Agent skill

launch-qa

Run the pre-launch checklist on a PlusVibe campaign (clean verified leads, filled merge vars, signature and opt-out, spam check, sending settings, reply webhook) and write a pass/fail report.

activeNeeds a keyActs undeclared424 words

Filed under Positioning and messaging.

From sccsadmin11/outbound-gtm-sc · 11 skill entries · 0 · pushed 2026-10-22

What it does when it runs

Run the pre-launch checklist on a PlusVibe campaign (clean verified leads, filled merge vars, signature and opt-out, spam check, sending settings, reply webhook) and write a pass/fail report. Any failure blocks the launch.

Automated analysis of the skill and the 4 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.

Keys and connectors you must supply: PLUSVIBE_API_KEY
Hosts it reaches: app.plusvibe.ai
relay.acme.example
relay.yourdomain.example
Tool permissions it declares: No allowed-tools in the frontmatter. It does act, so it runs under whatever permissions your session already grants.
Actions present in the files: shell

Ask about launch-qa

Opens your assistant with this page's recorded context. Check the linked sources before relying on it.

Is this safe to install?Claude ChatGPT

Adapt it to my stackClaude ChatGPT

What else do I need for it to workClaude ChatGPT

Rather ask a human? Talk to Cheetah

Install it

View source on GitHub ↗

git clone --depth 1 --filter=blob:none --sparse https://github.com/sccsadmin11/outbound-gtm-sc.git /tmp/outbound-gtm-sc
git -C /tmp/outbound-gtm-sc sparse-checkout set "11-qa"
mkdir -p ~/.claude/skills/launch-qa
cp -R "/tmp/outbound-gtm-sc/11-qa/." ~/.claude/skills/launch-qa/

Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗

The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.

Before you install: this skill will not complete its job on a bare agent. It needs PLUSVIBE_API_KEY, which you have to obtain separately.

The skill

Source on GitHub ↗

Reproduced in full from sccsadmin11/outbound-gtm-sc/blob/fc996416957ff6232cc00c3b5c94d601b68e1d61/11-qa/SKILL.md, which is licensed MIT (repository). 424 words, 9 headings.

11 QA

Purpose

One last gate before anything sends. The campaign from skill 09 stays paused until every check here passes. Only this skill can launch it, and only with --launch.

Checks

Check	Passes when
leads_unique	No email appears twice
leads_verified	Every email passed skill 06 (`verify_mv=ok` or `verify_bb=deliverable`) and is not in `rejected_emails.csv`
merge_vars_filled	Every `{{var}}` in every subject and body has a value for every lead. No raw template slot is left
signature_opt_out	The signature and the opt-out line are in every email (text and HTML)
spam_check_passed	`spam_report.json` passed and its hash matches the current `sequence.json`
plusvibe_settings	Daily limit = connected inboxes x 15, send_priority 0.5 (50/50 new vs follow-up), plain text on, open tracking off, every ACTIVE Google inbox connected
webhook_reachable	The relay from skill 10 answers `GET /health`. In `--live` mode a PlusVibe webhook must also point at `<relay>/plusvibe`

Inputs

verified_leads.csv (06 or the copy of it used in 07), rejected_emails.csv (06)
sequence.json (07), spam_report.json (08), campaign_state.json (09)
inboxes_connected.csv (01), relay URL (10)

Outputs

qa_report.json and qa_report.md (see examples/qa_report.md and examples/qa_report_failed.md).
Exit code 0 = pass, 1 = fail.

Env vars

Only for --live: PLUSVIBE_API_KEY, PLUSVIBE_WORKSPACE_ID (https://app.plusvibe.ai/v2/settings/api-access). Live mode only makes GET calls, except --launch.

Steps (agent run instructions)

Offline run on local files:

python 11-qa/scripts/qa.py --leads verified_leads.csv --rejected rejected_emails.csv \
  --sequence sequence.json --spam-report spam_report.json --campaign-state campaign_state.json \
  --inboxes inboxes_connected.csv --relay-url https://relay.yourdomain.example

Live read-back from PlusVibe (read-only):

python 11-qa/scripts/qa.py ...same flags... --live

If a check fails, fix it in the skill that owns it (06 leads, 07 copy, 08 spam, 09 settings, 10 webhook), then run QA again. Never edit the report.

Show the user qa_report.md. Launch only when they say so:

python 11-qa/scripts/qa.py ...same flags... --live --launch --dry-run   # shows the launch call
python 11-qa/scripts/qa.py ...same flags... --live --launch             # starts sending

Notes

The opt-out line defaults to the one in sequence.json. Pass --opt-out to enforce a specific line.
{{sender_first_name}} is filled by PlusVibe from the sending inbox, so it is not required in the lead rows.
TODO: the /hook/list response shape is not documented in detail. QA looks for the relay URL anywhere in the response.

Handoff

PASS -> campaign launched -> replies flow into 10-speed-to-lead. FAIL -> back to the skill named in the report.

Files bundled with it

These load only when the skill asks for them, so they cost nothing until it runs.

Other skills for the same job

Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.

launch by coreyhaines31 · 57,918
launch-strategy by OpenClaudia · 724
hyperframes-product-launch-video by Varnan-Tech · 688
oss-launch-kit by Varnan-Tech · 688
producthunt-launch-kit by Varnan-Tech · 688
vid-product-launch by Varnan-Tech · 688
launch-strategy by shawnpang · 374
launch-it by AIDevGTM · 331

Need help setting it up?

This page tells you what launch-qa does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.

Book a call →

The directory stays free. There is nothing gated behind this.