BytesAgain is a curated directory of 60,000+ AI agent skills from ClawHub, GitHub, LobeHub, and Dify. Search skills by keyword in 7 languages, browse by role (developer, creator, trader, marketer) or by use case.

How do I find AI skills on BytesAgain?

Use the search bar on BytesAgain.com to search by keyword in 7 languages. You can also browse by role (developer, creator, trader, marketer) or by use case. Each skill shows install instructions for Claude, Cursor, OpenClaw, Continue, and more.

Yes, BytesAgain is completely free. No registration required for searching skills. The MCP API is also free with rate limits.

Does BytesAgain have an API for AI agents?

Yes! BytesAgain provides a free MCP SSE endpoint at /api/mcp/sse for AI agents, plus a REST API at /api/mcp?action=search&q= . No authentication needed.

Can I request a new AI skill on BytesAgain?

Yes! Visit the Requests page on BytesAgain.com to submit a skill request. Your request will be visible to the community and notified to the site admin.

🦀 ClawHub

Growth Experiment Prioritization Scorer

by @quochungto

Use this skill to score and rank a growth experiment backlog using the ICE framework (Impact, Confidence, Ease — each rated 1–10 and averaged) and select the...

Versionv1.0.0

#crypto #can-make-purchases #clawhub

⚡ When to Use

Trigger	Action
- You have a backlog of growth experiment ideas (5–100+) and need to decide which to run in the next 1–2 week sprint
- Your team keeps gravitating toward familiar or easy tests rather than the highest-impact options
- Experiment selection is happening in the weekly meeting by whoever argues most persuasively, rather than by a pre-meeting scoring process
- You are entering a new growth focus area (acquisition, activation, retention, monetization) and need to groom the idea bank for that area
- You have just used `high-tempo-experiment-cycle` to install a weekly cadence and need to score the initial backlog before the first growth meeting
Prerequisites before using this skill:
- You have a confirmed North Star metric (from `north-star-metric-selector` or from the team's existing documentation). Impact scoring is meaningless without a shared reference metric.
- The backlog exists as a document with at least a name and hypothesis per idea. Vague ideas ("improve onboarding") cannot be scored — they must be made specific first.
---

💡 Examples

Example 1: Series A — 20-Idea Backlog, Activation Sprint

A B2B SaaS team of 5 (growth PM, engineer, designer, marketer, data analyst) has 20 experiment ideas targeting activation — getting new trial users to the "aha moment" (≥3 team members using a shared project within 7 days). North Star: weekly collaborative sessions per team.

The scored backlog (abbreviated) looks like:

| Rank | Experiment | Impact | Confidence | Ease | ICE | Status | |------|------------|--------|------------|------|-----|--------| | 1 | Add progress bar to team setup wizard | 8 | 7 | 9 | 8.0 | Launch now | | 2 | In-app prompt to invite 2nd team member at step 3 | 8 | 8 | 7 | 7.7 | Launch now | | 3 | Email sequence: days 1, 3, 7 post-signup | 7 | 8 | 6 | 7.0 | Launch now | | 4 | Rebuild onboarding checklist UI | 9 | 6 | 3 | 6.0 | Pipeline: next sprint | | 5 | Integration with Slack for task notifications | 8 | 5 | 2 | 5.0 | Pipeline: 3 weeks (eng scoping) | | ... | ... | ... | ... | ... | ... | ... | | 19 | Add mascot to empty state screens | 3 | 4 | 8 | 5.0 | Drop | | 20 | Redesign marketing site hero | 4 | 3 | 2 | 3.0 | Drop |

Sprint selection: The growth PM selects experiments 1, 2, and 3 for the sprint (matching the team's capacity of 2–3 tests per week). Experiment 4 is slotted for the following sprint pending design mockups. Experiment 5 goes to engineering for a scope estimate. Experiments 19 and 20 are dropped — neither has a clear mechanism to increase collaborative sessions, which is the current NSM.

Example 2: Series B — 50-Idea Backlog, Retention Sprint

A marketplace team of 12 (two growth squads: acquisition + retention) needs to groom 50 ideas for a retention sprint targeting 90-day repeat purchase rate. North Star: orders per buyer per quarter.

Scoring challenge: The retention squad notices that 15 of the 50 ideas are acquisition ideas submitted by the other squad — they score well on Impact but target a different focus area. The growth lead moves all 15 to a separate acquisition backlog without scoring them in the retention sprint.

The remaining 35 retention ideas are scored. The top 8 (ICE ≥ 6.5) are selected for the sprint — 4 per squad per week. Ideas ranked 9–20 (ICE 4.5–6.4) are pipelined with dates. Ideas 21–35 (ICE ≤ 4.4) are reviewed for hypothesis quality: 5 are returned to submitters for clarification; 10 are dropped.

Key finding from the scoring: Three ideas that the retention squad assumed were quick (scoring themselves 8 on Ease) were recalibrated to Ease 4 by the growth lead after consulting the engineering team — all three required A/B test infrastructure that was not yet in place. Moving them to the pipeline freed up sprint slots for two mid-ranked ideas (ICE 6.2) that were genuinely fast to ship. The sprint launched on schedule.

View on ClawHub

TERMINAL

clawhub install bookforge-growth-experiment-prioritization-scorer