Prospecting
coreyhaines31/marketingskills
When the user wants to find, qualify, and build a list of prospects to reach out to, across B2B SaaS, general B2B, or local small businesses.
A skill your agent uses when you have a conference attendee list and the goal is meetings booked before or during the event, not generic warm-up.
$ npx skills add swan-gtm/gtm-skills --skill pre-conference-outreach -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install swan-gtm/gtm-skills pre-conference-outreach --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/swan-gtm/gtm-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/jeremy-hurst/pre-conference-outreach .claude/skills/pre-conference-outreach && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "pre-conference-outreach" agent skill from https://github.com/swan-gtm/gtm-skills/tree/main/skills/jeremy-hurst/pre-conference-outreach into .claude/skills/pre-conference-outreach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pre-conference-outreach", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/swan-gtm/gtm-skills/tree/main/skills/jeremy-hurst/pre-conference-outreachType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add swan-gtm/gtm-skills --skill pre-conference-outreach -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install swan-gtm/gtm-skills pre-conference-outreach --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/swan-gtm/gtm-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/jeremy-hurst/pre-conference-outreach .agents/skills/pre-conference-outreach && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "pre-conference-outreach" agent skill from https://github.com/swan-gtm/gtm-skills/tree/main/skills/jeremy-hurst/pre-conference-outreach into .agents/skills/pre-conference-outreach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pre-conference-outreach", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add swan-gtm/gtm-skills --skill pre-conference-outreach -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install swan-gtm/gtm-skills pre-conference-outreach --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/swan-gtm/gtm-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/jeremy-hurst/pre-conference-outreach .cursor/skills/pre-conference-outreach && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "pre-conference-outreach" agent skill from https://github.com/swan-gtm/gtm-skills/tree/main/skills/jeremy-hurst/pre-conference-outreach into .cursor/skills/pre-conference-outreach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pre-conference-outreach", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/swan-gtm/gtm-skills.git --path skills/jeremy-hurst/pre-conference-outreach--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add swan-gtm/gtm-skills --skill pre-conference-outreach -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install swan-gtm/gtm-skills pre-conference-outreach --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/swan-gtm/gtm-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/jeremy-hurst/pre-conference-outreach .gemini/skills/pre-conference-outreach && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "pre-conference-outreach" agent skill from https://github.com/swan-gtm/gtm-skills/tree/main/skills/jeremy-hurst/pre-conference-outreach into .gemini/skills/pre-conference-outreach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pre-conference-outreach", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install swan-gtm/gtm-skills pre-conference-outreachInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add swan-gtm/gtm-skills --skill pre-conference-outreach -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/swan-gtm/gtm-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/jeremy-hurst/pre-conference-outreach .github/skills/pre-conference-outreach && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "pre-conference-outreach" agent skill from https://github.com/swan-gtm/gtm-skills/tree/main/skills/jeremy-hurst/pre-conference-outreach into .github/skills/pre-conference-outreach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pre-conference-outreach", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add swan-gtm/gtm-skills --skill pre-conference-outreach -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install swan-gtm/gtm-skills pre-conference-outreach --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/swan-gtm/gtm-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/jeremy-hurst/pre-conference-outreach .opencode/skills/pre-conference-outreach && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "pre-conference-outreach" agent skill from https://github.com/swan-gtm/gtm-skills/tree/main/skills/jeremy-hurst/pre-conference-outreach into .opencode/skills/pre-conference-outreach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pre-conference-outreach", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
pre-conference-outreachA skill your agent uses when you have a conference attendee list and the goal is meetings booked before or during the event, not generic warm-up.
Pre Conference Outreach is an agent skill from swan-gtm/gtm-skills. Use this skill when you have a conference attendee list and the goal is meetings booked before or during the event, not generic warm-up. Every row is researched first, routed to the teammate whose lens matches the contact's real job, and staged as a tight 4-step sequence: a sub-250-character email that names the conference plus one verified angle, a blank connection request, a verbatim side-door offer (exec dinner or a hands-on session), and a short LinkedIn nudge. Scoring tier never skips anyone. Nothing…
Its SKILL.md is about 4.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/setup-customization-checklist.md`).
