Customer Deck Builder
zapier/gtm-cheat-codes
Builds a tailored sales or customer success deck from approved CRM context and generates it in Gamma through Zapier MCP for calls like QBRs or renewals.
Predicts retention potential by evaluating usage frequency, habit formation mechanics, and churn risk factors for a B2C app idea.
Install Retention Predictor
$ npx skills add MaxKmet/idea-validation-agents --skill retention-predictor -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install MaxKmet/idea-validation-agents retention-predictor --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/MaxKmet/idea-validation-agents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/retention-predictor .claude/skills/retention-predictor && 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 "retention-predictor" agent skill from https://github.com/MaxKmet/idea-validation-agents/tree/main/skills/retention-predictor into .claude/skills/retention-predictor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "retention-predictor", 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/MaxKmet/idea-validation-agents/tree/main/skills/retention-predictorType 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 MaxKmet/idea-validation-agents --skill retention-predictor -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install MaxKmet/idea-validation-agents retention-predictor --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MaxKmet/idea-validation-agents.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/retention-predictor .agents/skills/retention-predictor && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "retention-predictor" agent skill from https://github.com/MaxKmet/idea-validation-agents/tree/main/skills/retention-predictor into .agents/skills/retention-predictor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "retention-predictor", 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 MaxKmet/idea-validation-agents --skill retention-predictor -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install MaxKmet/idea-validation-agents retention-predictor --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MaxKmet/idea-validation-agents.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/retention-predictor .cursor/skills/retention-predictor && 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 "retention-predictor" agent skill from https://github.com/MaxKmet/idea-validation-agents/tree/main/skills/retention-predictor into .cursor/skills/retention-predictor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "retention-predictor", 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/MaxKmet/idea-validation-agents.git --path skills/retention-predictor--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 MaxKmet/idea-validation-agents --skill retention-predictor -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install MaxKmet/idea-validation-agents retention-predictor --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MaxKmet/idea-validation-agents.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/retention-predictor .gemini/skills/retention-predictor && 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 "retention-predictor" agent skill from https://github.com/MaxKmet/idea-validation-agents/tree/main/skills/retention-predictor into .gemini/skills/retention-predictor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "retention-predictor", 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 MaxKmet/idea-validation-agents retention-predictorInstalls 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 MaxKmet/idea-validation-agents --skill retention-predictor -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/MaxKmet/idea-validation-agents.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/retention-predictor .github/skills/retention-predictor && 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 "retention-predictor" agent skill from https://github.com/MaxKmet/idea-validation-agents/tree/main/skills/retention-predictor into .github/skills/retention-predictor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "retention-predictor", 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 MaxKmet/idea-validation-agents --skill retention-predictor -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install MaxKmet/idea-validation-agents retention-predictor --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MaxKmet/idea-validation-agents.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/retention-predictor .opencode/skills/retention-predictor && 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 "retention-predictor" agent skill from https://github.com/MaxKmet/idea-validation-agents/tree/main/skills/retention-predictor into .opencode/skills/retention-predictor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "retention-predictor", 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
retention-predictor- GitHub stars
- 477
- Token cost
- ~577 tokens
- SKILL.md length
- 191 words
- Files
- 1
- Skills in repo
- 15
- Repo updated
- First seen
- Licence
- MIT
At a glance
Predicts retention potential by evaluating usage frequency, habit formation mechanics, and churn risk factors for a B2C app idea.
- Works in 5 steps: Estimate natural usage frequency based… → Identify external triggers that would… → Score habit formation potential (1–5)… → …
- Tasks that involve Customer success
- SKILL.md covers Purpose, Input, Evaluation Factors and Process, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Retention Predictor is an agent skill from MaxKmet/idea-validation-agents. Predicts retention potential by evaluating usage frequency, habit formation mechanics, and churn risk factors for a B2C app idea.
Its SKILL.md is about 580 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Sales & Support, covering Customer success. The repository describes itself as: AI agents that act as your personal venture analyst - from startup idea brainstorming to full validation and go-to-market strategy. Built for developers who'd rather validate in… The licence is MIT.
