product-ops-context
Skill0 starsChanged 18 days agoMITView on GitHub
Create or update the product ops context file every other skill in this library reads first — the product, the teams and who decides what, the meeting rhythm, the tools and where things live, the metric definitions, and how launches work. Use at the start of any new project or team before using other product ops skills, when someone says "set up context," "here's how our team works," "remember our tools," "update our context," or "log this change," or whenever a skill keeps asking for the same background. It creates `.agents/product-ops-context.md`.
In this repository33 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- beta-program-managerSkill
- cross-team-dependency-mapSkill
- customer-advisory-board-prepSkill
- data-request-routerSkill
- decision-logSkill
- deprecation-planSkill
- duplicate-request-mergingSkill
- experiment-logSkill
- feature-flag-trackingSkill
- feedback-taggingSkill
- information-debt-auditSkill
- internal-enablement-briefSkill
- kpi-health-checkSkill
- launch-readiness-checklistSkill
- meeting-to-action-converterSkill
- new-pm-onboarding-packSkill
- pricing-packaging-change-logSkill
- process-documentationSkill
- product-metrics-definitionsSkill
- quarterly-planning-prepSkill
- raci-builderSkill
- release-notes-draftingSkill
- request-intake-triageSkill
- retro-facilitationSkill
- ritual-calendarSkill
- roadmap-hygieneSkill
- sprint-review-summarySkill
- support-escalation-patternsSkill
- tool-stack-auditSkill
- vendor-evaluation-scorecardSkill
- voice-of-customer-digestSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
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 16
If the file exists: read it, give a three-line summary of what's in it, show the version and the last two changelog entries, and ask which …
- Distinctive: line 20
Draft from what's here (faster): read whatever the person has shared or what's in the project — team pages, onboarding docs, a roadmap …
- Distinctive: line 25
Use only what the person or their documents say.
- Distinctive: line 80
People, not teams: Every owner and decider is a named person.
- Distinctive: line 81
Decided vs. discussed: Only decided processes go in the main sections.
- Distinctive: line 82
Plain words: Write it so someone outside the team could follow it.
- Distinctive: line 89
When another skill learns something durable mid-task — a new tool, a changed owner, a new meeting — suggest adding it here rather than …
- Distinctive: line 93
Every skill in this library reads this file first.
≈ “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
Product ops context
Every product ops skill needs the same background: what the product is, which teams exist, who makes which calls, which meetings happen when, where docs and tickets live, and what each metric means. This skill writes that down once, in one file, so no other skill has to ask again.
The file lives at .agents/product-ops-context.md. If you find it at .claude/product-ops-context.md instead, use it and offer to move it.
Step 1: Check what exists
If the file exists: read it, give a three-line summary of what's in it, show the version and the last two changelog entries, and ask which sections to update. Only gather what's needed for those sections.
If it doesn't exist, offer two ways to start:
- Draft from what's here (faster): read whatever the person has shared or what's in the project — team pages, onboarding docs, a roadmap export, meeting notes, a tool list — and draft every section. Then ask what's wrong and what's missing.
- Build it together: walk through the sections one at a time, a few questions each.
Step 2: Fill each section
Use only what the person or their documents say. Anything not given stays as "Not recorded." A context file with gaps is useful; a context file with guesses breaks every skill that trusts it.
# Product ops context
**Version:** 1.0 · **Last updated:** [date] · **Owner:** [person who keeps this current]
## Product
- What it is, in one sentence a new hire would understand:
- Who buys it, and who uses it day to day:
- Products, plans, or modules (names as customers see them):
- Stage and size: [e.g. Series B, 40 people, 2 product teams]
## Teams and decisions
| Team | Lead | What they own |
|---|---|---|
- Who decides: scope · launch dates · pricing · roadmap priority · deprecations
- Who must be told before customers hear about a change:
## Operating rhythm
| Meeting | When | Purpose | Output | Owner |
|---|---|---|---|---|
- Planning cycle: [quarterly / six-week / other], next one:
- Release cadence: [continuous / weekly / monthly drop]
## Where things live
| What | Tool | Link or location | Owner |
|---|---|---|---|
Cover: roadmap, tickets, customer feedback, support tickets, docs/wiki, dashboards, decision log, release notes.
## Metrics
| Metric | Definition | Source | Owner |
|---|---|---|---|
Link to the full metric definitions doc if one exists.
## Launches
- Launch tiers and what each requires:
- Who signs off go / no-go:
- Where customers hear about changes: [release notes, email, in-app, CSM]
## Customers
- Segments the team uses:
- Where customer input comes from: [calls, tickets, CAB, surveys, sales]
## Words we use
Team-specific terms and what they mean, so outputs match how the team talks.
## Open questions
Things the team hasn't settled that skills should flag, not guess.
## Changelog
- [date] v1.0 — Created. [what it was drafted from]Step 3: Rules for the file
- People, not teams. Every owner and decider is a named person. "Engineering" is not an owner.
- Decided vs. discussed. Only decided processes go in the main sections. Anything still being debated goes under Open questions.
- Plain words. Write it so someone outside the team could follow it.
- One page if possible. Link to longer docs instead of copying them in.
Step 4: Save and version
Save to .agents/product-ops-context.md (create the .agents/ folder if needed). On every real change, bump the version (1.0 → 1.1 for edits, 2.0 for a reorg or new team structure) and add a dated changelog line saying what changed and why.
When another skill learns something durable mid-task — a new tool, a changed owner, a new meeting — suggest adding it here rather than letting it get lost in that one output.
Related skills
Every skill in this library reads this file first. The ones that lean on it most:
- ritual-calendar — uses the Operating rhythm section, and can fill it in
- raci-builder — uses Teams and decisions, and can fill it in
- product-metrics-definitions — writes the full definitions the Metrics section links to
- tool-stack-audit — checks and fills Where things live
- new-pm-onboarding-pack — turns this file into a day-one pack for a new hire
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.

