magicj1995/papersmith/state-machine-markdown-helper
- community
Checking that the SKILL.md file is still in the repository.
Use for high-risk sections where context isolation and careful progression matter. Not suitable when: Do not rely on hidden state or automatic paper-structure tools. File changes: conditional. Default output: reviews/state_machine_draft_plan.md or approved edits to paper.md.
Install
npx vskill@latest install magicj1995/papersmith/state-machine-markdown-helperSKILL.md
state-machine-markdown-helper
Purpose
Run strict step-by-step section drafting with explicit evidence checks and confirmation gates.
When to Use
Use for high-risk sections where context isolation and careful progression matter.
When Not to Use
Do not rely on hidden state or automatic paper-structure tools.
Inputs
PROJECT_CONTEXT.md, storyline.md, paper.md, writingrules.md, notes/, references/, outputs/
Always read AGENTS.md first. For paper projects, treat PROJECT_CONTEXT.md, storyline.md, paper.md, and writingrules.md as the source-of-truth files.
Default Outputs
reviews/state_machine_draft_plan.md or approved edits to paper.md
Review, checker, diagnosis, and readiness outputs must go under reviews/. Intermediate reasoning notes must go under notes/. Related-work materials must go under references/. Final deliverables must go under outputs/.
Codex-Compatible Workflow
- Read this SKILL.md before claiming to use the skill.
- Read the relevant project files listed above.
- Build an evidence inventory before drafting, revising, or judging claims.
- If evidence is missing, use NEEDS_USER_EVIDENCE, CITATION_NEEDED, DATA_NEEDED, or BASELINE_NEEDED instead of inventing content.
- For review-only, check-only, diagnose-only, or planning tasks, write a Markdown report to the default output path and do not modify paper.md or storyline.md.
- Before modifying paper.md or storyline.md, provide an edit plan with target section, evidence used, proposed change, and risk; wait for explicit user confirmation.
- After approved edits, recommend a targeted review report under reviews/.
File Modification Policy
- May modify paper.md: Only after an edit plan and explicit user confirmation.
- May modify storyline.md: No by default.
- Requires user confirmation before source edits: Yes.
Safety Rules
- Do not fabricate experiments, results, datasets, baselines, citations, novelty, conclusions, or reviewer comments.
- Do not use legacy plugin commands, plugin tools, plugin-specific agents, UI status panels, or hidden workflow state.
- Do not write workflow state to JSON logs. Use local Markdown files in reviews/, notes/, references/, and outputs/.
- If the requested task depends on unavailable external files or unverified evidence, stop and ask for the missing material.
Migration Note
This is a Codex-compatible migration of the CoPaper-style state-machine-markdown-helper skill. The original intent is preserved, but execution is local-file-driven and Markdown-based.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingexamples/demo-paper-project/.agents/skills/state-machine-markdown-helper/SKILL.md
Popularity
- Repository stars
- 1
- 7-day trend score
- 8
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/magicj1995/papersmith/state-machine-markdown-helper)