When your agent uses it
- Tasks that involve Customer success
Example prompts
- “Use the retention-predictor skill to predict retention potential by evaluating usage frequency, habit formation mechanics, and churn risk factors…”
- “/retention-predictor”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Estimate natural usage frequency based on the problem (daily tooth brushing vs. annual tax filing).
- Identify external triggers that would cue app usage.
- Score habit formation potential (1–5) across the six factors above.
- Estimate D1, D7, D30 retention benchmarks for the app category.
- Flag high churn risk factors.
What it can do on your machine
Read from SKILL.md and the folder at commit 3a4c800. 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 json).
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
Retention Predictor loads about 577 tokens when it runs. Until then it costs about 37 tokens; SKILL.md has 191 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 MaxKmet/idea-validation-agents at commit 3a4c800, republished under its MIT licence (© MaxKmet). 191 words, ~577 tokens.
Download SKILL.mdSave it as
.claude/skills/retention-predictor/SKILL.md (or your agent's skills folder).- name
- retention-predictor
- description
- Predicts retention potential by evaluating usage frequency, habit formation mechanics, and churn risk factors for a B2C app idea.
<!-- version: 0.1.0 | outputs: memory/ideas/<slug>/retention.json -->Skill: retention-predictor
Purpose
Retention determines LTV. An app that churns users in week 1 can't build a business regardless of acquisition. This skill evaluates how sticky the idea is structurally — not based on feature lists, but on the underlying usage pattern and habit formation potential.
Input
- Idea slug
- App concept description
memory/ideas/<slug>/desire_scores.json(desire strength informs habit potential)memory/ideas/<slug>/user_extraction.json(usage frequency from pain map)
Evaluation Factors
| Factor | High Retention Signal | Low Retention Signal |
|---|---|---|
| Usage frequency | Daily or multiple times/day | Weekly or less |
| External trigger | Clear real-world trigger (meal, workout, payday) | No natural trigger |
| Progress/reward loop | Clear progress visible over time | No feedback loop |
| Network effects | Gets better with more users | No network component |
| Data lock-in | User data accumulates | Nothing to lose by leaving |
| Habit stack | Fits into existing daily routine | Requires behavior change |
Process
<!-- TODO: Add D1/D7/D30 retention benchmark database by app category --><!-- TODO: Add churn risk scoring rubric -->- Estimate natural usage frequency based on the problem (daily tooth brushing vs. annual tax filing).
- Identify external triggers that would cue app usage.
- Score habit formation potential (1–5) across the six factors above.
- Estimate D1, D7, D30 retention benchmarks for the app category.
- Flag high churn risk factors.
Output
Write to memory/ideas/<slug>/retention.json:
{
"natural_usage_frequency": "multiple daily | daily | weekly | monthly | infrequent",
"external_trigger": "",
"habit_formation_score": 0,
"churn_risk_factors": [],
"estimated_retention": {
"d1": 0,
"d7": 0,
"d30": 0
},
"churn_risk": "low | medium | high",
"retention_verdict": "sticky | moderate | disposable"
}Notes
<!-- TODO: Cross-reference with desire_scores — survival/control desires = higher retention -->© MaxKmet, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/retention-predictor of MaxKmet/idea-validation-agents.
Open the folder on GitHubat commit 3a4c800
Compare with similar skills
Retention Predictor 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 |
|---|---|---|---|---|---|---|
| Retention Predictor this skillMaxKmet/idea-validation-agents | 477 | — | ~577 | Automated safety check: Pass | MIT | |
| Customer Deck Builderzapier/gtm-cheat-codes | 342 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Cs Health Scorecardmohitagw15856/pm-claude-skills | 1.4k | — | ~2.4k | Automated safety check: Pass | MIT | |
| Youtube SearchZeroPointRepo/youtube-skills | 1k | 1 repos | ~1.8k | Automated safety check: Pass | MIT | |
| YtZeroPointRepo/youtube-skills | 1k | 1 repos | ~951 | Automated safety check: Pass | MIT | |
| Loki Modedavila7/claude-code-templates | 32k | 7 repos | ~7.1k | Automated safety check: Warn | MIT |
Similar skills
- Official
Cs Health Scorecard
mohitagw15856/pm-claude-skills
Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.
