pm-agentic-cookbook
llms.txt2 starsChanged 32 days agoApache-2.0View on GitHub
A workflow and skill collection for turning confirmed business sources into models, requirements, prototypes and verifiable delivery.
In this repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- acceptance-criteriaSkill
- check-prdSkill
- consistency-auditSkill
- create-prdSkill
- domain-modelingSkill
- journey-auditSkill
- source-intakeSkill
- spec-captureSkill
- table-template-designerSkill
- test-authoringSkill
- ui-generatorSkill
The file
Files
# PM Agentic Cookbook > A workflow and skill collection for turning confirmed business sources into models, requirements, prototypes and verifiable delivery. ## Agent usage - [Agent Guide](AGENT_GUIDE.md): Choose available skills, confirm domains and configuration, and respect phase decisions. ## Process - [Workflow](process/overview.md): Read the phase order and evidence boundaries. - [Executor protocol](process/agent-execution-protocol.md): Separate authors, auditors and walkthrough executors. ## Skills - [source-intake](skills/source-intake/SKILL.md): Assess and index the source material for a project. - [domain-modeling](skills/domain-modeling/SKILL.md): Define entities, relationships and domain rules. - [acceptance-criteria](skills/acceptance-criteria/SKILL.md): Create criteria and reconcile delivery evidence. - [create-prd](skills/create-prd/SKILL.md): Draft requirements from confirmed inputs. - [check-prd](skills/check-prd/SKILL.md): Review a requirements document and explicit domain supplements. - [ui-generator](skills/ui-generator/SKILL.md): Generate an interactive business prototype. - [table-template-designer](skills/table-template-designer/SKILL.md): Design complex business tables. - [test-authoring](skills/test-authoring/SKILL.md): Write executable tests from requirements. - [journey-audit](skills/journey-audit/SKILL.md): Plan and audit runtime journeys. - [consistency-audit](skills/consistency-audit/SKILL.md): Compare specifications, models and implementation paths. - [spec-capture](skills/spec-capture/SKILL.md): Capture confirmed reusable rules. ## Specs - [Reference rule library](specs/README.md): Start with the supplied UI/UX, integration, engineering, security and testing rules, then adapt them to the host. - [Host spec map](AGENT_GUIDE.md#host-configuration): Locate the rules declared by the host instead of guessing paths. - [Kit architecture](process/kit-architecture.md): Read the Definition, Provider, configuration and gate contracts. ## Examples - [Examples](examples/): Read the example documents available in this checkout.
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.