How do I install the Arch Flow skill?

Run npx skillmds@latest add tomevault-io/arch-flow in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Arch Flow safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Arch Flow?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Arch Flow free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Arch Flow?

tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Arch Flow by tomevault-io — Agent Skill

Name: Arch Flow
Author: tomevault-io

Arch Flow

Read-only flow-status and next-step router for arch-step, arch-mini-plan, and lilarch docs. Use when the user asks 'what's next?', wants a checklist, or wants the single best next move without running the workflow. Not for doing the planning or implementation work itself. Use when this capability is needed.

tomevault-io Updated Sep 17, 2026

File contents

arch-flow

Use this skill to inspect an existing arch-style doc and recommend the next move.

Read references/detection.md, references/checklist-rules.md, and references/recommendation-rules.md before building the checklist.

When to use

The user asks "what's next?", "where are we in the flow?", or wants a checklist.
You want a deterministic next-step recommendation from DOC_PATH and WORKLOG_PATH, not memory.
The doc is part of the full arch flow, the arch-mini-plan path, or the lilarch flow.

When not to use

The user wants you to actually perform research, planning, implementation, or auditing. Use arch-step or lilarch.
The user wants generic continuation on a full-arch doc. Use arch-step.
The user wants the concise strength/weakness status surface or wants to execute one explicit full-arch step. Use arch-step.
The doc is a bug doc or a goal-loop doc. Use the governing skill for that workflow family.

What to do

Resolve DOC_PATH and the derived WORKLOG_PATH.
Infer whether the doc is:
- full arch
- arch-mini-plan follow-through
- lilarch
Build a full evidence-based checklist:
- mark each required step DONE, PENDING, OPTIONAL, or UNKNOWN
- include the evidence note for each line
Recommend the single best next move:
- arch-step for full-arch execution or post-mini-plan follow-through until the code audit is clean
- arch-docs for full-arch or post-mini-plan docs cleanup after the clean code audit
- lilarch for lilarch steps
If the user asks to run the next step, switch to the governing skill and do the work there.

Invariants

Use the plan doc (DOC_PATH) as the source of truth.
Keep this skill read-only unless the user explicitly asks you to proceed into the next step.
Do not invent steps or ask questions that can be answered from the repo/doc.

Reference map

references/detection.md - flow-family detection and artifact sanity checks
references/checklist-rules.md - evidence-based checklist construction rules
references/recommendation-rules.md - exact next-move recommendation rules by doc family

Converted and distributed by TomeVault — claim your Tome and manage your conversions.

---name: arch-flowdescription: Read-only flow-status and next-step router for arch-step, arch-mini-plan, and lilarch docs. Use when the user asks 'what's next?', wants a checklist, or wants the single best next move without running the workflow. Not for doing the planning or implementation work itself. Use when this capability is needed.---# arch-flowUse this skill to inspect an existing arch-style doc and recommend the next move.Read `references/detection.md`, `references/checklist-rules.md`, and `references/recommendation-rules.md` before building the checklist.## When to use- The user asks "what's next?", "where are we in the flow?", or wants a checklist.- You want a deterministic next-step recommendation from `DOC_PATH` and `WORKLOG_PATH`, not memory.- The doc is part of the full arch flow, the arch-mini-plan path, or the lilarch flow.## When not to use- The user wants you to actually perform research, planning, implementation, or auditing. Use `arch-step` or `lilarch`.- The user wants generic continuation on a full-arch doc. Use `arch-step`.- The user wants the concise strength/weakness status surface or wants to execute one explicit full-arch step. Use `arch-step`.- The doc is a bug doc or a goal-loop doc. Use the governing skill for that workflow family.## What to do1. Resolve `DOC_PATH` and the derived `WORKLOG_PATH`.2. Infer whether the doc is: - full arch - arch-mini-plan follow-through - lilarch3. Build a full evidence-based checklist: - mark each required step `DONE`, `PENDING`, `OPTIONAL`, or `UNKNOWN` - include the evidence note for each line4. Recommend the single best next move: - `arch-step` for full-arch execution or post-mini-plan follow-through until the code audit is clean - `arch-docs` for full-arch or post-mini-plan docs cleanup after the clean code audit - `lilarch` for lilarch steps5. If the user asks to run the next step, switch to the governing skill and do the work there.## Invariants- Use the plan doc (`DOC_PATH`) as the source of truth.- Keep this skill read-only unless the user explicitly asks you to proceed into the next step.- Do not invent steps or ask questions that can be answered from the repo/doc.## Reference map- `references/detection.md` - flow-family detection and artifact sanity checks- `references/checklist-rules.md` - evidence-based checklist construction rules- `references/recommendation-rules.md` - exact next-move recommendation rules by doc family---> Converted and distributed by [TomeVault](https://tomevault.io/claim/aelaguiz) — claim your Tome and manage your conversions.

Frequently asked questions