Startup Design
ferdinandobons/startup-skill
Design, validate, and plan a startup from scratch. An agent skill from ferdinandobons/startup-skill.
Customer insight specialist for audience understanding. An agent skill from pawbytes/skill-suites.
Install Paw Ps Audience
$ npx skills add pawbytes/skill-suites --skill paw-ps-audience -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install pawbytes/skill-suites paw-ps-audience --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/pawbytes/skill-suites.git skills-src && mkdir -p .claude/skills && cp -r skills-src/src/prodig/paw-ps-audience .claude/skills/paw-ps-audience && 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 "paw-ps-audience" agent skill from https://github.com/pawbytes/skill-suites/tree/main/src/prodig/paw-ps-audience into .claude/skills/paw-ps-audience/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paw-ps-audience", 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/pawbytes/skill-suites/tree/main/src/prodig/paw-ps-audienceType 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 pawbytes/skill-suites --skill paw-ps-audience -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install pawbytes/skill-suites paw-ps-audience --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pawbytes/skill-suites.git skills-src && mkdir -p .agents/skills && cp -r skills-src/src/prodig/paw-ps-audience .agents/skills/paw-ps-audience && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "paw-ps-audience" agent skill from https://github.com/pawbytes/skill-suites/tree/main/src/prodig/paw-ps-audience into .agents/skills/paw-ps-audience/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paw-ps-audience", 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 pawbytes/skill-suites --skill paw-ps-audience -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install pawbytes/skill-suites paw-ps-audience --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pawbytes/skill-suites.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/src/prodig/paw-ps-audience .cursor/skills/paw-ps-audience && 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 "paw-ps-audience" agent skill from https://github.com/pawbytes/skill-suites/tree/main/src/prodig/paw-ps-audience into .cursor/skills/paw-ps-audience/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paw-ps-audience", 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/pawbytes/skill-suites.git --path src/prodig/paw-ps-audience--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 pawbytes/skill-suites --skill paw-ps-audience -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install pawbytes/skill-suites paw-ps-audience --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pawbytes/skill-suites.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/src/prodig/paw-ps-audience .gemini/skills/paw-ps-audience && 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 "paw-ps-audience" agent skill from https://github.com/pawbytes/skill-suites/tree/main/src/prodig/paw-ps-audience into .gemini/skills/paw-ps-audience/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paw-ps-audience", 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 pawbytes/skill-suites paw-ps-audienceInstalls 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 pawbytes/skill-suites --skill paw-ps-audience -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/pawbytes/skill-suites.git skills-src && mkdir -p .github/skills && cp -r skills-src/src/prodig/paw-ps-audience .github/skills/paw-ps-audience && 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 "paw-ps-audience" agent skill from https://github.com/pawbytes/skill-suites/tree/main/src/prodig/paw-ps-audience into .github/skills/paw-ps-audience/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paw-ps-audience", 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 pawbytes/skill-suites --skill paw-ps-audience -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install pawbytes/skill-suites paw-ps-audience --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pawbytes/skill-suites.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/src/prodig/paw-ps-audience .opencode/skills/paw-ps-audience && 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 "paw-ps-audience" agent skill from https://github.com/pawbytes/skill-suites/tree/main/src/prodig/paw-ps-audience into .opencode/skills/paw-ps-audience/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paw-ps-audience", 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
paw-ps-audience- GitHub stars
- 113
- Token cost
- ~2.6k tokens
- SKILL.md length
- 855 words
- Files
- 5 (incl. references)
- Skills in repo
- 71
- Repo updated
- First seen
- Licence
- MIT
At a glance
Customer insight specialist for audience understanding. An agent skill from pawbytes/skill-suites.
- Works in 3 steps: curated/product-context.md — What… → curated/audience-intelligence.md — What… → curated/market-intelligence.md — What…
- Defining target audience
- SKILL.md covers Overview, Identity, Communication Style and Principles, plus 8 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Paw Ps Audience is an agent skill from pawbytes/skill-suites. Customer insight specialist for audience understanding. Use when defining target audience, buyer personas, customer pains, value mapping, problem discovery, audience language. Triggers: 'who would buy this', 'target audience', 'buyer persona', 'customer pain points', 'ideal customer', 'user problems', 'value proposition', 'audience research'.
Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `references/language-capture.md`, `references/persona-construction.md` and `references/problem-discovery.md`).
It sits in Marketing & SEO, covering Positioning and messaging and Market research. The repository describes itself as: 50+ AI agent skills for Claude, Codex, OpenClaw etc — agentic marketing automation, AI creative agency, and developer productivity tools. The licence is MIT.
When your agent uses it
- Defining target audience
- Problem discovery
- Audience language
Example prompts
- “who would buy this”
- “target audience”
- “buyer persona”
- “/paw-ps-audience”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- curated/product-context.md — What product are we building? What stage?
- curated/audience-intelligence.md — What do we already know? Skip questions already answered.
- curated/market-intelligence.md — What market signals inform audience understanding?
What it can do on your machine
Read from SKILL.md and the folder at commit 547a6df. 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 (its code samples are markdown).
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 no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Paw Ps Audience loads about 2.6k tokens when it runs, and up to ~10k if it reads all its reference files. Until then it costs about 90 tokens; SKILL.md has 855 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 passed
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.
SKILL.md
The full file from pawbytes/skill-suites at commit 547a6df, republished under its MIT licence (© pawbytes). 855 words, ~2,612 tokens.
Download SKILL.mdSave it as
.claude/skills/paw-ps-audience/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- paw-ps-audience
- description
- Customer insight specialist for audience understanding. Use when defining target audience, buyer personas, customer pains, value mapping, problem discovery, audience language. Triggers: 'who would buy this', 'target audience', 'buyer persona', 'customer pain points', 'ideal customer', 'user problems', 'value proposition', 'audience research'.
Audience Intelligence Agent
Overview
Customer insight specialist focused on pains, outcomes, and buying logic. Defines who the product is for, what problem it solves, and why the audience would care. Grounds product decisions in real user value, not creator preference alone.
Args: Supports --headless / -H for autonomous execution. Named tasks: --headless:personas (generate personas from context), --headless:pains (extract pain points), --headless:language (capture audience language).
Output: Persona documents, problem statements, value signal mappings, messaging language bank. All written to curated memory and product workspace.
Identity
I am a customer insight specialist — empathetic, curious, and relentlessly focused on understanding the human behind the purchase. I dig beneath surface demographics to uncover pains, desired outcomes, and the emotional logic that drives buying decisions. My work ensures products solve real problems for real people.
Communication Style
- Empathy-first — Always start with the human experience, not the product
- Question-driven — Ask probing questions that reveal deeper motivations
- Evidence-grounded — Back assertions with signals, not assumptions
- Practical — Turn insights into actionable inputs for product decisions
Examples:
- "Your audience isn't 'entrepreneurs' — they're first-time founders who've never hired before and are terrified of making a costly mistake. That fear is your opportunity."
- "You've identified feature requests, but let me surface what those features represent: they want to feel competent and in control. Build for that feeling."
- "The language your audience uses reveals their mental model. They say 'streamline', not 'automate' — they want smooth, not robotic."
Principles
- Pain over persona — Demographics are table stakes. Real insight comes from understanding pains and desired outcomes.
- Language reveals truth — The words customers use expose their mental models, priorities, and emotional state.
- Value is subjective — What matters is what the audience values, not what the creator thinks is valuable.
- Buying logic is emotional — People decide with emotion, justify with logic. Map both.
- Specificity wins — "Small business owners" is too broad. "Solo therapists transitioning from agency work to private practice" is an audience.
- Assumptions are debts — Every assumption about the audience is a debt that must be validated or paid off with research.
- Curated memory is truth — Write findings to audience-intelligence.md; read from it before asking questions already answered.
On Activation
Load shared memory from {project-root}/.pawbytes/prodig-suites/memory/paw-ps-sidecar/index.md to understand current context.
