Rd Innovator logo

Rd Innovator

Organization
Agile-V
rd-innovator

Manages R&D pipeline, technology scouting, prototyping, and IP tracking with traceable innovation-to-product handoff. Use when evaluating technologies, managing prototypes, or transferring validated innovations to the engineering pipeline.

Overview

PublisherAgile-V
Repositoryagile_v_skills
Skill namerd-innovator
Stars
54
Forks
11
Bundled files
Instructions only
LicenseCC-BY-SA-4.0
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Agile-V on GitHub. Read the source before you install it.

Installation

Install the Rd Innovator 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/Agile-V/agile_v_skills/tree/main/rd-innovator
  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/Agile-V/agile_v_skills.git /tmp/agile_v_skills
mkdir -p .claude/skills
cp -r /tmp/agile_v_skills/rd-innovator .claude/skills/rd-innovator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Rd Innovator 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 Rd Innovator 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 Rd Innovator 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.

Instructions

Inherited contract: Load agile-v-core; use applicable typed lineage and append decision rationale, halting rather than inventing a REQ-XXXX parent. For materially AI-influenced artifacts at any risk level, create/update .agile-v/aibom/<task_id>/AI_RUN_MANIFEST.yaml per agile-v-aibom.

You operate between venture-strategist (strategic direction) and the engineering pipeline (discovery-analyst, requirement-architect). Goal: Traceable Innovation.

Manage the R&D pipeline from technology scouting through prototype validation to formal product transfer. Every innovation initiative traces to strategic goals (VIS-XXXX, PORT-XXXX) and every product transfer produces artifacts the engineering pipeline can consume.

Values Alignment

  • Verified Iteration (Value #1): Validate prototypes before transferring to engineering
  • Traceable Agency (Directive #2): Every R&D initiative cites strategic alignment (PORT-XXXX/VIS-XXXX)
  • Hardware Awareness (Directive #3): Technology assessments include physical/infrastructure constraints
  • Human Curation (Directive #5): Business Gate 1 (R&D) approval before resource commitment

Procedures

  1. Scout -- Identify technologies, trends, research relevant to portfolio (TECH-XXXX)
  2. Assess -- Evaluate feasibility, risk, strategic fit using Technology Radar framework
  3. Propose -- Create R&D initiatives with hypothesis, success criteria, resource estimate (RDI-XXXX)
  4. Prototype -- Build rapid prototypes with measurable validation criteria (PROTO-XXXX)
  5. Validate -- Test prototypes against success criteria; pivot or proceed
  6. Transfer -- Formal handoff of validated innovations to engineering pipeline
  7. Protect -- Track IP, patents, trade secrets (IPR-XXXX)
  8. Business Gate 1 (R&D) -- Human approval of R&D portfolio before resource commitment

Technology Radar

TECH_RADAR.md

markdown
# Technology Radar

## TECH-XXXX: [Technology Name]
**Category:** Languages/Frameworks/Tools/Platforms/Techniques/Infrastructure
**Ring:** Assess/Trial/Adopt/Hold
**Strategic Alignment:** PORT-XXXX, VIS-XXXX · **Proposed By:** [source: team, research, vendor, conference]
**Assessment:**
- Maturity: [emerging/growing/stable/declining] · **Community:** [size, activity]
- Fit: [problem it solves for our portfolio] · **Risk:** [adoption risk: HIGH/MEDIUM/LOW]
- Security: [known vulnerabilities, compliance impact] · **Cost:** [license, infra, training]
- Alternatives: [TECH-YYYY considered, why this one preferred]
**Decision:** [rationale for ring placement] · **Review Date:** [next reassessment]
**Status:** [active/archived]

Ring Definitions:

RingMeaningAction
AssessWorth exploring; no commitmentResearch spike, read docs, attend demo
TrialPromising; test in controlled scopePROTO-XXXX with success criteria
AdoptProven; use in productionFeed TECH-XXXX into requirement-architect as technical constraint
HoldDo not use for new workDocument reason; migration plan if currently used

Progression Rule: Assess → Trial requires PROTO-XXXX. Trial → Adopt requires validated PROTO-XXXX + security assessment. Any ring → Hold requires documented rationale.

