reverse-engineer
llms.txt1 starsChanged 34 days agoMITView on GitHub
An open-source skill pack: reverse engineer a product from public evidence, rebuild it on looot, and request the data sources that are missing. looot (https://looot.ai) is one key and one prepaid balance for 2,500+ data API endpoints from 90+ providers. The agent searches the catalog, sees the price before it runs, and pays per call. A failed call costs nothing.
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- bounded-probeSkill
- claims-auditSkill
- competitor-diffSkill
- evidence-researchSkill
- rebuild-on-loootSkill
- request-providerSkill
- reverse-engineerSkill
- site-teardownSkill
The file
We split this llms.txt into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
No install: read AGENTS.md
≈ “Common” is an estimate: at least 1 in 5 of the 3,592 llms.txt files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
# reverse-engineer > An open-source skill pack: reverse engineer a product from public evidence, rebuild it on looot, and request the data sources that are missing. looot (https://looot.ai) is one key and one prepaid balance for 2,500+ data API endpoints from 90+ providers. The agent searches the catalog, sees the price before it runs, and pays per call. A failed call costs nothing. ## Skills - skills/reverse-engineer/SKILL.md: how a product works, every step tagged observed, inferred or unknown - skills/rebuild-on-looot/SKILL.md: capability map to real looot jobs, then a working app from template/ - skills/request-provider/SKILL.md: confirm a gap, then ask looot and open an issue - skills/bounded-probe/SKILL.md, skills/site-teardown/SKILL.md, skills/evidence-research/SKILL.md, skills/competitor-diff/SKILL.md, skills/claims-audit/SKILL.md: the supporting steps ## Install - MCP: claude mcp add --transport http looot https://api.looot.ai/mcp - Skills: npx skills@1.7.0 add loootai/reverse-engineer - Claude Code plugin: /plugin marketplace add loootai/reverse-engineer - No install: read AGENTS.md ## Free path (no token) - GET https://api.looot.ai/v1/catalog/overview?depth=jobs - GET https://api.looot.ai/v1/public-catalog?q=<words> - Plain GETs of public pages. Read scripts as text and never run them. ## Rules Public information only. Quote before any paid call. Stable idempotency key per call. A run still in progress is pending, not failed. Never put tokens or personal data in a request. ## Links - Examples: examples/ - Template: template/ - Docs: https://docs.looot.ai - Missing provider: the capability_request MCP tool or POST /v1/capability-requests (https://docs.looot.ai/support)
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.