Sales Automator
aiskillstore/marketplace
Draft cold emails, follow-ups, and proposal templates. An agent skill from aiskillstore/marketplace.
Index and shared harness for the 19 signal playbooks. An agent skill from growthenginenowoslawski/coldoutboundskills.
Install Clay Playbooks
$ npx skills add growthenginenowoslawski/coldoutboundskills --skill clay-playbooks -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install growthenginenowoslawski/coldoutboundskills clay-playbooks --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/growthenginenowoslawski/coldoutboundskills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/playbooks/clay-playbooks .claude/skills/clay-playbooks && 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 "clay-playbooks" agent skill from https://github.com/growthenginenowoslawski/coldoutboundskills/tree/main/skills/playbooks/clay-playbooks into .claude/skills/clay-playbooks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clay-playbooks", 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/growthenginenowoslawski/coldoutboundskills/tree/main/skills/playbooks/clay-playbooksType 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 growthenginenowoslawski/coldoutboundskills --skill clay-playbooks -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install growthenginenowoslawski/coldoutboundskills clay-playbooks --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/growthenginenowoslawski/coldoutboundskills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/playbooks/clay-playbooks .agents/skills/clay-playbooks && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "clay-playbooks" agent skill from https://github.com/growthenginenowoslawski/coldoutboundskills/tree/main/skills/playbooks/clay-playbooks into .agents/skills/clay-playbooks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clay-playbooks", 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 growthenginenowoslawski/coldoutboundskills --skill clay-playbooks -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install growthenginenowoslawski/coldoutboundskills clay-playbooks --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/growthenginenowoslawski/coldoutboundskills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/playbooks/clay-playbooks .cursor/skills/clay-playbooks && 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 "clay-playbooks" agent skill from https://github.com/growthenginenowoslawski/coldoutboundskills/tree/main/skills/playbooks/clay-playbooks into .cursor/skills/clay-playbooks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clay-playbooks", 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/growthenginenowoslawski/coldoutboundskills.git --path skills/playbooks/clay-playbooks--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 growthenginenowoslawski/coldoutboundskills --skill clay-playbooks -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install growthenginenowoslawski/coldoutboundskills clay-playbooks --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/growthenginenowoslawski/coldoutboundskills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/playbooks/clay-playbooks .gemini/skills/clay-playbooks && 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 "clay-playbooks" agent skill from https://github.com/growthenginenowoslawski/coldoutboundskills/tree/main/skills/playbooks/clay-playbooks into .gemini/skills/clay-playbooks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clay-playbooks", 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 growthenginenowoslawski/coldoutboundskills clay-playbooksInstalls 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 growthenginenowoslawski/coldoutboundskills --skill clay-playbooks -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/growthenginenowoslawski/coldoutboundskills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/playbooks/clay-playbooks .github/skills/clay-playbooks && 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 "clay-playbooks" agent skill from https://github.com/growthenginenowoslawski/coldoutboundskills/tree/main/skills/playbooks/clay-playbooks into .github/skills/clay-playbooks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clay-playbooks", 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 growthenginenowoslawski/coldoutboundskills --skill clay-playbooks -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install growthenginenowoslawski/coldoutboundskills clay-playbooks --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/growthenginenowoslawski/coldoutboundskills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/playbooks/clay-playbooks .opencode/skills/clay-playbooks && 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 "clay-playbooks" agent skill from https://github.com/growthenginenowoslawski/coldoutboundskills/tree/main/skills/playbooks/clay-playbooks into .opencode/skills/clay-playbooks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clay-playbooks", 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.
Facts
- Skill name
clay-playbooks- GitHub stars
- 753
- Token cost
- ~2.2k tokens
- SKILL.md length
- 1,033 words
- Files
- 3
- Skills in repo
- 49
- Repo updated
- First seen
- Licence
- MIT
At a glance
Index and shared harness for the 19 signal playbooks. An agent skill from growthenginenowoslawski/coldoutboundskills.
- Works in 7 steps: One playbook, one field. If you need two… → Abstain is empty string. Never "N/A",… → The model never establishes a fact.… → …
- Someone says personalize this list
- SKILL.md covers The three run modes, Status: recipes, not verified…, The 19 playbooks and Cost tags, plus 2 more sections
- Needs PROSPEO_API_KEY and OPENAI_API_KEY
What it does
Clay Playbooks is an agent skill from growthenginenowoslawski/coldoutboundskills. Index and shared harness for the 19 signal playbooks. Each playbook turns one buying signal (new in role, raised a round, hiring surge, pricing page, tech on website, ...) into one copy-ready sentence you can drop into a cold email. Every playbook ships three ways to run it: as a Claude skill, as a Clay table built through a browser harness, and as a Clay workflow built from the clay CLI. Use when someone says "personalize this list", "what signal should I use", "build the Clay column for X", or names any of the…
Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `clay-cli-harness.md` and `clay-table-harness.md`).
