claudecodex

workbench

Requirements-first delivery with adaptive opportunity scanning, optional release gates, weighted review, and grounded research.

8 on GitHubby nklischv0.26.13MITupdated 15 days agoproductivity
/

Plugin workbench from marketplace nklisch-skills in nklisch/skills. Commands read from the repo's manifest — 12 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (11)

  • code-craft

    Keep code readable and free of ceremony while designing, implementing, or reviewing in a Workbench project. Use only when .work/CONVENTIONS.md declares owner: workbench. Covers finding the repository's existing model before inventing one, designing an abstraction with its first consumer, naming read

  • deliver

    Implement, verify, review, reconcile, and close one ready Workbench feature or story. Use when .work/CONVENTIONS.md declares owner: workbench and the item has settled requirements. Supports direct delivery and units owned by work, usually in the existing context. Resolve bounded technical discoverie

  • design

    Resolve consequential implementation choices for a Workbench outcome, or stress-test its design before costly implementation, authoring the design directly in its work item. Use only when .work/CONVENTIONS.md declares owner: workbench. Keep accepted context and the same outcome owner, revise only de

  • ideate

    Collaboratively explore, clarify, or stress-test work before committing to scope or design. Use for brainstorming, challenge, initial exploration of a substantial or cross-cutting initiative, early design exploration that could materially change what should be designed, or coupled product, domain, o

  • park

    Capture useful context for later without expanding current scope. Use only when .work/CONVENTIONS.md declares owner: workbench and the user wants the finding in that project's Workbench backlog; ignore this skill otherwise. Create the smallest useful .work/backlog item, preserving supplied context a

  • release

    Prepare or reconcile a versioned Workbench release summary, optionally apply project-defined release gates through scan, and clean completed outcome files. Use only when .work/CONVENTIONS.md declares owner: workbench and the user asks to bind completed outcomes to a version; ignore this skill for un

  • research-handoff

    Turn actionable findings from completed .research briefs into user-confirmed Workbench items. Use only when .work/CONVENTIONS.md declares owner: workbench, .research/CONVENTIONS.md declares owner: workbench-research, and the user requests a concrete handoff into its ledger; ignore this skill otherwi

  • research

    Conduct and maintain source-grounded research for a concrete Workbench workflow. Use only when .work/CONVENTIONS.md declares owner: workbench and the requested evidence should enter Workbench's .research substrate owned by workbench-research or inform a tracked outcome. Ignore this skill in uninitia

  • scan

    Discover, investigate, verify, and consolidate improvement opportunities in an adopted Workbench project without starting remediation. Use when the user asks to look for problems, investigate a quality concern, scan a project surface, or propose improvements in areas such as correctness, security, t

  • setup

    Destructively consolidate, initialize, migrate, adopt, or refresh Workbench in any repository, removing superseded workflow files after verified conversion. Use only when the user explicitly invokes setup or states that they want to initialize, adopt, migrate, upgrade, refresh, or reconcile Workbenc

  • work

    Scope, implement, fix, simplify, groom, review, continue, or finish a concrete Workbench outcome, from one change through several epics. Use only when .work/CONVENTIONS.md declares owner: workbench. Own the continuous conversation, gather consequential requirements, draw on design and delivery guida

Hooks (2)

  • SessionStart

    if command -v python3 >/dev/null 2>&1; then exec python3 -B "${CLAUDE_PLUGIN_ROOT}/scripts/session-context.py"; else exec python -B "${CLAUDE_PLUGIN_ROOT}/scripts/session-context.py"; fi

  • PostCompact

    if command -v python3 >/dev/null 2>&1; then exec python3 -B "${CLAUDE_PLUGIN_ROOT}/scripts/session-context.py"; else exec python -B "${CLAUDE_PLUGIN_ROOT}/scripts/session-context.py"; fi

View source on GitHub

More from nklisch/skills

All 15 plugins →

agile-workflow

claudecodex

Markdown-based work-tracking substrate for AI-driven projects. Items as files in .work/, late-binding releases, gates that produce items, goal-backed autopilot queue runner.

32 skills · hooks

8

workflow

claudecodex

Software development workflow skills — design features, implement from plans, refactor codebases, extract patterns, design tests, and ship releases.

24 skills · 1 agent

8

code-audit

claudecodex

Standalone markdown-first code audit skills — deep code scan, bug scan, security scan, test scan, perf scout, bold refactor, and repo eval without requiring agile-workflow or .work.

7 skills

8

nates-toolkit

claudecodex

Standalone, project-agnostic utility skills with no workflow lock-in — plainspeak (plain-language re-explanation), agent-reflection (self-reflection on tool & skill usage), write-tool-skill + skill-auditor (skill authoring and quality auditing).

5 skills

8

agentic-research

claudecodex

Agentic Research Discipline (ARD) — grounded, verifiable AI research with a non-erodable anti-fabrication floor, selectable verification gates, and a .research/ substrate tier paralleling .work/. ARD is the plugin's internal, empirically-warranted discipline (ard-core/).

4 skills

8

krometrail

claudecodex

Control a local Chromium browser and inspect transient behavior with source-linked temporal visual evidence.

2 skills · 1 MCP server

8

Similar plugins

caveman

claude

Talk like caveman. Cut filler. Keep technical details explicit.

22 skills · 1 command · 3 agents · hooks

JuliusBrussee/caveman 119,462

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

pake

claudecodex

Package any website or local web build into a lightweight desktop app with Pake CLI.

1 skill

tw93/Pake 63,463

Maintain workbench?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins15 plugins