Pmstudio Nfr logo

Pmstudio Nfr

Community
coco-research
pmstudio-nfr

Detailed completeness audit of all project documents. Use when someone asks "are we ready for production", "audit our docs", "readiness check", "nfr tracker", or "what's missing". Do NOT use for a quick command listing — use /pmstudio instead. Scans every document for section-level completeness, reports staleness, and gives prioritized gap-closure recommendations.

Overview

Publishercoco-research
Repositorycoco
Skill namepmstudio-nfr
Stars
550
Forks
12
Bundled files
6
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.

  • 6 bundled files

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

  • Open source

    Published by coco-research on GitHub. Read the source before you install it.

Installation

Install the Pmstudio Nfr 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/coco-research/coco/tree/main/skills/nfr-tracker
  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/coco-research/coco.git /tmp/coco
mkdir -p .claude/skills
cp -r /tmp/coco/skills/nfr-tracker .claude/skills/pmstudio-nfr
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pmstudio Nfr 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 Pmstudio Nfr 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 Pmstudio Nfr 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.

NFR Tracker — Operational Readiness Auditor

Purpose

Meta-command that discovers all project documents, checks existence and freshness, and produces a readiness dashboard with prioritized recommendations for what to create or update next.

Process

Step 1: Detect Project Context

Read these files to understand the project:

  1. CLAUDE.local.md — project name, type, architecture, folder structure
  2. .sync-watch.json — registered documents and watch directories
  3. Run ls -R on the project root to discover all files

Determine the product lifecycle stage from context:

  • Ideate/Build — pre-production (DR/IRP not yet required)
  • Production — live product (DR/IRP required)
  • Mixed — some components live, some building (e.g., ProductA production + ProductB ideate)

Step 2: Scan Document Registry

Check for each document type. For each, record: exists (Y/N), path, last modified date, stale (Y/N based on threshold).

Document registry:

Document TypeSource SkillFile PatternRequired WhenStaleness
PRD/prd-generatorPRD/*.html, PRD/*.mdAlways30 days
Project Memory(auto)CLAUDE.local.mdAlways7 days
Presentation/project-docsPresentations/*.htmlRecommended30 days
Architecture Map/project-docsArchitecture/*.html, *Architecture*.htmlIf PRD has architecture section60 days
Stakeholder Directory/project-docsData/Stakeholder*.xlsx, Data/Stakeholder*.mdIf >5 stakeholders30 days
Change Log/change-logData/Change-Log*.mdRecommended14 days
ARB Presentation/arb-reviewPresentations/ARB-*.htmlBefore architecture review90 days
DR Plan/dr-planOperational/DR-Plan*.htmlProduction180 days
Incident Response Plan/irpOperational/IRP-*.htmlProduction180 days
Recovery Procedures/recovery-planOperational/Recovery-*.htmlIf DR Plan exists180 days
Verification Report/project-docsVerification/*.mdBefore milestones60 days

Staleness calculation: Compare file modification date to today. If (today - last_modified) > threshold, mark as STALE.

Search strategy: Use glob patterns first. If the project uses non-standard paths (from CLAUDE.local.md folder structure), adapt the search. Example: Some projects store PRDs in non-default paths like ProductB-Control-Framework/PRD/ not PRD/.

Step 3: Assess Completeness (Optional Deep Check)

If --deep flag or user requests "thorough check":

For each FOUND document, open it and check for key sections:

  • PRD: Has executive summary, requirements, timeline, risks? Missing sections = partial.
  • DR Plan: Has RTO/RPO targets, scenarios, procedures? Missing = partial.
  • IRP: Has severity matrix, escalation contacts, playbooks? Missing = partial.

Without --deep, existence + freshness is sufficient.

Step 4: Generate Recommendations

Prioritize missing/stale documents:

Priority logic:

  1. CRITICAL — Production product missing DR or IRP
  2. HIGH — Any required document missing or stale >2x threshold
  3. MEDIUM — Recommended document missing or stale >1x threshold
  4. LOW — Optional document missing

Each recommendation includes:

  • What to create/update
  • Why it matters
  • The slash command to run

Step 5: Output Report

Console output (default):

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 NFR TRACKER ► READINESS REPORT — {Project Name}
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Lifecycle: {Production / Ideate / Mixed}
Scanned: {timestamp}

| Document              | Status  | Path              | Updated    | Stale? |
|-----------------------|---------|-------------------|------------|--------|
| ...                   | FOUND   | ...               | YYYY-MM-DD | No     |
| ...                   | MISSING | —                 | —          | —      |
| ...                   | FOUND   | ...               | YYYY-MM-DD | STALE  |

Coverage: N/M ({pct}%)    Stale: N    Missing: N

Recommendations:
1. [{priority}] {description}
   → Run: /{command}
...
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Markdown file output (with --format md):

Write to Operational/Readiness-Report-{YYYY-MM-DD}.md with the same content plus a header with project metadata.

Modes

  • /nfr-tracker — Full audit, console output
  • /nfr-tracker --format md — Write report to file
  • /nfr-tracker --deep — Check document completeness, not just existence
  • /nfr-tracker --scope {name} — Filter to a specific product/instance within the project

Critical Rules

  1. Read-only. This skill never creates or modifies documents. It only reports.
  2. Adapt paths. Don't assume standard folder structure. Read CLAUDE.local.md for actual paths.
  3. No false positives. Only mark FOUND if the file has real content (>100 bytes). Empty scaffolds don't count.
  4. Date accuracy. Use file system modification date, not content parsing, for freshness checks.

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 Pmstudio Nfr AI skill do?

Detailed completeness audit of all project documents. Use when someone asks "are we ready for production", "audit our docs", "readiness check", "nfr tracker", or "what's missing". Do NOT use for a quick command listing — use /pmstudio instead. Scans every document for section-level completeness, reports staleness, and gives prioritized gap-closure recommendations.

Why use Pmstudio Nfr on TypingMind?

Because you install it once and use it with any model. Pmstudio Nfr 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 Pmstudio Nfr in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/coco-research/coco/tree/main/skills/nfr-tracker. 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 Pmstudio Nfr?

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 Pmstudio Nfr?

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

Is the Pmstudio Nfr AI skill free?

It is published on GitHub by coco-research. Check the repository for licensing terms. 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 👇