decision-flow
Skill1 starsChanged 18 days agoMITView on GitHub
Use for approval or eligibility logic with labelled approve, reject, and escalate branches ending in distinct outcomes.
In this repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- architecture-diagramSkill
- data-flowSkill
- process-flowSkill
- architecture-diagramsSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use this skill when the diagram explains a choice and its outcomes.
- Very specific: line 12
Use shape: "decision" for each question and shape: "end" for each outcome.
- Very specific: line 13
Every branch has source, target, and a useful label, such as Yes, No, Approve, Reject, or Escalate.
≈ “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
Decision flow
Use this skill when the diagram explains a choice and its outcomes. Give each decision a diamond. Label every outgoing branch and end each outcome at its own terminator. Mark exception paths dashed.
Spec rules
- Use
shape: "decision"for each question andshape: "end"for each outcome. - Every branch has
source,target, and a usefullabel, such asYes,No,Approve,Reject, orEscalate. - Set
dashed: truefor exception and escalation paths. Setcolorto a six digit RGB hex string when a branch needs emphasis. direction: "TB"suits most decision trees. Give all node IDs unique strings.
{"title":"KYC decision","direction":"TB","nodes":[{"id":"start","shape":"start"},{"id":"review","shape":"decision","label":"Identity verified?"},{"id":"approve","shape":"end","label":"Approve"},{"id":"reject","shape":"end","label":"Reject"},{"id":"escalate","shape":"end","label":"Escalate"}],"edges":[{"source":"start","target":"review"},{"source":"review","target":"approve","label":"Yes"},{"source":"review","target":"reject","label":"No"},{"source":"review","target":"escalate","label":"Exception","dashed":true}]}Render and inspect
On first use run python -m tools.bootstrap. Run python -m archdiagram.cli validate spec.json, then python -m archdiagram.cli render spec.json -f drawio -o out/decision.drawio. Other formats are svg, html, pdf, pptx, and vsdx; PDF needs python -m tools.bootstrap --pdf. Inspect branch labels and confirm every result has its own end node. Revise and render again. Via MCP, use get_diagram_template("decision_flow"), validate_spec, and generate_diagram.
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.

