claudecodex

drafting

Independent skills for exploration, incremental planning and execution, research, challenge, verification, and retrospectives

1 on GitHubv3.0.0CC0-1.0updated 18 days agoProductivity
/

Plugin drafting from marketplace kimmywork-skills in kimmywork/skills. Commands read from the repo's manifest — 18 days ago.

What it installs

Skills (11)

  • align

    Keep project documentation aligned when implementation, requirements, decisions, or research evidence changes, or when document moves and renames require reference remapping. Use to create, update, archive, or remap plans, architecture notes, research reports, and current references.

  • challenge

    Challenge an existing artifact, plan, idea, conclusion, or decision to expose weak assumptions, hidden risks, edge cases, failure modes, and unresolved trade-offs. Use when the main need is adversarial critique or questioning before proceeding, rather than a formal evidence-based verdict.

  • deep-research

    Investigate a question through source-based evidence, tracing, comparison, and synthesis. Use for research, root cause analysis, system mapping, source tracing, contradiction resolution, or any task whose answer must be derived rather than assumed.

  • distillation

    Summarize and retrospect on completed or ongoing work, then decide whether the lessons should update an existing SKILL.md or become a new reusable skill. Use for retrospectives, process reviews, lessons learned, and workflow improvement.

  • increment

    Turn requirements into an agreed, executable, and verifiable incremental plan, then optionally carry it out one increment at a time. Use for requirement analysis, scoping, implementation planning, delivery planning, or execution when the desired direction exists but details need shared understanding

  • parkinglot

    Park out-of-scope issues, improvement ideas, and tangents found during a task in PARKING_LOT.md instead of acting on them, then review parked items in batches to find shared causes and decide each item's fate. Use when you notice something worth improving outside the current task, when the user says

  • probing

    Explore an uncertain goal with the user until a useful direction, decision, or target emerges. Use when the user has a vague idea, competing possibilities, unclear priorities, or cannot yet state what they want well enough to plan or act.

  • prune

    Remove whatever is not necessary — obsolete or reproducible files and workspace clutter, and overgrowth in a drafted design or plan — keeping the smallest set that is necessary and sufficient. Use when syncing, planning, or landing decisions.

  • restraint

    Act with restraint — do what the user actually wants, and nothing more. Use alongside the task skill when the agent might over-engineer, over-expand, or act beyond the granted scope.

  • vnv

    Produce an evidence-based verification or validation verdict for an existing result, artifact, execution, claim, or decision. Use for reviews, audits, fact checks, compliance checks, acceptance decisions, plan-conformance checks, second opinions, cross-validation, or readiness assessments.

  • worklog

    Record completed logical workspace changes as traceable daily log entries and maintain a current workstate snapshot. Use after a logical change that edits, creates, deletes, or reconfigures workspace files. Also use when the user asks to check progress, review recent changes, or see what is planned

View source on GitHub

Problems found in this repo's manifests

  • "deprecated-solution-delivery-loop" points to ./delivery/, which doesn't exist in the repo — install will fail

More from kimmywork/skills

All 5 plugins →

utility

claudecodex

Utility skills for daily work

5 skills

1

design

claudecodex

Design system building, design review, and presentation craft

2 skills

1

loop

claudecodex

Permission-bounded recurring workflow creation, validation, and execution

2 skills

1

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 drafting?

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 plugins5 plugins