Youtube Search
ZeroPointRepo/youtube-skills
A skill your agent uses when the user wants to find YouTube content on any topic: searching for videos or channels, finding creators who cover a subject, discovering tutorials, talks, or expert…
Yt
ZeroPointRepo/youtube-skills
A skill your agent uses when YouTube is relevant: pasted video links or IDs, @handles, quick video lookups, summaries, channel latest uploads, topic search, or any request involving YouTube content…
Loki Mode
davila7/claude-code-templates
Multi-agent autonomous startup system for Claude Code. An agent skill from davila7/claude-code-templates.
Account Research
explorium-ai/gtm-skills
Account research skill for Claude Code and Codex: generate a high-signal company intelligence brief including firmographics, technographics, funding history, hiring signals, business events, recent…
More from MaxKmet/idea-validation-agents
All 15 skills in this repoCac Modeler
MaxKmet/idea-validation-agents
Models LTV, CAC by channel, LTV:CAC ratios, and payback period for an indie developer.
Competitor Mapper
MaxKmet/idea-validation-agents
Maps the full competitive landscape — direct, indirect, substitute, and emerging competitors — with positioning gap analysis, review mining, and marketinsights-calibrated saturation scoring.
Decision Memo
MaxKmet/idea-validation-agents
Writes a concise, human-readable decision brief summarizing the full validation analysis — including score, verdict, RAT experiment, pre-mortem, and tier-appropriate next actions.
Desire Evaluator
MaxKmet/idea-validation-agents
Scores the strength of core human desire motivations (survival, status, belonging, control, curiosity) for a given app idea to predict user pull and retention potential.
Distribution Analysis
MaxKmet/idea-validation-agents
Evaluates organic reach potential, paid feasibility, platform distribution advantages, creator economy fit, and founder edge for a B2C app idea.
Idea Scoring
MaxKmet/idea-validation-agents
Aggregates all dimension scores into a final idea score (0–100) and issues a verdict.
Related
Categories
Questions about Retention Predictor
What does Retention Predictor do?
Predicts retention potential by evaluating usage frequency, habit formation mechanics, and churn risk factors for a B2C app idea. Retention Predictor is an agent skill from MaxKmet/idea-validation-agents. Predicts retention potential by evaluating usage frequency, habit formation mechanics, and churn risk factors for a B2C app idea.
When should I use Retention Predictor?
Retention Predictor fits situations like: tasks that involve Customer success.
How do I install Retention Predictor in Claude Code?
Run `npx skills add MaxKmet/idea-validation-agents --skill retention-predictor -a claude-code`. Or copy the skill folder (skills/retention-predictor in MaxKmet/idea-validation-agents) into .claude/skills/retention-predictor in your project. Claude Code loads it when a task matches its description.
How do I install Retention Predictor in Codex?
Run `npx skills add MaxKmet/idea-validation-agents --skill retention-predictor -a codex`. Or copy the skill folder (skills/retention-predictor in MaxKmet/idea-validation-agents) into .agents/skills/retention-predictor in your project. Codex loads it when a task matches its description.
Can I use Retention Predictor 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 MaxKmet/idea-validation-agents --skill retention-predictor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/retention-predictor, .gemini/skills/retention-predictor, .github/skills/retention-predictor and .opencode/skills/retention-predictor in your project.
What does Retention Predictor need to run?
SKILL.md names no scripts, command-line tools or credentials: Retention Predictor is instructions for the agent only.
Does Retention Predictor 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 Retention Predictor 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 Retention Predictor use?
Retention Predictor 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 Retention Predictor use?
About 577 tokens (SKILL.md is roughly 2.3k 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 Retention Predictor?
Skills that share tags, products or a category with Retention Predictor: Customer Deck Builder (zapier/gtm-cheat-codes, 342 stars), Cs Health Scorecard (mohitagw15856/pm-claude-skills, 1.4k stars), Youtube Search (ZeroPointRepo/youtube-skills, 1k stars) and Yt (ZeroPointRepo/youtube-skills, 1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Retention Predictor?
MaxKmet (a GitHub user) maintains it in MaxKmet/idea-validation-agents, which has 477 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on June 16, 2026.
Source: MaxKmet/idea-validation-agents on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.