Marketing Strategist
CoWork-OS/CoWork-OS
Comprehensive marketing strategy across 25 disciplines — positioning, copywriting frameworks, buyer psychology, SEO, CRO, paid ads, funnel architecture, content strategy, growth loops, analytics…
Audits a startup, app or landing page from a URL, localhost, repository, screenshots or copy, then gives a launch-readiness verdict, prioritized fixes and an HTML report.
Install LaunchAudit
$ npx skills add buildfastwithai/gen-ai-experiments --skill launchaudit -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install buildfastwithai/gen-ai-experiments launchaudit --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/buildfastwithai/gen-ai-experiments.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/launchaudit/launchaudit .claude/skills/launchaudit && 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 "launchaudit" agent skill from https://github.com/buildfastwithai/gen-ai-experiments/tree/main/skills/launchaudit/launchaudit into .claude/skills/launchaudit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "launchaudit", 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/buildfastwithai/gen-ai-experiments/tree/main/skills/launchaudit/launchauditType 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 buildfastwithai/gen-ai-experiments --skill launchaudit -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install buildfastwithai/gen-ai-experiments launchaudit --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/buildfastwithai/gen-ai-experiments.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/launchaudit/launchaudit .agents/skills/launchaudit && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "launchaudit" agent skill from https://github.com/buildfastwithai/gen-ai-experiments/tree/main/skills/launchaudit/launchaudit into .agents/skills/launchaudit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "launchaudit", 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 buildfastwithai/gen-ai-experiments --skill launchaudit -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install buildfastwithai/gen-ai-experiments launchaudit --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/buildfastwithai/gen-ai-experiments.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/launchaudit/launchaudit .cursor/skills/launchaudit && 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 "launchaudit" agent skill from https://github.com/buildfastwithai/gen-ai-experiments/tree/main/skills/launchaudit/launchaudit into .cursor/skills/launchaudit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "launchaudit", 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/buildfastwithai/gen-ai-experiments.git --path skills/launchaudit/launchaudit--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 buildfastwithai/gen-ai-experiments --skill launchaudit -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install buildfastwithai/gen-ai-experiments launchaudit --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/buildfastwithai/gen-ai-experiments.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/launchaudit/launchaudit .gemini/skills/launchaudit && 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 "launchaudit" agent skill from https://github.com/buildfastwithai/gen-ai-experiments/tree/main/skills/launchaudit/launchaudit into .gemini/skills/launchaudit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "launchaudit", 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 buildfastwithai/gen-ai-experiments launchauditInstalls 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 buildfastwithai/gen-ai-experiments --skill launchaudit -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/buildfastwithai/gen-ai-experiments.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/launchaudit/launchaudit .github/skills/launchaudit && 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 "launchaudit" agent skill from https://github.com/buildfastwithai/gen-ai-experiments/tree/main/skills/launchaudit/launchaudit into .github/skills/launchaudit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "launchaudit", 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 buildfastwithai/gen-ai-experiments --skill launchaudit -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install buildfastwithai/gen-ai-experiments launchaudit --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/buildfastwithai/gen-ai-experiments.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/launchaudit/launchaudit .opencode/skills/launchaudit && 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 "launchaudit" agent skill from https://github.com/buildfastwithai/gen-ai-experiments/tree/main/skills/launchaudit/launchaudit into .opencode/skills/launchaudit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "launchaudit", 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
launchaudit- GitHub stars
- 785
- Token cost
- ~1.8k tokens
- SKILL.md length
- 916 words
- Files
- 6 (incl. scripts, references)
- Skills in repo
- 13
- Repo updated
- First seen
- Licence
- MIT
At a glance
Audits a startup, app or landing page from a URL, localhost, repository, screenshots or copy, then gives a launch-readiness verdict, prioritized fixes and an HTML report.
- Works in 7 steps: Inspect before asking → Reconstruct the startup → Trace the public journey → …
- Checking whether a landing page or product is ready to launch
- SKILL.md covers Language, Read the references, Select the mode and Workflow, plus 3 more sections
- Runs JavaScript scripts from its folder; calls node
What it does
The agent plays a first-time visitor and launch reviewer: it infers what the product does before asking questions, inspects the public experience, separates evidence from inference and delivers exact fixes in a standalone report. Five modes exist. Standard is the default, quick checks the main page, primary call to action and trust path and returns the verdict with the top five fixes, deep adds product, pricing, docs, install and conversion paths on desktop and mobile, technical stresses broken paths, metadata, accessibility signals and console errors, and before-after compares two versions.
