kotnisofiane-bit
UserLocal, deterministic project-memory engine with a read-only Continuity Workbench.
Categories
Indexed Skills (11)
dubsar-audit-readiness
Run the complete local audit-readiness workflow for automations or AI agents: scope, evidence index, inventory, sensitive actions, evidence gaps, validation, and deterministic export. Use when the user requests end-to-end preparation for human review; use a specialized skill for only one phase.
export-audit-bundle
Export a validated, deterministic, non-certifying bundle of local audit-preparation files and approved artifacts. Use when scope, inventory, sensitive-action mapping, and evidence-gap review are complete and the user wants a portable human-review package.
frame-audit-scope
Define a bounded, evidence-aware audit scope for automations, AI agents, workflows, or connected business systems. Use when starting an audit preparation, deciding what local evidence may be inspected, recording exclusions, or narrowing an open-ended assessment request.
map-sensitive-actions
Map automation or AI-agent actions that can communicate externally, move money, change access, alter data, affect people, or create another material business effect. Use when preparing control points, stop conditions, ownership, and human-review requirements.
review-evidence-gaps
Review a local audit-preparation workspace and separate supported observations, reported statements, contradictions, missing evidence, and limitations. Use before presenting readiness findings or exporting a human-review bundle.
dubsar-project-continuity
Keep a significant project bounded, evidence-aware, and safely resumable through a mission, lots, an execution contract, evidence records, and a deterministic handoff. Use when the user requests the complete end-to-end workflow or installs the DUBSAR pack as one portable Hermes skill; prefer a specialized skill for a single step.
record-project-evidence
Append project claims with reproducible local evidence, artifact references, validation results, and limitations. Use when asked to capture proof, preserve an audit trail, or verify a lot during or after work without conflating plans, commands, and observed outcomes.
resume-project-context
Reconstruct the current state of a project from its portable mission, lots, execution contract, and evidence files without inventing progress. Use when asked to resume, hand off, recover, or verify project state after interruption, tool change, or uncertainty about completion.
decompose-project-lots
Split an approved mission into small, ordered, independently verifiable lots with dependencies, exclusions, proof, and stop conditions. Use when asked to break down, phase, sequence, or audit a project that is too large for one safe execution pass.
draft-execution-contract
Define the exact scope, permitted actions, exclusions, validation, evidence, recovery expectations, and stop rules for one project lot. Use when asked for an execution contract, preflight boundary, or safe implementation agreement immediately before material project work.
frame-project-mission
Turn a significant project request into a bounded mission with purpose, scope, exclusions, acceptance evidence, risks, and stop conditions. Use when asked to frame, charter, scope, or clarify a broad or ambiguous project before planning or change begins.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.