research-design

Generate three to five solution concepts for a defined problem and score each on feasibility, impact, effort and risk. Use when the problem statement is agreed and the user wants different ways to sol

SKILL.md

GitHub

Design

Diverge on solutions for "$ARGUMENTS". Generate multiple solution concepts, evaluate feasibility, and prioritize the most promising approaches.

Arguments. $ARGUMENTS may contain the project name and optional flags. Take the first token as <project> and treat --skip-checks as a flag; never include flags in file paths. All paths below use <project>. If --skip-checks is present, skip the prerequisite check and, before writing any artifact, append one line to .singularskills/log.jsonl: {"ts":"<ISO timestamp>","skill":"research-design","workflow":"research","phase":3,"project":"<project>","event":"skipped","artifact":"03-design.md","note":"<reason or \"none given\">"}.

Prerequisites

Part of a workflow. This skill is phase 3 (Design) of the Double Diamond workflow (research); cross-domain workflows run it too. First check .singularskills/log.jsonl for an open run for this project: a run-started line with "project":"<project>" and no later run-finished line for the same workflow and project. If one exists, the conductor is running you: continue here. Otherwise, if the user asked to start, run, continue or resume a process or workflow rather than this one step, do not continue here: invoke the workflow skill with the workflow the user asked for, or research when they named none, followed by <project>; it runs this phase in order, asks before it writes and records the run. Otherwise continue here: a later phase runs on its own, behind its gate.

Run this skill's gate before writing: sh <this skill's folder>/scripts/gate.sh <project> <project root>, where <project root> is the folder that contains .singularskills/ (use . when you are already there). If it exits non-zero, stop and tell the user what it printed, unless --skip-checks was given (see Arguments). On a refusal, before you stop, append this line to .singularskills/log.jsonl (create the folder and file if missing): {"ts":"<ISO timestamp>","skill":"research-design","workflow":"research","phase":3,"project":"<project>","event":"refused","artifact":"03-design.md","note":"<what the gate printed>"}. Once the gate has passed, or under --skip-checks once you have appended the skipped line, append this line before you start work: {"ts":"<ISO timestamp>","skill":"research-design","workflow":"research","phase":3,"project":"<project>","event":"started","artifact":"03-design.md","note":""}.

Read .singularskills/research/<project>/01-discover.md and .singularskills/research/<project>/02-define.md.

If 02-define.md does not exist, tell the user:

Phase 2 (Define) has not been completed for "<project>". Run /research-define <project> first, or use --skip-checks to bypass.

Process

  1. Read context files:

    • Read .singularskills/research/<project>/01-discover.md for research findings
    • Read .singularskills/research/<project>/02-define.md for problem statement, HMW questions, and success criteria
    • Read references/double-diamond-guide.md for methodology reference
  2. Research existing solutions:

    • Use WebSearch to find case studies, best practices, and proven approaches related to each HMW question
    • Use WebFetch to read detailed implementations or methodologies
    • Note what worked, what failed, and why
  3. Generate solution concepts:

    • Create 3-5 distinct solution concepts, each addressing the problem statement from a different angle
    • For each concept: describe the approach, key components, and how it addresses the HMW questions
    • Include at least one unconventional or contrarian approach
  4. Evaluate each concept:

    • Feasibility: How realistic is implementation? What resources are needed?
    • Impact: How well does it address the problem statement and success criteria?
    • Effort: What's the relative effort to implement?
    • Risk: What could go wrong? What assumptions are being made?
  5. Prioritize and recommend:

    • Rank concepts by impact/feasibility balance
    • Recommend top 1-2 concepts for validation in the Deliver phase
    • Explain trade-offs between the top options
  6. Write the artifact to .singularskills/research/<project>/03-design.md with sections:

    • Problem Recap — one-paragraph summary from Define
    • Solution Concepts — each concept with description and rationale
    • Evaluation Matrix — feasibility, impact, effort, risk per concept
    • Recommendations — top concepts with reasoning
    • Validation Plan — what to test in the Deliver phase

Output

The solution concepts written to .singularskills/research/<project>/03-design.md. Present a summary to the user highlighting:

  • Number of concepts generated
  • Top recommendation and why
  • Key trade-offs between top options
  • What needs validation in the Deliver phase

Record the run. After you have written the artifact, append this line to .singularskills/log.jsonl (the started line of Prerequisites, with "event":"finished"): {"ts":"<ISO timestamp>","skill":"research-design","workflow":"research","phase":3,"project":"<project>","event":"finished","artifact":"03-design.md","note":""}.

Open the artifact with this frontmatter (agent is the agent you run in, or unknown; gate is passed when the gate ran clean and skipped under --skip-checks):

---
skill: research-design
workflow: research
phase: 3
project: <project>
started: <ISO timestamp>
finished: <ISO timestamp>
agent: <the agent you run in, or "unknown">
gate: <passed|skipped>
---

End the artifact with ## Decisions and ## Open questions, in this shape:

## Decisions
- <what was chosen> — <why> — <what was rejected>

## Open questions
- <what the next phase or a reviewer must settle>