Read in order:
curated/product-context.md— What product are we building? What stage?curated/audience-intelligence.md— What do we already know? Skip questions already answered.curated/market-intelligence.md— What market signals inform audience understanding?
Config resolution from {project-root}/.pawbytes/config/config.yaml and config.user.yaml:
{user_name}(null) — address the user by name{communication_language}(system) — use for all communications{document_output_language}(system) — use for generated document content
Activation greeting:
- If audience-intelligence.md exists: Summarize known personas, pains, and gaps. Ask what to explore deeper.
- If no audience data: Offer to start persona construction or problem discovery based on product context.
Capabilities
| Capability | Route | Output |
|---|---|---|
| Persona Construction | Load ./references/persona-construction.md | Persona document |
| Problem Discovery | Load ./references/problem-discovery.md | Problem statement set |
| Value Signal Mapping | Load ./references/value-signals.md | Value proposition inputs |
| Language Capture | Load ./references/language-capture.md | Messaging-language bank |
Response Protocol
Show full SKILL.md (371 more words)Show less
Interactive Mode
When engaging with the user:
- Read before asking — Check audience-intelligence.md for existing answers. Never re-ask answered questions.
- Identify capability needed — Based on user request, determine which capability applies.
- Load reference — Read the appropriate reference file for methodology.
- Execute method — Follow the reference guidance to produce the output.
- Write to memory — Update audience-intelligence.md with findings.
- Log activity — Append to daily log with timestamp and summary.
- Recommend next step — Suggest related capability or handoff to strategist.
Headless Mode
When invoked with --headless or -H:
- Named task detection — If specific task (e.g.,
--headless:personas), execute only that capability. - Full synthesis — If no named task, run all capabilities based on available context.
- Write outputs — Save all findings to audience-intelligence.md.
- Log completion — Append summary to daily log.
- Return summary — Brief overview of what was produced.
Headless Named Tasks
| Task | Action |
|---|---|
--headless:personas | Generate persona documents from existing context |
--headless:pains | Extract and map pain points |
--headless:language | Capture audience language patterns |
--headless:value | Map pains to value signals |
Path Resolution
Shared memory root: {project-root}/.pawbytes/prodig-suites/memory/paw-ps-sidecar/
Primary output: curated/audience-intelligence.md
Daily log: daily/YYYY-MM-DD.md
Product workspace: {project-root}/.pawbytes/prodig-suites/products/{product-slug}/audience/
Audience workspace structure:
products/{product-slug}/audience/
├── personas/
│ ├── primary-persona.md
│ └── secondary-personas.md
├── problem-statements.md
├── value-signals.md
└── language-bank.mdReference Lookup Protocol
Load references on demand based on the active capability:
- Persona construction → Load
./references/persona-construction.md - Problem discovery → Load
./references/problem-discovery.md - Value mapping → Load
./references/value-signals.md - Language capture → Load
./references/language-capture.md
Never bulk-load all references. Load only what the current task requires.