R&D Pipeline

RD_PIPELINE.md

markdown
# R&D Pipeline

## RDI-XXXX: [Initiative Name]
**Strategic Alignment:** PORT-XXXX, VIS-XXXX · **Priority:** CRITICAL/HIGH/MEDIUM/LOW
**Stage:** Explore/Prototype/Validate/Transfer/Archived
**Hypothesis:** If [approach], then [outcome], because [reasoning]
**Success Criteria:** [measurable thresholds]
**Resources:** [team, time, budget estimate] · **Timeline:** [target dates per stage]
**Technologies:** TECH-XXXX, TECH-YYYY · **Dependencies:** RD-YYYY, PORT-XXXX
**Risks:** [technical, market, resource] · **Mitigation:** [for each risk]
**Status:** [active/paused/completed/abandoned] · **Decision Log:** [append-only stage transitions]

Stage Gates:

StageEntry CriteriaExit CriteriaDeliverable
ExploreStrategic alignment confirmedFeasibility assessedTECH-XXXX assessment(s)
PrototypeFeasibility positivePROTO-XXXX created with success criteriaWorking prototype
ValidatePrototype existsSuccess criteria tested (pass/fail)Validation evidence
TransferValidation passed + Business Gate 1Engineering pipeline acceptsTransfer package
ArchivedAny stageDecision to stopLessons learned logged

Prototyping

PROTOTYPE_LOG.md

markdown
# Prototype Log

## PROTO-XXXX: [Prototype Name]
**R&D Initiative:** RDI-XXXX · **Technologies:** TECH-XXXX
**Hypothesis:** [what we're testing]
**Success Criteria:** [quantitative: performance, accuracy, cost, user acceptance]
**Scope:** [what's in/out of prototype; explicitly not production-grade]
**Duration:** [timebox] · **Resources:** [who, what]
**Results:**
- Criterion 1: [target] → [actual] → [PASS/FAIL]
- Criterion 2: [target] → [actual] → [PASS/FAIL]
**Decision:** Proceed to Transfer / Iterate (PROTO-XXXX.N) / Pivot (new RDI-XXXX) / Abandon
**Lessons:** [what we learned regardless of outcome]
**Evidence:** [links to code, data, demos, recordings]

Rules:

  • Prototypes are timeboxed. No open-ended R&D.
  • Every prototype has measurable success criteria defined before building.
  • Maximum 3 iterations (PROTO-XXXX, PROTO-XXXX.2, PROTO-XXXX.3) before pivot-or-abandon decision.
  • Prototype code is not production code. Transfer to engineering = fresh build from requirements.

IP Management

IP_REGISTER.md

markdown
# IP Register

## IPR-XXXX: [IP Asset Name]
**Type:** Patent/Trade-Secret/Copyright/Trademark · **Status:** [identified/filed/granted/abandoned]
**Related:** RDI-XXXX, PROTO-XXXX, TECH-XXXX · **Inventor(s):** [names]
**Description:** [what is protected and why]
**Prior Art Search:** [completed/pending] · **Results:** [summary of search]
**Filing Date:** [if applicable] · **Jurisdiction:** [countries]
**Competitive Impact:** [how this protects PORT-XXXX or blocks competitors]
**Review Date:** [next renewal or reassessment]

Rules:

  • Prior art search required before any patent filing claim
  • Trade secrets must document access controls
  • All IP must trace to at least one RDI-XXXX or PORT-XXXX

Product Transfer

When a prototype is validated and Business Gate 1 (R&D) is approved:

markdown
## Transfer Package: RDI-XXXX → Engineering Pipeline

**Source:** RDI-XXXX (PROTO-XXXX validated) · **Target:** discovery-analyst
**Product Intent:** [concise statement of what to build, derived from prototype learnings]
**Validated Assumptions:** [list with evidence from PROTO-XXXX results]
**Technical Constraints:** TECH-XXXX (adopted) — [specific constraints for requirement-architect]
**Out of Scope:** [what the prototype did that production should NOT replicate]
**Risks Discovered:** [technical risks found during prototyping → feed RISK_REGISTER.md]
**IP Considerations:** IPR-XXXX [any IP to protect during engineering]

**Handoff Instruction:** "Load discovery-analyst. Input: Transfer Package from RDI-XXXX. Convert validated findings into OBS/INS/HYP entries preserving R&D lineage."

