Cxc Pabcd logo

Cxc Pabcd

Community
lidge-jun
cxc-pabcd

Use for Plan-Audit-Build-Check-Done work. Triggers: PABCD, plan this, 기획, 단계별로, 요구사항 정리.

Overview

Publisherlidge-jun
Repositorycodexclaw
Skill namecxc-pabcd
Stars
51
Forks
10
Bundled files
12
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 12 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by lidge-jun on GitHub. Read the source before you install it.

Installation

Install the Cxc Pabcd AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/lidge-jun/codexclaw/tree/main/plugins/codexclaw/skills/pabcd
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/lidge-jun/codexclaw.git /tmp/codexclaw
mkdir -p .claude/skills
cp -r /tmp/codexclaw/plugins/codexclaw/skills/pabcd .claude/skills/cxc-pabcd
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cxc Pabcd in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Cxc Pabcd on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Cxc Pabcd is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

PABCD Workflow

PABCD keeps session state and a transition ledger. Before state control, read Phase control for commands, bindings, artifacts, attestations and state files (SESSION-IDENTITY-01, ORCH-ARTIFACT-01, ATTEST-SHAPE-01).

Intent boundary

Loading grants no execution authority; explicit limits win. cxc-dev owns class, fast path, reading, proof and safety; cxc-loop owns HOTL activation.

How It Works

text
IDLE -> P -> A -> B -> C -> D -> IDLE
         any phase -> I -> P

I preserves plan/audit context and needs HITL with no active goal. Interactive P/A/B pause for confirmation; C/D proceed after their work. Goal-mode cycles explicitly enter P through phase control.

Phases

Read the mandatory owner before its work.

Phase / triggerWork and mandatory owner
IClarify requirements: cxc-interview. Hints do not enter phases.
P, including plan-onlyExplore and plan without implementation: Plan phase owns consultation, dependency order (PHASE-SPLIT-01), scope and verifiers. C2+ reads Plan output.
A, if authorizedAudit, resolve/rebut blockers and re-audit to pass/justified near-pass: Audit phase.
BImplement audited scope, verify and surface deviations; cxc-dev owns git (DEV-GIT-COMMIT-01, DEV-GIT-PUSH-01); declared stacks read Stacked PRs (DEV-STACK-02).
CFresh relevant proof and source-of-truth sync: Check phase.
DRecord conclusion, changes and evidence; update STATUS and the devlog (cxc devlog path), apply cxc-dev git rules, resolve this work-phase's pending work and close to IDLE. Read Reader documents (READER-DOC-02/04).
P/A defining render/conditional checksRead Check phase above for reachable activation and observable evidence.

LOOP-PESSIMIST-01 (DEFAULT): for loop/multi-pass D, record what did not improve, which hypothesis died and what evidence would refute the direction.

Work-Phase Loop (multi-pass tasks)

A work-phase is an outcome slice; a PABCD phase is one letter. Perform a full P→A→B→C→D cycle per work-phase, close D to IDLE, then start next P. Never batch work-phases' B steps or close directly from B. A transition is not its artifact; real loops cannot skip phases. cxc-dev owns C0/C1 exceptions.

Continuation, new units (LOOP-UNIT-CHAIN-01) and previous-D handoff (LOOP-CONTINUITY-01) follow cxc-loop. PLAN-TRACK-01 (DEFAULT): when available, mirror progress in native update_plan; the durable plan remains authoritative.

Implementation-Unit Documents

Before C2+ unit planning or multi-phase roadmaps, read Implementation units (DIFFLEVEL-ROADMAP-01, LEXICO-SPLIT-01, UNIT-RESIDENCE-01); cxc-loop owns docs-first entry.

PABCD Depth by Work Class

cxc-dev owns class definitions and tie-breaks. PABCD depth per class:

ClassPlan (P)Audit (A)Build (B)Check (C)Record (D)
C0-C1None/inlineOptionalDirect fixSmallest proofcxc-dev: C0 exempt; C1 only in an existing owning unit
C2CompactMicro-auditImplement + focused testsTargeted gateSummary
C3Compact/full by persistence/riskRequired for public contract, architecture, persistence or cross-session risk; otherwise focusedImplement; reviewer when usefulAffected suites + contract docs consistencySummary + evidence; durable if state must persist
C4Full, mandatoryIndependent reviewer requiredImplement + independent verificationFull relevant gatesDurable risk/approval/evidence
C5Interview/research first———Reclassify before implementation

Delegation model — choosing a surface

Before dispatch, read Dispatch surfaces for leaf/task isolation and grants, then Delegation for subagents. cxc-dev owns skill attachments and peer contact; explicit limits win.

Loop Engineering (§11)

Repeated repairs, reviewer FAIL or archetype selection read Loop engineering (LOOP-REPAIR-01, LOOP-DOOM-01, REVIEW-SYNTHESIS-01). Optimization/comparison/plateaus also read Optimization. Composition, response projection and computation read Native execution.

Catalog Discovery routing

Interview sub-modes and option discovery follow cxc-interview (INTERVIEW-CATALOG-01, CATALOG-DESIGN-FIRST-01); the option ontology is Catalog schema.

Repository Root

Resolve the actual target repository root before planning and resolve relative source/test paths against it; clarify an ambiguous root before proceeding.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Cxc Pabcd AI skill do?

Use for Plan-Audit-Build-Check-Done work. Triggers: PABCD, plan this, 기획, 단계별로, 요구사항 정리.

Why use Cxc Pabcd on TypingMind?

Because you install it once and use it with any model. Cxc Pabcd is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Cxc Pabcd in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/lidge-jun/codexclaw/tree/main/plugins/codexclaw/skills/pabcd. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Cxc Pabcd?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Cxc Pabcd?

As many as you like. As long as a model supports skills, you can use Cxc Pabcd with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Cxc Pabcd AI skill free?

Yes. It is published on GitHub by lidge-jun under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