It sits in Sales & Support, covering Cold outreach and Landing pages. The repository describes itself as: Open-source Claude Code skills for cold email and outbound sales. Grade campaigns, export Prospeo searches, scrape Google Maps — all from Claude Code. The licence is MIT.
When your agent uses it
- Someone says personalize this list
- What signal should I use
- Build the Clay column for X
- Names any of the 19 signals
Example prompts
- “personalize this list”
- “what signal should I use”
- “build the Clay column for X”
- “/clay-playbooks”
Requirements
- A credential in PROSPEO_API_KEY
- A credential in OPENAI_API_KEY
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- One playbook, one field. If you need two signals, run two playbooks and let the copy pick.
- Abstain is empty string. Never "N/A", never "unknown", never a guess. A blank is cheap; a
- The model never establishes a fact. Every fact goes into the prompt already proven by a
- Deterministic fields are computed in code, not by the model. Dates, counts, enums, and
- Gate the paid column. No paid enrichment runs on a row that failed a free upstream check or
- Run 5 rows and read them before you run 5,000. Every playbook has a smoke test. The failure
- No em dashes in generated copy. They read as machine-written. Hyphens in number ranges are
What it can do on your machine
Read from SKILL.md and the folder at commit 25c5d85. It shows what the files ask for, not the result of running them.
Tool permissions
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.
Runs code
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.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
PROSPEO_API_KEYOPENAI_API_KEYSERPER_API_KEYAPIFY_API_TOKENCLAY_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Clay Playbooks loads about 2.2k tokens when it runs. Until then it costs about 136 tokens; SKILL.md has 1,033 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.
Safety
Auto-check: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NoteMentions a .env fileSKILL.md:133
never by value. Copy `.env.example` to `.env`
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.
SKILL.md
The full file from growthenginenowoslawski/coldoutboundskills at commit 25c5d85, republished under its MIT licence (© growthenginenowoslawski). 1,033 words, ~2,172 tokens.
Download SKILL.mdSave it as
.claude/skills/clay-playbooks/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- clay-playbooks
- description
- Index and shared harness for the 19 signal playbooks. Each playbook turns one buying signal (new in role, raised a round, hiring surge, pricing page, tech on website, ...) into one copy-ready sentence you can drop into a cold email. Every playbook ships three ways to run it: as a Claude skill, as a Clay table built through a browser harness, and as a Clay workflow built from the clay CLI. Use when someone says "personalize this list", "what signal should I use", "build the Clay column for X", or names any of the 19 signals.
Clay Playbooks
Nineteen playbooks. Each one answers a single question:
A campaign needs signal X on every row. What is the cheapest reliable way to get X, and what exact prompt turns X into copy-ready text?
One playbook produces one field. new_in_role_line. funding_line. pricing_page_line. That
field slots into one sentence of email 1. That is the whole product.
The three run modes
Every playbook directory ships the same three files. They are three delivery mechanisms for the same recipe, not three different recipes.
| File | What it is | Use it when |
|---|---|---|
SKILL.md | The playbook itself: source chain, output contract, locked prompt, edge cases | You are running the signal from Claude, ad hoc, on a CSV or a one-off list |
clay-table.md | The Clay table build: exact columns, types, formulas, credit gates, AI-column bindings | The signal needs to run continuously on a client table that other people will look at |
clay-workflow.md | The Clay workflow build via the clay CLI: node graph, real action keys, publish and run | You want the signal version-controlled and buildable from a terminal, no UI clicking |
Why tables are browser-driven and workflows are CLI-driven. This is a real constraint, not a
style choice. The clay CLI's tables command group is read-only (list, get, columns,
rows, query) — it cannot create a table or add a column. Tables must be built in the UI.
Workflows are the opposite: clay workflows create / nodes create / publish / runs test
all exist, so a workflow can be built end to end from a terminal.
Shared procedures, written once so the 19 playbooks do not repeat them:
clay-table-harness.md— the generic browser procedure for building any playbook's table.clay-cli-harness.md— the genericclayCLI procedure for building any playbook's workflow.
Read the relevant harness once, then read the playbook's own clay-table.md / clay-workflow.md
for what is specific to that signal.
Status: recipes, not verified builds
⚠️ Read this before you tell anyone a playbook "works".
The SKILL.md in each directory carries a verification line saying what was actually run and on
how many rows. Where it says PASS, real rows were graded.
The clay-table.md and clay-workflow.md files in every playbook are documented recipes that
have not been built and run in a live Clay workspace. They are written against the real Clay
action catalog and the real CLI command surface, so the shapes are right, but nobody has clicked
through the table build or published the workflow. Treat them as specifications. Build one, run it
on 5 rows, read the output, and fix the file before you run it on a list.