Guardrails are explicit. The agent does not submit forms, create accounts, start trials, install software or make purchases unless you authorize it, and it does not claim a public-page audit can verify private analytics, billing, monitoring, legal compliance or authenticated behavior. The report is written in your language and ends in one of three verdicts: Ready to launch, Launch after critical fixes, or Not ready yet.
References for the evaluation framework and report schema are read before each audit, and scripts/generate_report.mjs with a premium-report.css template produces the HTML file. A repository is inspected only when it is in scope and treated as evidence, not proof that production runs the same version.
When your agent uses it
- Checking whether a landing page or product is ready to launch
- Reviewing positioning, calls to action, trust signals and accessibility on a live site
- Comparing a redesigned page against the previous version with the same criteria
Example prompts
- “Audit my landing page at http://localhost:3000 before we launch next week.”
- “Run a quick LaunchAudit on our pricing page and list the top fixes.”
- “Do a before-after audit of the old and new homepage screenshots in the design folder.”
Requirements
- A live URL, localhost page, repository, screenshots or copy to audit
- Node.js to run the report generator script
- A browser the agent can use to inspect live pages
Workflow steps
7 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 7b62043. 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
Ships 1 file in scripts/ (JavaScript), which the agent can run.
Shell commands in SKILL.md call:
node
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
LaunchAudit loads about 1.8k tokens when it runs, and up to ~4.4k if it reads all its reference files. Until then it costs about 154 tokens; SKILL.md has 916 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); the scripts in this folder are not scanned.
SKILL.md
The full file from buildfastwithai/gen-ai-experiments at commit 7b62043, republished under its MIT licence (© buildfastwithai). 916 words, ~1,848 tokens.
Download SKILL.mdSave it as
.claude/skills/launchaudit/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- launchaudit
- description
- Audit a startup, SaaS, app, developer tool, landing page, or product before launch from a live URL, localhost page, repository, screenshots, or supplied copy. Use when Codex needs to determine what a startup appears to do, test whether its public experience is launch-ready, inspect positioning, calls to action, product proof, trust, UX, accessibility, responsive behavior, broken paths, technical surface, or launch operations, produce a Ready to launch / Launch after critical fixes / Not ready yet verdict, prioritize exact improvements, or create a polished standalone HTML launch-readiness report.
LaunchAudit
Audit the startup as a first-time visitor and launch reviewer. Infer the product before asking questions, inspect the public experience, distinguish evidence from inference, and deliver exact fixes in a standalone report.
Language
- Match the user's language in conversation.
- Write the report in the user's language unless they request another language.
- Preserve product names, URLs, interface labels, and source quotations when accuracy requires it.
Read the references
- Read references/evaluation-framework.md before every audit.
- Read references/report-schema.md before creating the JSON source or HTML report.
Select the mode
standard— Inspect the primary public journey and create the full report. Use by default.quick— Inspect the main page, primary CTA, and most important trust path. Return the verdict and top five fixes.deep— Inspect relevant product, pricing, documentation, trust, install, and conversion paths on desktop and mobile.technical— Emphasize broken paths, metadata, responsive behavior, accessibility signals, console errors, and visible performance risks.before-after— Compare two versions with the same criteria and clearly attribute improvements or regressions.
Do not imply that a public-page audit can verify private analytics, billing, production monitoring, legal compliance, or authenticated product behavior.
Workflow
1. Inspect before asking
- Open the supplied URL or artifact and determine what the startup appears to do, who it serves, the promised outcome, the mechanism, the primary action, and the likely launch stage.
- Prefer the integrated browser for live sites and localhost apps. Inspect visible page state before interacting.
- Follow relevant public navigation and CTA destinations. Do not submit forms, create accounts, begin trials, install software, make purchases, or transmit user data unless the user explicitly authorizes that action.
- Use screenshots when visual hierarchy, responsive behavior, clipping, overlap, or interaction state matters.
- Inspect a supplied repository only when it is in scope. Treat repository findings as product evidence, not proof that production uses the same version.
- Ask only about missing information that would materially change the verdict. The default request should work with only a URL.
2. Reconstruct the startup
State:
- what the product appears to be
- primary audience
- urgent problem or trigger
- promised outcome
- mechanism
- primary CTA
- current alternative
Label each important statement as Observed, Inferred, or Unknown. If the startup cannot be explained accurately after the first screen and one supporting section, treat that as a launch finding rather than asking the founder to explain it.
3. Trace the public journey
Follow the smallest realistic path from first visit to the primary conversion:
- Arrival
- Comprehension
- Evidence
- Risk reduction
- Action
- Confirmation or next-step expectation
Record the exact page, element, or interaction that supports each finding. Do not manufacture analytics or user behavior.
4. Evaluate readiness
Use the weighted system in references/evaluation-framework.md.
- Score only what the inspected evidence supports.