It sits in Sales & Support. It works with LinkedIn. The repository describes itself as: Open, production-grade GTM skills for AI agents. The licence is MIT.
2 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 67abd04. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Pre Conference Outreach loads about 4.3k tokens when it runs, and up to ~5.2k if it reads all its reference files. Until then it costs about 137 tokens; SKILL.md has 2,403 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from swan-gtm/gtm-skills at commit 67abd04, republished under its MIT licence (© swan-gtm). 2,403 words, ~4,346 tokens.
.claude/skills/pre-conference-outreach/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.Replace every {{...}} before enabling. See the setup checklist reference for the full setup list.
{{EVENT_NAME}} - The conference as people say it in a DM (e.g. "GTM2026", "SaaStr"){{EVENT_CITY}} - Host city, used to pick "hitting the conf?" vs "Making the trip?"{{EVENT_DATES}} - Date range, used to pick "this week" vs "next week" at send time{{EXEC_SIDE_EVENT}} - Your executive side-door offer, as it reads in a sentence (e.g. "an exec dinner on Tuesday night"){{PRACTITIONER_SIDE_EVENT}} - Your hands-on side-door offer (e.g. "a skills hackathon during the conference", "a build session"){{EXEC_SENDER}} - Teammate with the authority lens: talks to whoever owns the problem and its budget{{SALES_LEADER_SENDER}} - Teammate with the seller-management lens: talks to people who manage sellers{{PRACTITIONER_SENDER}} - Teammate with the practitioner lens: talks to hands-on operators of the GTM stack{{EXEC_SENDER_MIN_ORG_SIZE}} - Employee count above which {{EXEC_SENDER}} may send (default: 100){{CRM}} - Your CRM (e.g. HubSpot, Attio, Salesforce){{SIGNAL_LIBRARY}} - Optional: your list of verified third-party angles and how to verify each (funding, hiring, product launches, stack changes){{ATTENDEE_TAG}} - The tag or memory line you use to record "this person attended {{EVENT_NAME}}"{{M1_CHAR_CAP}} - Hard character cap on the first email body (default: 250){{VOICE_GUIDE}} - Optional: a sender's voice guide to load when they are the senderAn attendee list for {{EVENT_NAME}} (or an explicit "run pre-conference outreach on these people") needs sequences that drive a meeting before or during the conference, plus a side-door CTA: {{EXEC_SIDE_EVENT}} for the exec and sales-leader senders, {{PRACTITIONER_SIDE_EVENT}} for the practitioner sender.
This is a reusable play. Swap the event fill-ins when the next conference is the instance. Sequence everyone on the file. Score or scoring tier does not route or skip anyone.
Do not use this play when:
Approval is always queued for a human. There is no auto-send carve-out on this play.
| Fill-in | Value |
|---|---|
{{EVENT_NAME}} | e.g. GTM2026 |
{{EVENT_CITY}} | e.g. NYC |
{{EVENT_DATES}} | e.g. September 28 - October 1 |
{{EXEC_SIDE_EVENT}} | e.g. an exec dinner on Tuesday night |
{{PRACTITIONER_SIDE_EVENT}} | e.g. a skills hackathon during the conference |
Phrasing that depends on timing and location is decided at send time, not hardcoded: "this week" vs "next week"; "hitting the conf?" if they are based in {{EVENT_CITY}} vs "Making the trip?" if they are traveling in.
This is not optional and it is not only a first-party signal scan. Do not draft M1, assign a sender, or stage a sequence for a row until research has run on that domain.
Skipping research because "they're probably cold", "no CRM match", or "it's a list upload" is a failure.
For every row, read both:
If a prior deal exists (open, closed-won, or closed-lost), research the deal context the way your closed-lost re-engagement procedure does. Run it. Do not fork the procedure here. At minimum:
Closed-won or customer (including alias domains) still hits the existing-customer hard stop: do not sequence.
If research surfaces material history (open deal, booked meeting, live thread, closed-lost with a stated "not now", prior trial, another owner working it), do not pretend the account is cold. Use that history as first-party context in M1 when it is still appropriate to sequence, or stop and flag when a standard pre-send gate trips (live unanswered inbound thread, account already engaged, booked meeting, active owner).
