multica-ultimate-workbench

In the author's own words, from each skill's SKILL.md — showing the first 30 of 33 files.

• workbench-agent-install-unifier

  Use when syncing skills, MCPs, or AGENTS.md sections across coding agents with agent-install.

  skills/workbench-agent-install-unifier/SKILL.md on GitHub (opens in a new tab)

• workbench-algorithm-advisory-gate

  Advisory-only algorithm and data-structure review gate between Technical Design and Task List.

  skills/workbench-algorithm-advisory-gate/SKILL.md on GitHub (opens in a new tab)

• workbench-browser-proofshot-qa

  Browser verification, proof screenshots, traces, console and network checks, and reproducible UI evidence for Workbench QA.

  skills/workbench-browser-proofshot-qa/SKILL.md on GitHub (opens in a new tab)

• workbench-capy-git-dialogue-guardrails

  Source-first, self-loop resistant guardrails for Capy GitHub dialogue responders before any write-capable PR, issue, or review action.

  skills/workbench-capy-git-dialogue-guardrails/SKILL.md on GitHub (opens in a new tab)

• workbench-capy-process-check

  Use when checking live Capy task or PR state through Brave, Computer Use, or a Capy browser panel.

  skills/workbench-capy-process-check/SKILL.md on GitHub (opens in a new tab)

• workbench-capy-vm-lane

  Controlled VM/Computer execution lane for GUI, browser, sandbox, and screenshot-backed tasks.

  skills/workbench-capy-vm-lane/SKILL.md on GitHub (opens in a new tab)

• workbench-closeout-validator

  Strict parser and validator for Workbench closeout comments, verdict/status discipline, PR reference types, and cross-issue REMAINING sync.

  skills/workbench-closeout-validator/SKILL.md on GitHub (opens in a new tab)

• workbench-code-review

  Findings-first review discipline for code, diffs, task plans, live workflow changes, and implementation evidence.

  skills/workbench-code-review/SKILL.md on GitHub (opens in a new tab)

• workbench-conductor

  Two-ring orchestration, routing, issue and comment discipline, and role boundaries for the Multica Workbench.

  skills/workbench-conductor/SKILL.md on GitHub (opens in a new tab)

• workbench-debug-investigate

  Root-cause investigation for bugs, regressions, suspicious runtime behavior, failed automations, and unexpected outcomes.

  skills/workbench-debug-investigate/SKILL.md on GitHub (opens in a new tab)

• workbench-design-docs

  Product design, technical design documents, user-facing copy, specs, diagrams, and handoff documentation.

  skills/workbench-design-docs/SKILL.md on GitHub (opens in a new tab)

• workbench-docs-release

  Post-change documentation sync for decisions, synthesis, skill maps, release notes, and durable handoffs.

  skills/workbench-docs-release/SKILL.md on GitHub (opens in a new tab)

• workbench-flue-agent-harness

  Deployable Flue agent harness lane for HTTP, CI, Node, Cloudflare, and sandbox-backed agents.

  skills/workbench-flue-agent-harness/SKILL.md on GitHub (opens in a new tab)

• workbench-frontend-design-qa

  Frontend and visual QA for responsive surfaces, screenshots, text fit, hierarchy, and interaction states.

  skills/workbench-frontend-design-qa/SKILL.md on GitHub (opens in a new tab)

• workbench-goal-mode-v2

  Two-layer autonomous conductor — design loop produces decision packets, dispatch loop routes to bounded issues with dedupe/cooldown/archive controls. Replaces v1's single-agent persistence with a durable control loop that stops only at real blockers.

  skills/workbench-goal-mode-v2/SKILL.md on GitHub (opens in a new tab)

• workbench-goal-mode

  Goal-persistence execution wrapper for autonomous work that must continue across turns until the stated objective is actually satisfied.

  skills/workbench-goal-mode/SKILL.md on GitHub (opens in a new tab)

