Curate one project-grounded academic literature snapshot after the Svatah baseline, then inspect its frozen sources and method cards.
3 stars
0 votes
0 copies
2 views
Added September 6, 2026
ai-agentsbash
Security analysis
A100/100
Scanned September 6, 2026
$npx -y skills add bayeslabs-rsi/Svatah --skill literature --agent claude-code
Installs into .claude/skills of the current project.
Are you the author of Literature?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/bayeslabs-rsi-literature)
---
name: literature
description: Curate one project-grounded academic literature snapshot after the Svatah baseline, then inspect its frozen sources and method cards.
argument-hint: <optional status or card query>
---
# Literature Curation
Svatah literature is a run-start input, not an optimization-loop activity.
## Initial Curation
Run this exactly once after the benchmark baseline is committed and
`.sva/project.md` describes the task, inputs, primary metric, constraints, and
baseline:
```bash
sva literature curate --repo-root .
```
The command builds a typed project profile, issues one bounded query to each
configured academic provider, rejects unrelated sources, synthesizes concrete
source-grounded method cards, and freezes the result for the active run.
Resuming the run reuses the same snapshot.
## Read-Only Inspection
```bash
sva literature status --repo-root .
sva literature cards --repo-root . --limit 3
sva literature cards --repo-root . --query "<typed task or mechanism>" --limit 3
```
These commands never access the network. Round plans and subagent briefs may
use only card IDs from this frozen snapshot.
## Manual Revision
Only an operator may replace a frozen snapshot, and only when the project or
benchmark contract materially changed:
```bash
sva literature curate --repo-root . --refresh --reason "<project contract change>"
```
This creates a new revision and preserves the previous revision. Advisors,
critics, recovery rounds, plateau handling, and subagents must never invoke a
refresh automatically.
## Rules
- Do not invoke provider adapters directly or construct an ad hoc query.
- Do not turn hypotheses, critic feedback, experiment IDs, or planner labels
into literature queries.
- Do not claim that an abstract proves an exact implementation.
- A literature-backed experiment must reference a valid frozen method-card ID.
- If curation is empty or unavailable, continue without literature. Do not
retry automatically.