Empty memory plus a quiet {{CRM}} feed is still a completed research pass. Then fall through the M1 ladder below. Record what was read in the reasoning log:
research: [memory + CRM records actually read]; prior deal: none | [deal stage + one-line context]
If that line is missing, the research did not happen. Do not build.
This is in addition to your standard live-thread and account-engagement gates, not a substitute for them.
This play overrides tier-based sender routing. Sender is the persona owner for the contact's actual role: judgment on the real job, not a fixed title list. Titles vary wildly company to company ("VP GTM Programs", "Global Head of Revenue Strategy, Ops & Enablement", "GTM Systems & Operations" appear on no list and are exactly the right people). One contact, one sender.
Use a verified employee count when available (a LinkedIn-verified count is the preferred source); otherwise the count already on the account record. State the count and the resulting sender in the reasoning log.
| Sender | When | Mandate | Desired outcome |
|---|---|---|---|
| {{EXEC_SENDER}} | Only if org > {{EXEC_SENDER_MIN_ORG_SIZE}} employees AND the contact owns the problem or the budget (C-level or VP-equivalent who owns GTM systems and tooling decisions) | Authority lens, not hands-on-keyboard | Meeting before or during the conference, and/or {{EXEC_SIDE_EVENT}} |
| {{SALES_LEADER_SENDER}} | People who manage sellers (VP or Head of Sales, VP of Sales Development, Head of SDR/BDR; Director of Sales only if no department head). Also exec-mandate contacts at <= {{EXEC_SENDER_MIN_ORG_SIZE}} employees | Seller-management lens, plus small-org exec fallback | Meeting before or during the conference, and/or {{EXEC_SIDE_EVENT}} |
| {{PRACTITIONER_SENDER}} | Hands-on practitioners (GTM engineers, RevOps who run the stack, growth and funnel leads, director-level marketing ops or GTM systems owners). No employee-count gate. | Practitioner lens | Meeting before or during the conference, and/or {{PRACTITIONER_SIDE_EVENT}} |
Exec size gate (hard): if employee count is {{EXEC_SENDER_MIN_ORG_SIZE}} or below, do not assign {{EXEC_SENDER}} even when the title is CRO, CMO, CEO, or VP RevOps. Route that contact to {{SALES_LEADER_SENDER}} and keep the exec side-door CTA (Scenario 1). If the count is unknown after a reasonable lookup, do not default to {{EXEC_SENDER}}. Use {{SALES_LEADER_SENDER}} and note the unknown count.
Hard exclusions:
If the upload already names a sender, still verify the mandate and the exec size gate; reassign if either fails.
If a row has no resolvable LinkedIn URL, skip the LinkedIn steps and flag the row. Do not invent a URL. If there is no work email after enrichment, fall back to LinkedIn-only rather than emailing a personal inbox.
Load {{VOICE_GUIDE}} when it exists for the chosen sender.
Scenario 1 - Meetings + exec side event ({{EXEC_SENDER}} when over the size gate, otherwise {{SALES_LEADER_SENDER}})
Scenario 2 - Meetings + practitioner side event ({{PRACTITIONER_SENDER}}). M1 can still ask for a meeting. M2 is the only structural change.
| Step | Timing | Channel | Content |
|---|---|---|---|
| 1 / M1 | Day 0 | Conference attendance is the primary hook, tied to a researched angle. Ask for a meeting. Max {{M1_CHAR_CAP}} characters. | |
| 2 | Immediate (same day as M1) | LinkedIn connection request | Blank. No note. Auto-skips if already connected. |
| 3 / M2 | Day 3 | Side-door offer. Verbatim. No name in the message. | |
| 4 / M3 | After M2 (next LinkedIn touch) | LinkedIn DM | Verbatim. No name in the message. |
Who: {{EXEC_SENDER}} (over the size gate + authority-lens contact) or {{SALES_LEADER_SENDER}} (seller-management lens, or exec-mandate at or under the gate).
M1: researched email per the ladder below. Meeting ask.
Step 2: blank connection request.
M2 - email, Day 3, verbatim (no name):
We're also hosting {{EXEC_SIDE_EVENT}} if that's preferable - can shoot over the reg link if interested. Lmk!Do not paste the registration link in the email. Offer to send it.