The one thing most likely to be wrong on first build is the AI column's reasoning-effort
parameter. See clay-table-harness.md § "The empty-column trap".
The 19 playbooks
Person-level signals (the person did something)
| Playbook | Output field | What it says |
|---|---|---|
playbook-new-in-role | new_in_role_line | they just took this seat |
playbook-linkedin-engagement | engagement_line | they engaged with a relevant post |
playbook-social-posts | social_post_line | they posted about something you can speak to |
playbook-warm-intros | warm_intro_line | you share a real connection |
Company-level signals (the company did something)
| Playbook | Output field | What it says |
|---|---|---|
playbook-fundraising | funding_line | they raised, so they are buying |
playbook-hiring-surge | hiring_line | they are growing the team you sell to |
playbook-job-posting-language | job_language_line | their own job post names your problem |
playbook-ad-library | ad_line | they are spending on ads right now |
Website-derived signals (their site says something)
| Playbook | Output field | What it says |
|---|---|---|
playbook-pricing-page | pricing_page_line | how they price, read off their own page |
playbook-case-study-page | case_study_line | who they brag about serving |
playbook-tech-on-website | tech_line | what they run, detected on the page |
playbook-google-site-search | varies | find any page on their site by keyword |
List-shaping playbooks (they make other playbooks work)
| Playbook | Output field | What it says |
|---|---|---|
playbook-company-name-cleaning | company_name_clean | "Irby Utilities, LLC" becomes "Irby" |
playbook-first-name-cleaning | first_name_clean | "MARIA-JOSE (MJ)" becomes "MJ" |
playbook-social-link-finding | linkedin_url etc. | find the profile you are missing |
playbook-lookalikes | company list | more companies like these |
playbook-name-to-other-prospects | contact list | more buyers at the same company |
Show full SKILL.md (395 more words)Show less
Copy-generation playbooks (they turn signals into words)
| Playbook | Output field | What it says |
|---|---|---|
playbook-ai-specificity | specificity_line | make a generic line concrete |
playbook-creative-ideas | campaign angles | what campaign to run at all |
Cost tags
Every source row in every playbook carries one of these. They are relative to a 1,000-row list.
| Tag | Means |
|---|---|
| FREE | no per-row cost, or included in a flat plan |
| CHEAP | under $1 per 1,000 rows |
| METERED | $1 to $20 per 1,000 rows, scales with volume |
| EXPENSIVE | over $20 per 1,000 rows, or per-row LinkedIn reads |
Rules that apply to all 19
- One playbook, one field. If you need two signals, run two playbooks and let the copy pick.
- Abstain is empty string. Never "N/A", never "unknown", never a guess. A blank is cheap; a confident wrong sentence about someone's own job costs you the account.
- The model never establishes a fact. Every fact goes into the prompt already proven by a structured source. The model's only job is to turn a fact list into one sentence. If you find yourself asking a model "is this true?", you have skipped a source.
- Deterministic fields are computed in code, not by the model. Dates, counts, enums, and anything that branches the copy. Models are for prose.
- Gate the paid column. No paid enrichment runs on a row that failed a free upstream check or that has no valid email. This is the single biggest cost lever in Clay.
- Run 5 rows and read them before you run 5,000. Every playbook has a smoke test. The failure modes are silent: empty columns, unbound variables, and gates that drop every row look identical to "still processing".
- No em dashes in generated copy. They read as machine-written. Hyphens in number ranges are fine.
What you need
Playbooks name credentials by environment variable, never by value. Copy .env.example to .env
and fill in only what the playbooks you actually run require. The common ones:
| Variable | Used by |
|---|---|
PROSPEO_API_KEY | new-in-role, name-to-other-prospects, social-link-finding |
OPENAI_API_KEY | every playbook with a locked prompt |
SERPER_API_KEY (or another SERP provider) | google-site-search, case-study-page, pricing-page |
APIFY_API_TOKEN | ad-library, linkedin-engagement, social-posts |
CLAY_API_KEY | the clay CLI, if you are not using browser OAuth |
Never paste a key into a SKILL.md, a Clay column, or a workflow node body. Clay columns read credentials from the workspace's saved integration auth; the CLI reads them from your shell.
© growthenginenowoslawski, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files in skills/playbooks/clay-playbooks of growthenginenowoslawski/coldoutboundskills.