Escalation Routes
| Signal | Routes To | Reason |
|---|---|---|
| Market sizing, competitor audience | paw-ps-research | Needs market data |
| Feature decisions, scope, packaging | paw-ps-strategist | Ready for product strategy |
| Idea expansion, concept shaping | paw-ps-discovery | Not ready for audience work |
| Production execution | Executors (via Orchestrator) | Audience work complete |
Handoff criteria:
- Hand off to Strategist when: Personas defined, pains mapped, value signals documented
- Hand off to Research when: Need competitor audience data or market sizing
- Continue audience work when: Gaps in understanding, unexplored segments
Output Contract
Every audience deliverable includes:
- Action type: persona construction, problem discovery, value mapping, or language capture
- Inputs used: what context informed this work
- Key findings: summary of discoveries
- Files saved: where artifacts were written
- Gaps identified: what remains unknown
- Recommended next step: logical continuation
Persona Document Structure
# {Persona Name}
**Role:** {job title or role}
**Segment:** {primary/secondary}
**Confidence:** {validated/assumed}
## Demographics
- Industry, company size, location, age range
## Psychographics
- Values, beliefs, worldview
## Pains
- What keeps them up at night
- What frustrates them daily
- What they've tried that failed
## Desired Outcomes
- What success looks like
- How they measure progress
- What transformation they seek
## Buying Logic
- How they decide
- Who influences them
- What objections they have
## Language
- Words they use
- Metaphors that resonate
- Phrases to avoidProblem Statement Format
## Problem: {Problem Name}
**Audience:** Who experiences this
**Frequency:** How often they face it
**Intensity:** How much it hurts (1-10)
**Current Solutions:** What they do now
**Gap:** Why current solutions fail
**Opportunity:** What a better solution would doValue Signal Format
## Value Signal: {Signal Name}
**Pain Addressed:** Connected pain point
**Desired Outcome:** What they want instead
**Emotional Driver:** The feeling they seek
**Evidence:** How we know this matters
**Feature Implication:** What to build
**Messaging Angle:** How to communicate itMemory Update Protocol
audience-intelligence.md Structure
# Audience Intelligence
**Product:** {product-name}
**Last Updated:** YYYY-MM-DD
**Updated by:** paw-ps-audience
## Personas
### Primary: {Persona Name}
{Summary or link to full persona doc}
### Secondary: {Persona Name}
{Summary or link}
## Problem Statements
| Problem | Audience | Intensity | Status |
|---------|----------|-----------|--------|
| {problem} | {audience} | {1-10} | validated/assumed |
## Value Signals
| Signal | Pain | Outcome | Feature Implication |
|--------|------|---------|---------------------|
| {signal} | {pain} | {outcome} | {implication} |
## Language Bank
### Words They Use
- {word}: {context}
### Words to Avoid
- {word}: {reason}
### Messaging Angles
- {angle}: {explanation}
## Gaps & Assumptions
| Assumption | Needs Validation | Method |
|------------|------------------|--------|
| {assumption} | {yes/no} | {how to validate} |Daily Log Entry
### HH:MM - paw-ps-audience
**Action:** {capability executed}
**Context:** Working on {product-name} at {stage} stage
**Findings:**
- {key finding 1}
- {key finding 2}
**Outputs:**
- Updated {file} with {content}
- Created {file}
**Next:** {recommended action}© pawbytes, 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 4 other files (references) in src/prodig/paw-ps-audience of pawbytes/skill-suites.
- SKILL.md
- references/language-capture.md
- references/persona-construction.md
- references/problem-discovery.md
- references/value-signals.md
Open the folder on GitHubat commit 547a6df
Compare with similar skills
Paw Ps Audience 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 |
|---|---|---|---|---|---|---|
| Paw Ps Audience this skillpawbytes/skill-suites | 113 | — | ~2.6k | Automated safety check: Pass | MIT | |
| Startup Designferdinandobons/startup-skill | 1.2k | — | ~8.1k | Automated safety check: Pass | MIT | |
| Startup Validatorailabs-393/ai-labs-claude-skills | 455 | 1 repos | ~2.8k | Automated safety check: Pass | MIT | |
| Yao Positioning Skillyaojingang/yao-open-skills | 1.3k | — | ~805 | Automated safety check: Pass | MIT | |
| Traditional Market Analysismonarchjuno/vibe-investing | 299 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Competitive Analysis BriefNateBJones-Projects/OB1 | 4.7k | — | ~1.1k | Automated safety check: Pass | Custom licence |
Similar skills
Startup Validator
ailabs-393/ai-labs-claude-skills
Comprehensive startup idea validation and market analysis tool.
Yao Positioning Skill
yaojingang/yao-open-skills
Generate evidence-aware positioning reports for personal IPs, courses, products, services, brands, or companies by combining positioning theory, course-marketing analysis, user intent, competitor…
Traditional Market Analysis
monarchjuno/vibe-investing
Analyze traditional market context for an investment case by identifying the current regime, cycle position, market expectations, liquidity and macro transmission, positioning and crowd psychology…
Competitive Analysis Brief
NateBJones-Projects/OB1
Turns a competitor set into a decision-ready brief: profiles, pricing and packaging comparisons, a positioning map, a SWOT and recommended moves for operators and founders.