• workbench-gsd-tasking

  Owner-scoped task decomposition with gates, rollback, verification commands, and smoke tests.

  skills/workbench-gsd-tasking/SKILL.md on GitHub (opens in a new tab)

• workbench-hermes-docs-sync

  Use when Hermes reviews Claude-authored writeups, public docs, skill changes, README/agent/issue-template changes, or upstream speed-match documentation before syncing or publishing.

  skills/workbench-hermes-docs-sync/SKILL.md on GitHub (opens in a new tab)

• workbench-implementation

  Minimal-patch implementation, ops changes, scripts, automation specs, and local repository edits.

  skills/workbench-implementation/SKILL.md on GitHub (opens in a new tab)

• workbench-l2-pressure-gate

  Research Vault pressure gate for remote Hermes, VM, HarnessMax, and autonomous evolution sweeps.

  skills/workbench-l2-pressure-gate/SKILL.md on GitHub (opens in a new tab)

• workbench-memory-synthesis

  Durable memory, session summaries, decision logs, issue closeout synthesis, and compact handoffs.

  skills/workbench-memory-synthesis/SKILL.md on GitHub (opens in a new tab)

• workbench-mirage-vfs-tool

  Scout, pilot, or review Mirage virtual-filesystem tool use for Workbench agents while preserving source-of-truth and public-safety boundaries.

  skills/workbench-mirage-vfs-tool/SKILL.md on GitHub (opens in a new tab)

• workbench-product-brainstorming

  Bounded product ideation, workflow design, ambition checks, tradeoffs, and smallest-test shaping.

  skills/workbench-product-brainstorming/SKILL.md on GitHub (opens in a new tab)

• workbench-repo-brand-uplift

  Use when upgrading a public GitHub repository README, repo metadata, docs map, or first-impression brand surface to match the Zonic/Evensong proof-first standard.

  skills/workbench-repo-brand-uplift/SKILL.md on GitHub (opens in a new tab)

• workbench-research

  Evidence-first research, architecture discovery, vendor documentation review, benchmark reading, and unknown-system analysis.

  skills/workbench-research/SKILL.md on GitHub (opens in a new tab)

• workbench-review-qa

  PASS, FLAG, and BLOCK review discipline for workflow review, QA verification, release checks, and issue closeout.

  skills/workbench-review-qa/SKILL.md on GitHub (opens in a new tab)

• workbench-runtime-hygiene

  Disk, swap, VM, agent workspace, and stale session hygiene for Multica workbench runtimes.

  skills/workbench-runtime-hygiene/SKILL.md on GitHub (opens in a new tab)

• workbench-sanity-context

  Use when designing, reviewing, or updating Sanity as the shared context registry for workbench agents and CLIs.

  skills/workbench-sanity-context/SKILL.md on GitHub (opens in a new tab)

• workbench-sdd

  Specification-driven development from raw requirement to product design, technical design, task list, execution, and verification.

  skills/workbench-sdd/SKILL.md on GitHub (opens in a new tab)

• workbench-self-awareness-infra

  Capability discovery and current-state verification for Heavy Path, ambiguous repo/runtime ownership, and runtime-dependent Standard Path work.

  skills/workbench-self-awareness-infra/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 270k stars · 1 skill
• taste-skillby Leonxlnx Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages 97.3k stars · 13 skills
• archifyby tt-a1i Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more. 84.1k stars · 2 skills
• cherry-studioby CherryHQ AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs 52.7k stars · 30 skills
• khazix-skillsby KKKKhazix 数字生命卡兹克开源的 AI Skills 合集 | Agent Skills: leader（帮你定义目标）, neat-freak 洁癖, hv-analysis, khazix-writer & more — Claude Code, Codex & 40+ agents 21.4k stars · 6 skills
• Kamiby tw93 👩 🚒 Good content deserves good paper. Layout rules and templates that let AI agents export PDF, PNG and editable PowerPoint. 12k stars · 1 skill