively obviously automated.
72 
73The output is good when no two answers in a batch share a skeleton or a length, every answer carries at least one mechanic a competitor in the same thread could not have written, nothing was published on a subject the profile has already answered, and the commercial ask appears nowhere but the credential line.
74 
75## Rules
76 
77- MUST answer from a personal profile with a credential line matched to the topic cluster.
78- MUST carry at least one practitioner-level mechanic in every answer.
79- MUST deliver flagged questions as written answers with the flag attached, never as withheld work — except near-duplicate twins, which are skipped by design with the skip noted.
80- MUST vary opener shape and answer length deliberately across a batch.
81- MUST space a vendor-seeded cluster across days rather than answering it in one sitting.
82- NEVER include a link or a call to action, outside the disclosed "which company is best" pattern.
83- NEVER claim experience with a named product the writer has not used.
84- NEVER post two answers on the same subject from one profile.
85- NEVER answer incoherent or auto-generated questions — that is what farming profiles do.
86 
View all files on GitHub →

Details

Updated
Sep 23, 2026
License
MIT
Stars on the repo
★ 159
Checked
Source
swan-gtm/gtm-skills ↗
Creator
swan-gtm · 51 listings
View creator

Similar skills

See all →
SkillReverse engineer native, managed, Electron/JavaScriptREAmorluto/rea · by morlutoReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.★ 316k GitHub starsSkillBrainstorms ideas into designs before any creative workBrainstorming Ideas Into Designsobra/superpowers · by obraYou MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.★ 290k GitHub starsSkillRequires technical rigor and verificationCode Review Receptionobra/superpowers · by obraUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation★ 290k GitHub starsSkillDiagnosis loop for hard bugs and performance regressionsDiagnosing bugsmattpocock/skills · by mattpocockDiagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.★ 267k GitHub starsSkillImplement the result of /to-spec and /to-tickets in codeImplement specmattpocock/skills · by mattpocockImplement the result of /to-spec and /to-tickets in code.★ 267k GitHub starsSkillWriting a PR bodymattpocock/skills · by mattpocockUse when writing a PR body.★ 267k GitHub stars

More from swan-gtm

SkillAn ABM program cannot prove engagement mattersAccount-Based Engagement Scoring and Buying Group Measurementswan-gtm/gtm-skills · by swan-gtmUse this skill when an ABM program cannot prove engagement matters, accounts get handed to sales on gut feel, or nobody knows which activity moves buying groups forward. Builds an account engagement score (weighted signals plus decay), maps buying group coverage across the decision-making unit, and defines explicit handover gates so marketing and sales agree on readiness. Produces a scoring model, a buying group tracker template, and a handover decision rule. Rule: without buying group visibility a high engagement score is a false positive; handover requires both the score and the coverage threshold met. Trigger phrases: ABM measurement, which accounts are hot, buying committee coverage, when do we hand this to sales, account engagement score, ABM ROI.★ 159 GitHub starsSkillWriting ad copy — headline formulas, visual directionAd Copywriting - Headline Formulas, Visual Design & Voice of Customerswan-gtm/gtm-skills · by swan-gtmUse this skill when writing ad copy — headline formulas, visual direction, and voice-of-customer sourcing that makes ads specific instead of generic.★ 159 GitHub starsSkillDefining ad personasAd Persona Frameworkswan-gtm/gtm-skills · by swan-gtmUse this skill when defining ad personas — translating ICP segments into the persona lens every ad, angle, and offer gets built against.★ 159 GitHub starsSkillA percentage in a commercial term is being set, questionedAudit the base not the rateswan-gtm/gtm-skills · by swan-gtmUse this skill when a percentage in a commercial term is being set, questioned, or is producing a number nobody expected — sales commission, revenue share, affiliate and creator payouts, channel margin, agency fees, referral fees, rebates. Triggers: "reps are hitting quota but margin isn't moving", "what does this promo actually cost us", "our partner payouts are higher than the model", "is 15% a fair rate", "we're renegotiating the split", "the comp plan is paying out on deals we lost money on". It finds what the percentage multiplies, identifies the condition under which that choice starts to matter, quantifies the gap at that condition, and identifies the clause to revisit.★ 159 GitHub starsSkillInbound leads arrive incomplete B2B Data Enrichment for Revenue Operationsswan-gtm/gtm-skills · by swan-gtmUse this skill when inbound leads arrive incomplete (missing company size, industry, revenue), the TAM list lacks data for scoring, or the CRM cannot route and segment without enrichment. Maps coverage gaps, compares single-source and waterfall provider strategies, and builds an integration roadmap with cost guardrails and quality gates. Produces a provider recommendation matrix, a waterfall architecture, and a go or no-go checklist. Rule: no single provider has full coverage; a waterfall across two or more providers in sequence beats any one source on match rate. Trigger phrases: data enrichment, leads come in with no company info, enrichment coverage, firmographic data, which enrichment tool, data freshness.★ 159 GitHub starsSkillYou need to know what people are saying about a brandBrand mention monitorswan-gtm/gtm-skills · by swan-gtmUse this skill when you need to know what people are saying about a brand across the web and social — "monitor brand mentions", "what are people saying about [brand] this week", "run a brand sweep", "social listening", "find high-risk mentions", or "how does [brand] compare to [competitor] in the conversation". Sweeps social platforms, news, forums, and review sites; scores every mention on reach, velocity, sentiment, and risk-topic match; and produces a triage report bucketed into Crisis / Watch / Engage / Log with a suggested owner and response window for each mention, so the team responds before one spirals.★ 159 GitHub stars