opportunity-tree
Skill2 starsChanged 50 days agoMITView on GitHub
Render a Teresa Torres Opportunity Solution Tree from the graph — outcome at the root, opportunities, Ideas as solutions, backlog questions as experiments. Use on /opportunity-tree or for an OST / strategic view.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- Adelie-Squad/solosquadtheir own version, first seen Nov 8, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- Adelie-Squad/solosquad★ 25same 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 repository31 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- affinitySkill
- ai-personaSkill
- analytics-syncSkill
- backlogSkill
- catalogSkill
- cold-startSkill
- contradictionsSkill
- demo-dataSkill
- dovetail-syncSkill
- exportSkill
- extract-findingsSkill
- feature-panelSkill
- forget-participantSkill
- graph-lintSkill
- interview-guideSkill
- journey-mapSkill
- persona-avatarSkill
- persona-querySkill
- persona-talkSkill
- persona-voiceSkill
- persona-workshopSkill
- prdSkill
- prioritizeSkill
- researcherSkill
- retentionSkill
- source-syncSkill
- subject-accessSkill
- welcomeSkill
The file
Files
opportunity-tree — OST from Correlations
The graph already contains an Opportunity Solution Tree in pieces: every persona's ## Correlations ends in → Opportunity:, every Ideas/ file is a candidate solution, and Research backlog.md holds the open assumptions. This skill assembles them into the view PMs know from Teresa Torres — without inventing a single node.
Trigger
/opportunity-tree ← whole graph
/opportunity-tree Personas/Emma.md ← one persona's slice
/opportunity-tree --outcome "<metric>" ← name the root outcome explicitlyMapping (strict — every node traces to a file)
- Outcome (root) — the product outcome; ask the user if not given (suggest candidates from
Product Context.md/ Ideas'Metric to watchfields). One root; a second outcome is a second tree. - Opportunities (branches) — the
→ Opportunity:lines from## Correlations, each annotated with its persona and its supporting Signals/Evidence (that's L5-grade material by construction). Pains with no correlation yet can appear as thinner branches, marked "pain, not yet correlated (L3/L4)". - Solutions (leaves) —
Ideas/files under the opportunity they address; unscored ideas showRICE: TBD(from the## PM scoringblock when present). - Experiments / assumptions — matching open rows from
Research backlog.mdunder the solution or opportunity they'd de-risk.
Output
Mermaid diagram (default — pasteable into most docs) plus an indented-list fallback; offer to save as PRDs/Opportunity tree <YYYY-MM-DD>.md. Every node label carries its source in parentheses, short form.
Reading the tree honestly
- A bare branch is a finding, not a failure — an opportunity with no solutions means ideation hasn't happened; a solution with no experiments means it's about to be built on hope. Point both out.
- An orphan Idea (no opportunity above it) is roadmap-by-momentum — flag it and ask whether a Correlation is missing (needs synthesis:
ai-personaLevel 4) or the idea lacks grounding (needs research). - The tree is a view: it never edits Correlations, Ideas, or the backlog. Gaps it exposes become backlog rows only with the user's yes.
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.