M3 - LinkedIn DM, verbatim (no name):
tried you on email - in town for {{EVENT_NAME}} this week?Adjust "this week" / "next week" to the actual timing of the send vs the conference. Do not add a name.
Who: {{PRACTITIONER_SENDER}}. The angle should be relevant to technical personas (GTM engineers, RevOps, marketing ops, GTM systems, as examples). Do not use a seller-management angle on this path.
M1: researched email per the ladder below. Meeting ask is still allowed.
Step 2: blank connection request. {{PRACTITIONER_SENDER}} never connects with salespeople or sales managers, so those contacts should not be on this scenario.
M2 - email, Day 3, verbatim (no name):
We're also running {{PRACTITIONER_SIDE_EVENT}} if that's more your speed - can shoot over the details if interested. Lmk!Do not paste the side-event link in the email. Offer to send details.
M3 - LinkedIn DM, verbatim (no name), same as Scenario 1:
tried you on email - in town for {{EVENT_NAME}} this week?Conference attendance is the primary signal and may be named: it is a public, intentional act, the same logic that lets you name an event registration or a profile view. After the mandatory account research, pick the secondary angle with this ladder. Stop at the first that survives.
Never mention that you pulled them from a registration or attendee list. Never dump product in M1.
Hard cap: {{M1_CHAR_CAP}} characters on the M1 email body (count the full message, including the name if used). If a draft exceeds the cap, cut before staging. Do not keep both a long observation and a long ask. Conference + one angle + one meeting ask is the whole message. Record the character count in the reasoning log.
M1 is allowed to ask for time ("How's your sched looking?", "Making the trip?"). This play is exempt from your cold-outreach no-mention, no-pitch, no-CTA rules. A persona-matched pitch check is not applicable on this short cadence: there is no pitch step.
Angle examples (reference only. Write fresh, stay under the cap):
First-party (LinkedIn engagement):
You've been engaging a lot with our content on LinkedIn. Given we're both in {{EVENT_CITY}} this week for {{EVENT_NAME}}, thought it might be a great time to connect. How's your sched looking?
Third-party (GTM scale-up):
Noticed you guys are in rapid GTM scale-up mode. So given we're both in {{EVENT_CITY}} this week for {{EVENT_NAME}}, thought it might be a great opportunity to connect re how AI agents are supporting the scale-up efforts. How's your sched looking?
Third-party (the prospect deploys AI in their own product). Traveling in:
Given the focus on deploying AI agents into call centers, was curious if agents are also driving your own GTM motion. Happy to chat on it live if you're at {{EVENT_NAME}} next week. Making the trip?
Local variant of the close: hitting the conf?
The reasoning log on every sequence must include:
research: + prior deal: line (see HARD STOP)Every row on the file has a research line before it has a draft. Sender was chosen by what the person actually does, and the exec size gate was applied even when the title said CRO. M1 reads like a 30-second note from someone who is also going to be in the room: the conference, one real angle, one ask for time, under the cap. M2 and M3 are word-for-word the verbatim lines, with no name added and no link pasted. Everything sits queued for approval with a reasoning log a colleague could audit.
Spot first: a row with no research line, an account under the size gate assigned to the exec sender, a salesperson routed to the practitioner sender, and an M1 over the cap.
Mediocre looks like: "saw you're attending, want to meet?" sent to everyone with no angle; a pitch paragraph in M1; a dinner link dropped in M2; a hackathon offer sent to a VP Sales; or a closed-lost account sequenced as if it were cold because nobody opened the deal history.
© swan-gtm, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file (references) in skills/jeremy-hurst/pre-conference-outreach of swan-gtm/gtm-skills.
Open the folder on GitHubat commit 67abd04
Pre Conference Outreach next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Pre Conference Outreach this skillswan-gtm/gtm-skills | 172 | — | ~4.3k | Automated safety check: Pass | MIT | |
| Prospectingcoreyhaines31/marketingskills | 54k | — | ~5k | Automated safety check: Pass | MIT | |
| Sales OsromangojiberryAI/gojiberryai-sales-os | 139 | — | ~2k | Automated safety check: Pass | MIT | |
| Lead Generation Research GuideRightNow-AI/openfang | 18k | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| Cold Outreach Personalizeraiskilloftheweek/claude-ai-skill-of-the-week | 149 | — | ~2.6k | Automated safety check: Pass | None | |
| B2B Lead Generationminhnv0807/ai-business-skills | 609 | — | ~1.2k | Automated safety check: Pass | MIT |
coreyhaines31/marketingskills
When the user wants to find, qualify, and build a list of prospects to reach out to, across B2B SaaS, general B2B, or local small businesses.
romangojiberryAI/gojiberryai-sales-os
A complete outbound sales department in one skill. An agent skill from romangojiberryAI/gojiberryai-sales-os.
