grainulation/grainulator
Evidence and verification for model-assisted work, with portable workflows and clear next actions.
Sprint analytics — type distributions, stale claims, velocity, prediction scoring
Structural gap analysis -- find what the sprint has not considered.
Generate a compiled decision brief from the current sprint's claims.
Score past predictions against actual outcomes. Closes the feedback loop.
Adversarial testing of a specific claim. Try to disprove it.
Record stakeholder input — new constraints, corrections, or direction changes.
Size-efficient URL fetch with semantic extraction. Use for ad-hoc web research when you want content without the raw HTML overhead.
Use Grainulator to carry a substantial research or engineering task through investigation, implementation, and evidence-backed verification. Use when the user invokes /grainulator or asks for a tracked Grainulator workflow.
Check the unified Grainulator MCP server and local CLI without blocking useful work on optional connectors.
Initialize a dedicated sprint using the unified tool or local CLI while preserving existing data.
Multi-sprint orchestration — view dependency graph, dispatch next ready sprint
Generate a presentation deck from the compiled sprint data.
Pull a sprint from Confluence and import it as local claims.
Execute a multi-pass research investigation, adding claims with evidence.
Adjudicate conflicts between claims that the compiler flagged.
Intent router that detects user intent from plain messages and dispatches to the appropriate skill.
Set up the local Grainulator MCP connection, check capabilities, and initialize the requested sprint.
Show a snapshot of the current sprint -- claims, conflicts, coverage, and next actions.
Publish the current sprint to Confluence as a page with structured content.
Corroborate a claim against an external source URL.