- Mark inaccessible or private criteria as unknown.
- Report both the normalized readiness score and evidence coverage.
- Identify critical blockers before calculating the verdict.
- Never award “Ready to launch” when a primary conversion path is broken, the product cannot be understood, or evidence coverage is too low.
5. Prescribe fixes
For every material issue include:
- diagnosis
- observed evidence
- user or business consequence
- severity
- effort
- confidence
- exact recommended change
- validation method
Provide replacement copy for copy problems. Describe the target component and desired behavior for UI problems. Keep fixes within the inspected evidence; do not prescribe a complete rebrand or rebuild when a focused correction is enough.
Rank:
- Launch blockers
- High-impact fixes
- Quick wins
- Later improvements
Show full SKILL.md (348 more words)Show less
6. Build the seven-day plan
Turn the recommendations into a realistic sequence:
- Day 1: clarify and unblock
- Days 2–3: repair the primary journey
- Days 4–5: add proof and trust
- Day 6: verify responsive and technical surfaces
- Day 7: retest and launch
Adapt the plan when the product needs less or more work. Do not pretend that legal, security, or infrastructure risks can always be fixed in seven days.
7. Create the report
- Serialize the full analysis to
outputs/<startup-slug>-launchaudit.json. - Generate
outputs/<startup-slug>-launchaudit.htmlwith:
node scripts/generate_report.mjs <input.json> <output.html>- Validate the JSON and generated report.
- Inspect the report for missing sections, escaped text, score consistency, and readable colors.
- Return clickable absolute links to both files.
- Keep the JSON beside the HTML so a later audit can compare versions without starting over.
Verdict rules
- Ready to launch — score at least 80, evidence coverage at least 70%, no critical blocker, and the primary path works.
- Launch after critical fixes — score 55–79, or score 80+ with a material blocker that can be corrected without changing the core product.
- Not ready yet — score below 55, the startup remains unclear, the primary path is broken, or the experience lacks enough product reality to support a responsible launch.
Use the more cautious verdict when score and blocker evidence disagree. Explain the override.
Quality bar
- Make the report useful without founder narration.
- Separate product quality from presentation quality.
- Prefer concrete evidence over taste.
- Do not invent customers, traction, analytics, performance measurements, security controls, legal compliance, or production behavior.
- Do not penalize a startup for lacking enterprise features when its audience does not need them.
- Treat accessibility, privacy, security, and legal observations as preliminary unless a qualified audit establishes them.
- Include strengths worth preserving, not only problems.
- End with the next retest and the smallest measurable launch experiment.
Default output
Deliver:
- Reconstructed startup
- Launch verdict, readiness score, and evidence coverage
- Weighted diagnostic scorecard
- Primary journey map
- Critical blockers
- Prioritized improvements with exact fixes
- Copy or interface corrections where useful
- Seven-day action plan
- Retest checklist and launch experiment
- Standalone HTML report and editable JSON source
© buildfastwithai, 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 5 other files (scripts, references) in skills/launchaudit/launchaudit of buildfastwithai/gen-ai-experiments.
- SKILL.md
- agents/openai.yaml
- references/evaluation-framework.md
- references/report-schema.md
- scripts/generate_report.mjs
- templates/premium-report.css
Open the folder on GitHubat commit 7b62043
Compare with similar skills
LaunchAudit 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 |
|---|---|---|---|---|---|---|
| LaunchAudit this skillbuildfastwithai/gen-ai-experiments | 785 | — | ~1.8k | Automated safety check: Pass | MIT | |
| Marketing StrategistCoWork-OS/CoWork-OS | 473 | — | ~893 | Automated safety check: Pass | MIT | |
| Growth Engineeringindranilbanerjee/digital-marketing-pro | 855 | 1 repos | ~4.2k | Automated safety check: Pass | MIT | |
| Marketing For Foundersnpc-live/clawfirm | 156 | — | ~911 | Automated safety check: Pass | None | |
| Homepage Conversion AuditBrianRWagner/ai-marketing-claude-code-skills | 440 | — | ~1.8k | Automated safety check: Pass | None | |
| Ads LandingAgriciDaniel/claude-ads | 9.8k | — | ~612 | Automated safety check: Pass | MIT |
Similar skills
Growth Engineering
indranilbanerjee/digital-marketing-pro
Structured guidance for engineering growth systems — product-led growth motions, referral program design, viral loop mechanics, launch playbooks, retention loops, and affiliate programs — producing…
Marketing For Founders
npc-live/clawfirm
Practical marketing advisor for technical founders building SaaS, apps, or startups from 0 to their first 10/100/1000 users.