RightNow-AI/openfang
Reference knowledge for AI lead generation: building an ideal customer profile, researching prospects on the web, enriching lead records and finding email formats.
aiskilloftheweek/claude-ai-skill-of-the-week
Generates hyper-personalized cold outreach messages (email, LinkedIn DM, connection request) from raw prospect research.
minhnv0807/ai-business-skills
Plans B2B pipeline work from ICP definition and prospecting through lead scoring, outbound sequences, sales assets and MQL to SQL handoff, aiming at qualified pipeline.
coreyhaines31/marketingskills
Write and run B2B cold outbound that gets replies, from cold emails and follow-ups to sending setup, LinkedIn, multichannel cadences, and reply handling.
swan-gtm/gtm-skills
Annual and quarterly revenue plan construction, top-down vs bottoms-up reconciliation, plan versioning, stretch goal handling, and FP&A-RevOps collaboration for B2B revenue teams.
swan-gtm/gtm-skills
A skill your agent uses when setting up AI-powered personalization, building Clay or lemlist workflows, or automating prospect research — 6 AI personalization prompts (lemlist style) plus 2 email…
swan-gtm/gtm-skills
A skill your agent uses when a list of people already exists and someone needs to know who on it is worth contacting — event or webinar attendees, registrants, a prospecting export, a CRM segment, a…
swan-gtm/gtm-skills
A skill your agent uses 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…
swan-gtm/gtm-skills
Use this skill before staging a prospect and before drafting any first touch, when a segment has gone silent, and when deciding whether an account is genuinely cold.
swan-gtm/gtm-skills
Use this skill on a monthly cadence to detect champions and heavy users of your paying customers who changed jobs, verify the move against live LinkedIn data, score the new company, and surface…
Works with
Categories
A skill your agent uses when you have a conference attendee list and the goal is meetings booked before or during the event, not generic warm-up. Pre Conference Outreach is an agent skill from swan-gtm/gtm-skills. Use this skill when you have a conference attendee list and the goal is meetings booked before or during the event, not generic warm-up.
Pre Conference Outreach fits situations like: you have a conference attendee list and the goal is meetings booked before; during the event; not generic warm-up.
Run `npx skills add swan-gtm/gtm-skills --skill pre-conference-outreach -a claude-code`. Or copy the skill folder (skills/jeremy-hurst/pre-conference-outreach in swan-gtm/gtm-skills) into .claude/skills/pre-conference-outreach in your project. Claude Code loads it when a task matches its description.
Run `npx skills add swan-gtm/gtm-skills --skill pre-conference-outreach -a codex`. Or copy the skill folder (skills/jeremy-hurst/pre-conference-outreach in swan-gtm/gtm-skills) into .agents/skills/pre-conference-outreach in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add swan-gtm/gtm-skills --skill pre-conference-outreach -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pre-conference-outreach, .gemini/skills/pre-conference-outreach, .github/skills/pre-conference-outreach and .opencode/skills/pre-conference-outreach in your project.
SKILL.md names no scripts, command-line tools or credentials: Pre Conference Outreach is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Pre Conference Outreach is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.3k tokens (SKILL.md is roughly 17k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 864 tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Pre Conference Outreach: Prospecting (coreyhaines31/marketingskills, 54k stars), Sales Os (romangojiberryAI/gojiberryai-sales-os, 139 stars), Lead Generation Research Guide (RightNow-AI/openfang, 18k stars) and Cold Outreach Personalizer (aiskilloftheweek/claude-ai-skill-of-the-week, 149 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
swan-gtm (a GitHub organization) maintains it in swan-gtm/gtm-skills, which has 172 GitHub stars. The repository holds 32 skills in this directory. The repository was last updated on October 8, 2026.
Source: swan-gtm/gtm-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.