All authors
Claude Skills by grainulation
github.com/grainulation21 skills0 installs63 views
- Blind SpotStructural gap analysis -- find what the sprint has not considered.Votes: 0GitHub stars: 86
- BriefGenerate a compiled decision brief from the current sprint's claims.Votes: 0GitHub stars: 86
- CalibrateScore past predictions against actual outcomes. Closes the feedback loop.Votes: 0GitHub stars: 86
- ChallengeAdversarial testing of a specific claim. Try to disprove it.Votes: 0GitHub stars: 86
- FeedbackRecord stakeholder input — new constraints, corrections, or direction changes.Votes: 0GitHub stars: 86
- FetchSize-efficient URL fetch with semantic extraction. Use for ad-hoc web research when you want content without the raw HTML overhead.Votes: 0GitHub stars: 86
- HealthcheckCheck the unified Grainulator MCP server and local CLI without blocking useful work on optional connectors.Votes: 0GitHub stars: 86
- InitInitialize a dedicated sprint using the unified tool or local CLI while preserving existing data.Votes: 0GitHub stars: 86
- PresentGenerate a presentation deck from the compiled sprint data.Votes: 0GitHub stars: 86
- PullPull a sprint from Confluence and import it as local claims.Votes: 0GitHub stars: 86
- ResearchExecute a multi-pass research investigation, adding claims with evidence.Votes: 0GitHub stars: 86
- ResolveAdjudicate conflicts between claims that the compiler flagged.Votes: 0GitHub stars: 86
- RouterIntent router that detects user intent from plain messages and dispatches to the appropriate skill.Votes: 0GitHub stars: 86
- SetupSet up the local Grainulator MCP connection, check capabilities, and initialize the requested sprint.Votes: 0GitHub stars: 86
- StatusShow a snapshot of the current sprint -- claims, conflicts, coverage, and next actions.Votes: 0GitHub stars: 86
- SyncPublish the current sprint to Confluence as a page with structured content.Votes: 0GitHub stars: 86
- WitnessCorroborate a claim against an external source URL.Votes: 0GitHub stars: 86
- BeanRun a task as a recursive convergence loop, not a fixed checklist: investigate the most decisive open question, record what you learn as typed evidence in a ledger, let a compiler score what is still weak or contradictory, revise beliefs that new evidence overturns, and loop until the evidence converges — then deliver. Continuously spins up subagents and uses whatever skills/connectors exist. Verbose by default. Trigger on /bean, on "do this thoroughly / be systematic / deep work mode", OR wh...Votes: 0GitHub stars: 86
- AnalyticsSprint analytics — type distributions, stale claims, velocity, prediction scoringVotes: 0GitHub stars: 86
- GrainulatorUse 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.Votes: 0GitHub stars: 86
- OrchestrateMulti-sprint orchestration — view dependency graph, identify the next ready sprintVotes: 0GitHub stars: 86