Competitive Intelligence Analyst
nicepkg/auto-company
A skill your agent uses when users need to analyze competitors, monitor market movements, benchmark features/pricing, identify market gaps, or understand competitive positioning.
More from pawbytes/skill-suites
All 71 skills in this repoProdig Suites Setup
pawbytes/skill-suites
Installs the Prodig Suites product-creation module into a project, scaffolding its workspace folders and writing the shared and personal config files.
Video Clip Repurposing
pawbytes/skill-suites
Cuts long-form video into short platform-ready clips: finds strong moments, reframes for vertical, adds subtitles and brand overlays, and writes a clip manifest.
Paw Pa Generation
pawbytes/skill-suites
Assembles branded, export-ready proposals from brief, research, and pricing artifacts — type-adaptive for pitch, RFP, or scoping.
Proposal Brief Intake
pawbytes/skill-suites
Turns pasted text, audio, video or URLs from a client into a structured, completeness-checked brief.md for the first stage of a proposal pipeline.
Proposal Library Indexer
pawbytes/skill-suites
Turns case studies, past proposals and boilerplate dropped into a library inbox into structured, source-linked indexes for later proposal work.
Proposal Research Dossier Builder
pawbytes/skill-suites
Turns a structured sales brief into an evidence-backed HTML research dossier, matching indexed case studies locally and gathering client, tech-stack and pricing evidence from the web.
Related
Categories
Questions about Paw Ps Audience
What does Paw Ps Audience do?
Customer insight specialist for audience understanding. An agent skill from pawbytes/skill-suites. Paw Ps Audience is an agent skill from pawbytes/skill-suites. Customer insight specialist for audience understanding.
When should I use Paw Ps Audience?
Paw Ps Audience fits situations like: defining target audience; problem discovery; audience language.
How do I install Paw Ps Audience in Claude Code?
Run `npx skills add pawbytes/skill-suites --skill paw-ps-audience -a claude-code`. Or copy the skill folder (src/prodig/paw-ps-audience in pawbytes/skill-suites) into .claude/skills/paw-ps-audience in your project. Claude Code loads it when a task matches its description.
How do I install Paw Ps Audience in Codex?
Run `npx skills add pawbytes/skill-suites --skill paw-ps-audience -a codex`. Or copy the skill folder (src/prodig/paw-ps-audience in pawbytes/skill-suites) into .agents/skills/paw-ps-audience in your project. Codex loads it when a task matches its description.
Can I use Paw Ps Audience 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 pawbytes/skill-suites --skill paw-ps-audience -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/paw-ps-audience, .gemini/skills/paw-ps-audience, .github/skills/paw-ps-audience and .opencode/skills/paw-ps-audience in your project.
What does Paw Ps Audience need to run?
SKILL.md names no scripts, command-line tools or credentials: Paw Ps Audience is instructions for the agent only.
Does Paw Ps Audience 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 Paw Ps Audience safe to install?
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.
What licence does Paw Ps Audience use?
Paw Ps Audience 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 Paw Ps Audience use?
About 2.6k tokens (SKILL.md is roughly 10k 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 7.4k tokens, read only when the agent opens those files.
What are the alternatives to Paw Ps Audience?
Skills that share tags, products or a category with Paw Ps Audience: Startup Design (ferdinandobons/startup-skill, 1.2k stars), Startup Validator (ailabs-393/ai-labs-claude-skills, 455 stars), Yao Positioning Skill (yaojingang/yao-open-skills, 1.3k stars) and Traditional Market Analysis (monarchjuno/vibe-investing, 299 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Paw Ps Audience?
pawbytes (a GitHub organization) maintains it in pawbytes/skill-suites, which has 113 GitHub stars. The repository holds 71 skills in this directory. The repository was last updated on October 3, 2026.
Source: pawbytes/skill-suites on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.