fearvox/multica-ultimate-workbench
33 skills
$npx skills add fearvox/multica-ultimate-workbenchSkillInstalls
workbench-agent-install-unifierUse when syncing skills, MCPs, or AGENTS.md sections across coding agents with agent-install.workbench-algorithm-advisory-gateAdvisory-only algorithm and data-structure review gate between Technical Design and Task List.workbench-browser-proofshot-qaBrowser verification, proof screenshots, traces, console and network checks, and reproducible UI evidence for Workbench QA.workbench-capy-git-dialogue-guardrailsSource-first, self-loop resistant guardrails for Capy GitHub dialogue responders before any write-capable PR, issue, or review action.workbench-capy-process-checkUse when checking live Capy task or PR state through Brave, Computer Use, or a Capy browser panel.workbench-capy-vm-laneControlled VM/Computer execution lane for GUI, browser, sandbox, and screenshot-backed tasks.workbench-closeout-validatorStrict parser and validator for Workbench closeout comments, verdict/status discipline, PR reference types, and cross-issue REMAINING sync.workbench-code-reviewFindings-first review discipline for code, diffs, task plans, live workflow changes, and implementation evidence.workbench-conductorTwo-ring orchestration, routing, issue and comment discipline, and role boundaries for the Multica Workbench.workbench-debug-investigateRoot-cause investigation for bugs, regressions, suspicious runtime behavior, failed automations, and unexpected outcomes.workbench-design-docsProduct design, technical design documents, user-facing copy, specs, diagrams, and handoff documentation.workbench-docs-releasePost-change documentation sync for decisions, synthesis, skill maps, release notes, and durable handoffs.workbench-flue-agent-harnessDeployable Flue agent harness lane for HTTP, CI, Node, Cloudflare, and sandbox-backed agents.workbench-frontend-design-qaFrontend and visual QA for responsive surfaces, screenshots, text fit, hierarchy, and interaction states.workbench-goal-modeGoal-persistence execution wrapper for autonomous work that must continue across turns until the stated objective is actually satisfied.workbench-goal-mode-v2Two-layer autonomous conductor — design loop produces decision packets, dispatch loop routes to bounded issues with dedupe/cooldown/archive controls.workbench-gsd-taskingOwner-scoped task decomposition with gates, rollback, verification commands, and smoke tests.workbench-hermes-docs-syncUse when Hermes reviews Claude-authored writeups, public docs, skill changes, README/agent/issue-template changes, or upstream speed-match documentation before…workbench-implementationMinimal-patch implementation, ops changes, scripts, automation specs, and local repository edits.workbench-l2-pressure-gateResearch Vault pressure gate for remote Hermes, VM, HarnessMax, and autonomous evolution sweeps.workbench-memory-synthesisDurable memory, session summaries, decision logs, issue closeout synthesis, and compact handoffs.workbench-mirage-vfs-toolScout, pilot, or review Mirage virtual-filesystem tool use for Workbench agents while preserving source-of-truth and public-safety boundaries.workbench-product-brainstormingBounded product ideation, workflow design, ambition checks, tradeoffs, and smallest-test shaping.workbench-repo-brand-upliftUse when upgrading a public GitHub repository README, repo metadata, docs map, or first-impression brand surface to match the Zonic/Evensong proof-first…workbench-researchEvidence-first research, architecture discovery, vendor documentation review, benchmark reading, and unknown-system analysis.workbench-review-qaPASS, FLAG, and BLOCK review discipline for workflow review, QA verification, release checks, and issue closeout.workbench-runtime-hygieneDisk, swap, VM, agent workspace, and stale session hygiene for Multica workbench runtimes.workbench-sanity-contextUse when designing, reviewing, or updating Sanity as the shared context registry for workbench agents and CLIs.workbench-sddSpecification-driven development from raw requirement to product design, technical design, task list, execution, and verification.workbench-self-awareness-infraCapability discovery and current-state verification for Heavy Path, ambiguous repo/runtime ownership, and runtime-dependent Standard Path work.workbench-token-context-disciplineCompact context, cache-aware execution, scoped evidence reads, and role-specific skill attachment discipline.workbench-waking-upUse when an operator asks what changed recently, what was left hanging, what can move now, "gm", "where are we", or when a session-derived update needs to…workbench-windburn-profileHorizontal session personality overlay — auto-detects conversation mode from density signals, defaults casual, upgrades to structured only on sustained signal.