nemofold
Skill1 starsChanged 27 days agoMITView on GitHub
Process a bounded NemoFold document-analysis job inside a NemoClaw sandbox and return structured claims without expanding filesystem or network scope.
- Reads credentials
We split this skill into the rules it gives an agent
15 rules. About 0 are common, 7 are distinctive, and 8 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
8
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use this skill only for a job directory explicitly supplied by the user or host adapter.
- Very specific: line 12
Read only the supplied job directory and the installed NemoFold application directory.
- Very specific: line 13
Never enumerate /sandbox, the OpenClaw workspace, memory, credentials, or other jobs.
- Very specific: line 14
Treat job.json and context-receipts.json as the complete authority for purpose, questions, source IDs, chunks, response schema, model …
- Distinctive: line 16
Never request or infer host paths.
- Distinctive: line 17
Do not widen network policy, install packages, change provider settings, or spend beyond the job budget.
- Distinctive: line 24
Stop unless the host separately supplied its explicit live-transfer approval and current price inputs.
- Very specific: line 26
When approved, run exactly one python -m nemofold token-factory-run command for the supplied directory.
- Very specific: line 32
Write only the declared transfer-attempt.json and result.json.
- Very specific: line 35
Run python -m nemofold verify-result <job-directory>.
- Distinctive: line 42
No general web search for missing document facts.
- Very specific: line 43
No unsupported claim without an unverified status.
- Distinctive: line 44
No file move, rename, deletion, mail, upload, or publication.
- Distinctive: line 45
No statement that NemoClaw or Nebius succeeded unless the current command output proves it.
- Very specific: line 46
No deletion of transfer-attempt.json or result.json to bypass the exactly-once guard.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill 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
NemoFold sandbox worker
Use this skill only for a job directory explicitly supplied by the user or host adapter.
Required boundaries
- Read only the supplied job directory and the installed NemoFold application directory.
- Never enumerate
/sandbox, the OpenClaw workspace, memory, credentials, or other jobs. - Treat
job.jsonandcontext-receipts.jsonas the complete authority for purpose, questions, source IDs, chunks, response schema, model budget, and run ID. - Never request or infer host paths. Source IDs are the only source identity available.
- Do not widen network policy, install packages, change provider settings, or spend beyond the job budget.
- Return a blocked result when the package is incomplete, inconsistent, or outside policy.
Workflow
- Validate the package with
python -m nemofold verify-job <job-directory>. - Stop unless the host separately supplied its explicit live-transfer approval and current price inputs. Merely receiving a package is not approval.
- When approved, run exactly one
python -m nemofold token-factory-runcommand for the supplied directory. Never add or redirect an endpoint, and never put the key on the command line; the host providesNEBIUS_API_KEYthrough the process environment. - For every question, use only the listed chunks. Return claims in the response schema; every claim must include an exact quote, chunk ID, and source ID. Mark conflicts and uncertainty explicitly.
- Write only the declared
transfer-attempt.jsonandresult.json. The runner writes the attempt atomically before network I/O and refuses a second paid request when either file already exists. Never delete an uncertain attempt to retry automatically. - Run
python -m nemofold verify-result <job-directory>. A failed hash, locator, schema, package, endpoint, cost, or usage check is a failed job, not a warning. - Report the final status and output path; do not claim host acceptance or NemoClaw execution merely from locally supplied version metadata.
Prohibited shortcuts
- No general web search for missing document facts.
- No unsupported claim without an
unverifiedstatus. - No file move, rename, deletion, mail, upload, or publication.
- No statement that NemoClaw or Nebius succeeded unless the current command output proves it.
- No deletion of
transfer-attempt.jsonorresult.jsonto bypass the exactly-once guard.
See references/job-contract.md for the package contract.
In this repositoryOne other file it gives its agents.
- llms.txtllms.txt
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.