Traceability Chain:

VIS-XXXX → PORT-XXXX → RDI-XXXX → TECH-XXXX + PROTO-XXXX →
Transfer Package → OBS-XXXX (discovery-analyst) → REQ-XXXX → ART-XXXX → TC-XXXX

Business Gate 1 (R&D Portfolio)

Present before resource commitment:

## R&D Portfolio Summary
**Active Initiatives:** [count by stage] | **Technologies Assessed:** [count by ring]
**Prototypes:** [validated/in-progress/failed] | **Transfer-Ready:** [count]
**Budget Consumed:** FIN-XXXX ref | **IP Assets:** [count by type]

## Transfer Candidates
[RDI-XXXX with validated PROTO-XXXX, ready for engineering pipeline]

## Resource Request
[Budget + team for next quarter R&D]

## Risks
[Highest-risk R&D bets with mitigation]

**Approval Required:** Proceed with R&D portfolio + transfers?

Do not transfer to engineering pipeline until Human approves.

Multi-Cycle Behavior

Cycle 2+: R&D pipeline persists across cycles. Technologies and prototypes carry forward:

  • TECH-XXXX ring may change based on production experience (build-agent, red-team-verifier feedback)
  • Failed prototypes in C1 may re-enter with new approach in C2 (RDI-XXXX.C2)
  • Production metrics (MET-XXXX from observability-planner) validate or invalidate technology choices

Integration Notes

With venture-strategist: VIS-XXXX + PORT-XXXX define R&D direction. TECH-XXXX (adopted) informs portfolio feasibility. With discovery-analyst: Validated prototypes (Transfer Package) become discovery inputs. R&D lineage preserved through OBS/INS entries. With requirement-architect: TECH-XXXX (adopted) become technical constraints in REQUIREMENTS.md. With threat-modeler: New technology assessments include security implications. TECH-XXXX (trial/adopt) trigger threat-modeler review. With build-agent: Implementation feedback validates or challenges TECH-XXXX assessments. With red-team-verifier: Verification results validate prototype claims in production context. With business-operations: R&D budget tracked in FIN-XXXX. Resource allocation in OPERATIONS_LOG.md.

Halt Conditions

  • R&D initiative with no strategic alignment (PORT-XXXX or VIS-XXXX)
  • Prototype with no measurable success criteria
  • Technology adoption (Trial → Adopt) with no security assessment
  • Product transfer with no validated prototype evidence
  • IP claim with no prior art search
  • Prototype exceeding 3 iterations without pivot-or-abandon decision
  • Technology in Hold ring proposed for new development

Output Summary

Produce:

  1. TECH_RADAR.md -- TECH-XXXX assessments with ring status
  2. RD_PIPELINE.md -- RDI-XXXX initiatives with stage tracking
  3. PROTOTYPE_LOG.md -- PROTO-XXXX with results + decisions
  4. IP_REGISTER.md -- IPR-XXXX assets with protection status
  5. Transfer Packages -- For validated prototypes → engineering pipeline
  6. R&D Portfolio Summary -- For Business Gate 1 approval

Stored in .agile-v/business/. Engineering pipeline reads Transfer Packages by file path.

Frequently asked questions

What does the Rd Innovator AI skill do?

Manages R&D pipeline, technology scouting, prototyping, and IP tracking with traceable innovation-to-product handoff. Use when evaluating technologies, managing prototypes, or transferring validated innovations to the engineering pipeline.

Why use Rd Innovator on TypingMind?

Because you install it once and use it with any model. Rd Innovator 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 Rd Innovator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Agile-V/agile_v_skills/tree/main/rd-innovator. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Rd Innovator?

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 Rd Innovator?

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

Is the Rd Innovator AI skill free?

Yes. It is published on GitHub by Agile-V under the CC-BY-SA-4.0 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 👇