issue-driven
Skill1 starsChanged 6 days agoApache-2.0View on GitHub
Run the Issue-Driven Framework (by GoodRelax) with the person. It walks from the background of a matter to the one question worth answering (the Issue), then down through challenges, measures, and tasks to the answer, one step at a time. It works in the chat, and on the local whiteboard of this plugin (server board-control) when the person asks for it or agrees to it. Use when the user types /gr-whiteboard:issue-driven, asks to sort out a matter with the Issue-Driven Framework (Yomon), or when consult-on-board picks it.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- soilSpoon/skillstheir own version, first seen Oct 20, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- soilSpoon/skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository5 other files it gives its agents.
- consult-on-boardSkill
- debug-board-serverSkill
- five-whysSkill
- four-formsSkill
- talk-on-boardSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use the Issue-Driven Framework and the board to find, with the person, the one question worth answering, and to lead them step by step to …
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
issue-driven
Use the Issue-Driven Framework and the board to find, with the person, the one question worth answering, and to lead them step by step to its answer.
Talk in the chat first, one step at a time in short bullets. Open the board only when the person asks for it, or when a picture would make it clearer and you ask "Shall we sort this out on the whiteboard?" and they agree; then run it as the skill talk-on-board says. After open_board, start the watch Monitor of talk-on-board (Open step 2, client.js watch) at once, or you miss every Send. Draw the person's words, not your own ideas, and validate them, as consult-on-board says.
The eight steps
| Step | What it holds | It holds when |
| Background | The situation as it is | Free form |
| Purpose | What the work is for | A verb phrase |
| Analysis | Facts sorted, compared, and read | Free form; it leads to the Issue |
| Issue | The one question worth answering | One question that can be answered, is worth answering, and is essential. Do not go on to Challenge until it is a question |
| Challenge | What to overcome to answer it (strategy) | A verb phrase; a strategy to solve the Issue |
| Measure | How to overcome each challenge (tactics) | A verb phrase; the tactics for its Challenge |
| Task | The concrete work of each measure | A verb phrase; the concrete work of its Measure |
| Answer | The answer to the Issue, reached through the steps | A statement that answers the Issue, or says it is not reached yet and why |
The Japanese labels of the steps are in data/labels.json (SKILL_DIR is the folder of this file).
Run
Show the eight steps in one row first. Ask the person step by step: Background, Purpose, Analysis, Issue, Challenge, Measure, Task, Answer. Organize each answer under its heading. Never skip a step.
- At the start, show the eight steps and say in a few words where you are now (e.g. "step 2 of 8"). Do not promise how many rounds it takes.
- The row:
draw_mermaidwithfileset toSKILL_DIR/data/flow-ja.mmdfor a Japanese speaker, orSKILL_DIR/data/flow-en.mmd(absolute paths). Above it, write the title: the framework name and the subject (e.g. "Issue-Driven Framework Sample Inc. study group"). - Fill the box of the current step light blue (
edit_items,bgblue). Leave the other boxes as they are. Add no other colors. - Under the row, write the headings ("# Background", in the person's language) with the person's words as bullets. Write each measure indented under its challenge, and each task under its measure.
- Estimate the height of each step's area first and leave room between the areas. When added lines overlap the area below, move the lower areas down.
When a step pauses, weigh how much the person has said, how complex or hard it is, and what interests them. If a framework would help, pick one or two from consult-on-board's frameworks.json (the table below is a start), each with its purpose and why it fits now. Offer it in one short, inviting sentence with its benefit, e.g. "We have many options now. Shall we sort them on a decision matrix? It makes the priorities easier to set." The person decides. Make at most one offer per pause, and none when the step is already clear. Talk it through in the chat first, draw it only on the board the person has opened or agreed to, and validate it as consult-on-board says:
Step Tools Background pest, 3c, 5-forces Purpose mvv, smart Analysis swot, fishbone, as-is-to-be, four-forms Issue 5-whys, hmw Challenge logic-tree, ansoff, mece Measure ecrs, scamper, decision-matrix, eisenhower Task raci, gantt, kanban After the answer kpt, ywt, pdca
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

