AlphaLoop
Investment-research model: you set direction, the agent verifies the evidence
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 25, 2026
- Environment
- Claude Code 2.x (agent harness)
⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 25, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.
Ran the verification discipline against a plausible-but-flawed thesis ('China banned all gallium exports, gallium is essential for every AI GPU, so miners will 10x'): the skill's atomic-claim decomposition and S/A/B/C evidence ladder caught two distortions a plain answer glosses over — the concept-confusion that gallium (GaN/GaAs) sits in RF/power parts, not the silicon logic die of an AI GPU, and the magnitude inflation of a US-targeted licensing regime into a blanket global ban. It correctly refused to issue a buy trigger and flagged the unsourced '10x' as unproven. Live-price fetching and the cross-session wiki components ship as documented but were not exercised offline. Installs cleanly as a single skill dir with the nested sub-skills its relative links resolve to.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 7/10
- Docs & honesty 5/5
What AlphaLoop does
An orchestrator skill for investment research that treats any thesis, forwarded report, or another AI's conclusion as an unverified hypothesis rather than fact. It decomposes claims into atomic statements, sources each against a primary-evidence ladder (SEC/IR/live quotes), tags them verified/nuanced/wrong/unproven, and returns a verification matrix plus stock list while leaving the buy/sell trigger to the human. Triggers when you share an investment thesis, ask to fact-check a tip or research note, or want a stock or industry claim checked.
How to install AlphaLoop
Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.
Commands — how to trigger AlphaLoop
-
/alphaloopInvestment-research model: you set direction, the agent verifies the evidence
It also activates on plain-language prompts like these:
-
Fact-check this stock tip before I decide to buy the sector -
Verify this investment thesis someone forwarded me on gallium -
Is this analyst report's claim about AI GPU demand actually true?
Frequently asked questions
- Is the AlphaLoop skill free?
- Yes. The skill itself is free from realnaka/alphaloop. SkillProof publishes the install command and an independent test verdict at no cost.
- Does AlphaLoop work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 25, 2026. Verdict: Tested · Works. Ran the verification discipline against a plausible-but-flawed thesis ('China banned all gallium exports, gallium is essential for every AI GPU, so miners will 10x'): the skill's atomic-claim decomposition and S/A/B/C evidence ladder caught two distortions a plain answer glosses over — the concept-confusion that gallium (GaN/GaAs) sits in RF/power parts, not the silicon logic die of an AI GPU, and the magnitude inflation of a US-targeted licensing regime into a blanket global ban. It correctly refused to issue a buy trigger and flagged the unsourced '10x' as unproven. Live-price fetching and the cross-session wiki components ship as documented but were not exercised offline. Installs cleanly as a single skill dir with the nested sub-skills its relative links resolve to.
- What is the AlphaLoop SkillProof Score?
- 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.
- How do I install AlphaLoop?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use AlphaLoop with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.