write-opportunity
Skill0 starsChanged 17 days agoMITView on GitHub
Write a 1-2 page opportunity brief — problem, evidence, bets, non-goals, and the ask. Use when the user wants an opportunity brief, a pitch, a problem statement, or /write-opportunity. Do not write a PRD, requirements, or product code.
In this repository66 other files it gives its agents.
- AGENTS.mdAGENTS.md
- a11y-passSkill
- assess-changeSkill
- build-regression-packSkill
- charter-exploratorySkill
- classify-dataSkill
- commitSkill
- cut-releaseSkill
- data-changeSkill
- debugSkill
- design-experimentSkill
- diff-environmentsSkill
- draft-steercoSkill
- engineering-barSkill
- explain-codeSkill
- explore-codebaseSkill
- fix-ciSkill
- handoffSkill
- implement-changeSkill
- incident-triageSkill
- lean-reviewSkill
- map-dependenciesSkill
- map-design-handoffSkill
- map-processSkill
- open-prSkill
- performanceSkill
- plan-data-migrationSkill
- plan-incrementSkill
- plan-rollbackSkill
- plan-uatSkill
- prioritize-backlogSkill
- production-passSkill
- ready-to-mergeSkill
- record-decisionSkill
- refactor-safelySkill
- revert-changeSkill
- review-architectureSkill
- review-changeSkill
- review-pipelineSkill
- security-passSkill
- shape-workSkill
- ship-notesSkill
- spec-analyticsSkill
- spec-observabilitySkill
- start-projectSkill
- synthesize-discoverySkill
- triage-blockersSkill
- triage-defectSkill
- update-raidSkill
- verify-uiSkill
- write-api-examplesSkill
- write-architectureSkill
- write-designSkill
- write-dev-tasksSkill
- write-docsSkill
- write-integration-contractSkill
- write-nfrSkill
- write-prdSkill
- write-requirementsSkill
- write-runbookSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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 19
Do not implement. Do not invent users, market size, or competitors.
- Very specific: line 31
If the ask is already a committed initiative with success checks, say so and offer write-prd.
- Distinctive: line 38
If there is no evidence — only a solution idea — stop and ask for the hurt.
- Very specific: line 48
Read AGENTS.md if present.
- Distinctive: line 58
No secrets. No invented vendors or SLOs.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Write opportunity
Capture whether this is worth a PRD. This is not a PRD (write-prd), not requirements (write-requirements), and not a status update (write-status).
Do not implement. Do not invent users, market size, or competitors.
Is this the right skill?
| Signal | Do this instead |
| Why / who / success are already agreed | write-prd |
| Interview notes to distill | synthesize-discovery first, then this (or skip this if a PRD is the next artifact) |
| One-line bug or tiny change | shape-work |
| How we will build it | write-design |
| Status / RAG | write-status |
If the ask is already a committed initiative with success checks, say so and offer write-prd.
Required inputs
- A problem the user can point at (ticket, incident, quote, metric this program already has, or a written complaint)
AGENTS.mdif present;context/glossary.mdandcontext/systems-of-record.mdif they exist
If there is no evidence — only a solution idea — stop and ask for the hurt. Do not invent the hurt.
Human decisions (do not invent)
- Whether the program will spend discovery or PRD time on this
- Who the audience is, if not already in context
- Any numeric target that is not already measured
Procedure
- Read
AGENTS.mdif present. Readcontext/files it points at. Use terms as the glossary defines them. - Find the home: first existing
docs/discover/, a pathAGENTS.mdnames, or offer to createdocs/discover/. - Name the file like existing briefs. If none,
docs/discover/YYYY-MM-DD-<slug>.md. - Open references/opportunity-template.md. Copy every heading. Write
n/awhen unused. Do not add sections. - Fill only from the user and files you read:
- Problem is a hurt, not a feature.
- Evidence names sources (path, ticket id, quote). No source →
unknown, not a story. - Bets are optional ways to respond, not a design.
- Non-goals is non-empty.
- Ask is the next human decision (fund a PRD, run discovery, drop it).
- No secrets. No invented vendors or SLOs.
Output
- Path:
docs/discover/YYYY-MM-DD-<slug>.md(or the existing discover home) - Template:
references/opportunity-template.md
Quality bar
- Problem can be read without guessing the solution
- At least one evidence line names a real source, or is explicitly
unknown - Non-goals is non-empty
- Ask names a next skill or a human stop
- Unused headings are
n/a, not deleted
Done
- Path or the full text in the reply
- The problem in one sentence
- Next skill: usually
synthesize-discoveryif evidence is raw, elsewrite-prd, else stop — need user
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.