promptctl

promptctl/laws

Plugin Claude Code

Prompt- and guidance-engineering plugins: the universal architectural laws with medium-scoped quality skills, and personal agent-native workflow tooling.

promptctl/laws

Skill Claude CodeCodex

Rules for editing the laws skills in THIS repo. Use when creating, editing, or reviewing any skills//SKILL.md, any skills//references/craft.md, or any design-docs/design-goals-.md. Says which content belongs in which file. How to write the prose well is laws:prompt's job, not this skill's.

promptctl/laws

Instructions file CodexOpenCode

Instructions for promptctl/laws, covering agents and lit agent-native workflow.

promptctl/laws

Instructions file

Instructions for promptctl/laws: CRITICAL: This repository is configured for agent-native issue tracking with lit.

promptctl/laws

Plugin Claude Code

Universal architectural laws for code work, medium-scoped quality skills (code / prose / prompt), and skill-router hooks that route to the right one at session start, re-engage the laws on every message, and refuse a second medium skill in one session.

promptctl/laws

Hook

Runs when a session starts, executing skill-router.sh. From promptctl/laws.

promptctl/laws

Hook

Runs when you submit a prompt, before the agent sees it, executing skill-router.sh. From promptctl/laws.

promptctl/laws

Hook

Runs before the agent uses a tool for Skill tool calls, executing skill-router.sh. From promptctl/laws.

promptctl/laws

Skill Claude CodeCodex

Produce a thorough, functional, clean-room specification of an existing application - every externally observable behavior (invocation, inputs, outputs, configuration, startup requirements, shutdown, error behavior, interactions with external systems) captured precisely enough for an independent team to reimplement…

promptctl/laws

Skill Claude CodeCodex

How to write conversational replies to the user present in the session - answers, status updates, explanations, findings delivered directly in chat. Applies whenever the text you are producing is the reply itself and the reader is the person in the conversation right now. Does NOT apply to documents, files, reports…

promptctl/laws

Skill Claude CodeCodex

Universal architectural laws and domain bindings for all code work. Use when writing, editing, reviewing, refactoring, debugging, or designing code, tests, schemas, configuration, scripts, infrastructure, or system architecture - any task whose deliverable is code or will execute as code. Load BEFORE starting the…

promptctl/laws

Skill Claude CodeCodex

Craft reference for any text another LLM will consume — task prompts, subagent instructions, prompts written into files or code, and persistent agent guidance (CLAUDE.md files, system prompts, skill bodies, hook text). Use BEFORE writing either kind. The regime determines the craft — task prompts want terse, complete…

promptctl/laws

Skill Claude CodeCodex

Writing guidance for human-audience text - documentation, READMEs, reports, summaries, announcements, commit messages, emails, and any other writing a person (not a machine or an LLM) will read. Use when the deliverable is prose for people. Do not apply to code or to text another LLM will consume.

promptctl/laws

Plugin Claude Code

Agent-native workflow tooling: pull the next lit ticket (next), the mandatory session close-out and cross-session handoff that carries a goal across a reset (message-in-a-bottle), and the address-PR-review loop (address-pr-reviews).

promptctl/laws

Skill Claude CodeCodex

Address open PR review findings with judgment — read every finding, decide whether the feedback is right, fix or push back, resolve, and re-review by pushing. Repeat until clean. Use when the user says "address the PR review", "handle the review threads", "go through the review comments", or asks to respond to PR…

promptctl/laws

Skill Claude CodeCodex

Writes a message to a future session's agent. Send them your fondest memories of what you worked on, what went well, what didn't go well, and any useful tips they might need. You always run this when you finish a unit of work (closed a PR, completed the handed task, etc) or cross 300k–350k tokens of context. ALWAYS.

promptctl/laws

Skill Claude CodeCodex

Pick up the next ready ticket and start work.