Homepage Conversion Audit
BrianRWagner/ai-marketing-claude-code-skills
Audits a homepage or landing page for conversion in quick, standard or deep mode, scoring it by page type and ending with an impact-ranked action plan.
Ads Landing
AgriciDaniel/claude-ads
Audit paid-ad landing pages for message match, mobile experience, performance, accessibility, trust, forms, consent, tracking, security, and conversion friction.
Ship Check
textura-agency/next16-claude-starter
Pre-launch gate for this starter — build, mechanical rule checks, SEO, metadata and brand-kit completeness, the robot form, measured load (Lighthouse people + robot) and scroll (PC + phone)…
More from buildfastwithai/gen-ai-experiments
All 13 skills in this repoLanding Page Generator
buildfastwithai/gen-ai-experiments
Builds a single self-contained HTML landing page from a template with copy frameworks, four themes and SEO meta, then runs bundled audit scripts for conversion and speed.
Talking Avatar Voice Chat App
buildfastwithai/gen-ai-experiments
Builds a realtime voice-chat app around a talking character portrait made from your photo or a text description, with mouth sprites driven by the audio.
Startupblueprint
buildfastwithai/gen-ai-experiments
Turn a startup, SaaS, app, developer tool, website, repository, or product idea into an evidence-backed business plan, monetization strategy, pricing architecture, editable 12-month financial model…
Eazyr Repo Onboarding Kit
buildfastwithai/gen-ai-experiments
Creates a QUICKSTART, doctor scripts and a documented .env.example for an unfamiliar repo from facts scanned in the repo, and audits how easy it is to onboard.
Mutation Test Strength Audit
buildfastwithai/gen-ai-experiments
Measures how well a Python pytest suite catches behavior changes through diff-scoped mutation testing, then proposes and verifies tests for surviving mutants.
Customer Finder
buildfastwithai/gen-ai-experiments
Find and qualify evidence-backed potential first customers, early adopters, design partners, or beta users for a startup using recent public pain and buying signals.
Related
Categories
Questions about LaunchAudit
What does LaunchAudit do?
Audits a startup, app or landing page from a URL, localhost, repository, screenshots or copy, then gives a launch-readiness verdict, prioritized fixes and an HTML report. The agent plays a first-time visitor and launch reviewer: it infers what the product does before asking questions, inspects the public experience, separates evidence from inference and delivers exact fixes in a standalone report. Five modes exist.
When should I use LaunchAudit?
LaunchAudit fits situations like: checking whether a landing page or product is ready to launch; reviewing positioning, calls to action, trust signals and accessibility on a live site; comparing a redesigned page against the previous version with the same criteria.
How do I install LaunchAudit in Claude Code?
Run `npx skills add buildfastwithai/gen-ai-experiments --skill launchaudit -a claude-code`. Or copy the skill folder (skills/launchaudit/launchaudit in buildfastwithai/gen-ai-experiments) into .claude/skills/launchaudit in your project. Claude Code loads it when a task matches its description.
How do I install LaunchAudit in Codex?
Run `npx skills add buildfastwithai/gen-ai-experiments --skill launchaudit -a codex`. Or copy the skill folder (skills/launchaudit/launchaudit in buildfastwithai/gen-ai-experiments) into .agents/skills/launchaudit in your project. Codex loads it when a task matches its description.
Can I use LaunchAudit 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 buildfastwithai/gen-ai-experiments --skill launchaudit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/launchaudit, .gemini/skills/launchaudit, .github/skills/launchaudit and .opencode/skills/launchaudit in your project.
What does LaunchAudit need to run?
Going by SKILL.md and its folder, LaunchAudit needs JavaScript for the scripts in its folder and the command-line tools its instructions call (node). Our summary lists: A live URL, localhost page, repository, screenshots or copy to audit; Node.js to run the report generator script; A browser the agent can use to inspect live pages.
Does LaunchAudit 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 LaunchAudit 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does LaunchAudit use?
LaunchAudit 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 LaunchAudit use?
About 1.8k tokens (SKILL.md is roughly 7.4k 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 2.5k tokens, read only when the agent opens those files.
What are the alternatives to LaunchAudit?
Skills that share tags, products or a category with LaunchAudit: Marketing Strategist (CoWork-OS/CoWork-OS, 473 stars), Growth Engineering (indranilbanerjee/digital-marketing-pro, 855 stars), Marketing For Founders (npc-live/clawfirm, 156 stars) and Homepage Conversion Audit (BrianRWagner/ai-marketing-claude-code-skills, 440 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains LaunchAudit?
buildfastwithai (a GitHub organization) maintains it in buildfastwithai/gen-ai-experiments, which has 785 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on September 22, 2026.
Source: buildfastwithai/gen-ai-experiments on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.