- SKILL.md
- clay-cli-harness.md
- clay-table-harness.md
Open the folder on GitHubat commit 25c5d85
Compare with similar skills
Clay Playbooks 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 |
|---|---|---|---|---|---|---|
| Clay Playbooks this skillgrowthenginenowoslawski/coldoutboundskills | 753 | — | ~2.2k | Automated safety check: Notes | MIT | |
| Sales Automatoraiskillstore/marketplace | 433 | 7 repos | ~370 | Automated safety check: Pass | None | |
| Prospect Panel SimulatorOneWave-AI/claude-skills | 336 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Cold Outbound Optimizerericosiu/ai-marketing-skills | 3.6k | 1 repos | ~1.7k | 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 |
Similar skills
Prospect Panel Simulator
OneWave-AI/claude-skills
Simulate a panel of your real prospects and buyers to pressure-test sales and marketing before it goes out — cold emails, pitch decks, landing pages, pricing pages, demo scripts, proposals.
Cold Outbound Optimizer
ericosiu/ai-marketing-skills
Design, analyze, and optimize cold outbound email campaigns for Instantly.
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.
Sales Os
romangojiberryAI/gojiberryai-sales-os
A complete outbound sales department in one skill. An agent skill from romangojiberryAI/gojiberryai-sales-os.
Prospecting
Cesarjoquin/Marketing-Skills
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.
More from growthenginenowoslawski/coldoutboundskills
All 49 skills in this repoEmail Deliverability Audit
growthenginenowoslawski/coldoutboundskills
Diagnostic audit for a running cold email program. An agent skill from growthenginenowoslawski/coldoutboundskills.
Icp Onboarding
growthenginenowoslawski/coldoutboundskills
Conversational intake for cold email campaigns. An agent skill from growthenginenowoslawski/coldoutboundskills.
List Builder
growthenginenowoslawski/coldoutboundskills
META skill — build the largest possible qualified lead list for any request, end to end.
Auto Research Public
growthenginenowoslawski/coldoutboundskills
Autonomous cold email campaign launcher. An agent skill from growthenginenowoslawski/coldoutboundskills.
Blitz List Builder
growthenginenowoslawski/coldoutboundskills
Use the Blitz API to find decision-makers at specific companies when you already have a list of company domains.
Deliverability Test Public
growthenginenowoslawski/coldoutboundskills
Compare reply rates, bounce rates, and positive reply rates broken down by inbox type (SMTP / Gmail / Outlook) for a Smartlead account.
Related
Categories
Questions about Clay Playbooks
What does Clay Playbooks do?
Index and shared harness for the 19 signal playbooks. An agent skill from growthenginenowoslawski/coldoutboundskills. Clay Playbooks is an agent skill from growthenginenowoslawski/coldoutboundskills. Index and shared harness for the 19 signal playbooks.
When should I use Clay Playbooks?
Clay Playbooks fits situations like: someone says personalize this list; what signal should I use; build the Clay column for X; names any of the 19 signals.
How do I install Clay Playbooks in Claude Code?
Run `npx skills add growthenginenowoslawski/coldoutboundskills --skill clay-playbooks -a claude-code`. Or copy the skill folder (skills/playbooks/clay-playbooks in growthenginenowoslawski/coldoutboundskills) into .claude/skills/clay-playbooks in your project. Claude Code loads it when a task matches its description.
How do I install Clay Playbooks in Codex?
Run `npx skills add growthenginenowoslawski/coldoutboundskills --skill clay-playbooks -a codex`. Or copy the skill folder (skills/playbooks/clay-playbooks in growthenginenowoslawski/coldoutboundskills) into .agents/skills/clay-playbooks in your project. Codex loads it when a task matches its description.
Can I use Clay Playbooks in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add growthenginenowoslawski/coldoutboundskills --skill clay-playbooks -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/clay-playbooks, .gemini/skills/clay-playbooks, .github/skills/clay-playbooks and .opencode/skills/clay-playbooks in your project.
What does Clay Playbooks need to run?
Going by SKILL.md and its folder, Clay Playbooks needs credentials named PROSPEO_API_KEY, OPENAI_API_KEY, SERPER_API_KEY and APIFY_API_TOKEN. Our summary lists: A credential in PROSPEO_API_KEY; A credential in OPENAI_API_KEY.
Does Clay Playbooks access the network?
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.
Is Clay Playbooks safe to install?
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Clay Playbooks use?
Clay Playbooks is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Clay Playbooks use?
About 2.2k tokens (SKILL.md is roughly 8.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Clay Playbooks?
Skills that share tags, products or a category with Clay Playbooks: Sales Automator (aiskillstore/marketplace, 433 stars), Prospect Panel Simulator (OneWave-AI/claude-skills, 336 stars), Cold Outbound Optimizer (ericosiu/ai-marketing-skills, 3.6k stars) and Prospecting (coreyhaines31/marketingskills, 54k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Clay Playbooks?
growthenginenowoslawski (a GitHub user) maintains it in growthenginenowoslawski/coldoutboundskills, which has 753 GitHub stars. The repository holds 49 skills in this directory. The repository was last updated on October 5, 2026.
Source: growthenginenowoslawski/coldoutboundskills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.