pm-transversal-docs
Skill1 starsChanged 42 days agoMITView on GitHub
Cross-phase skill for **PM documentation in Confluence and Jira** — structure, templates, voice, linking, and hygiene. Invoke whenever the user is creating or improving Confluence pages (PRDs, strategy memos, DACI, launch plans, retros, FAQs) or Jira tickets/epics (ticket hygiene, linking, parent/child, labels, components, automations). Trigger on "Confluence", "Jira", "cria a página", "estruture o PRD na Confluence", "abre os tickets", "epic structure", "ticket hygiene", "linking", "release page", "documentation", "wiki", "wiki template". Produces doc structures that colleagues actually read and tickets that survive backlog refinement without rework. Complements the MCP Atlassian/Rovo integration when available — this skill is instructional (how to write), not automated execution.
In this repository65 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- anti-slopSkill
- data-science-analystSkill
- humanize-deliverablesSkill
- humanizerSkill
- inference-disciplineSkill
- pm-archetype-aiSkill
- pm-archetype-enterpriseSkill
- pm-archetype-growthSkill
- pm-archetype-platformSkill
- pm-phase-defineSkill
- pm-phase-deliverSkill
- pm-phase-developSkill
- pm-phase-discoverSkill
- pm-prioritization-regua-comumSkill
- pm-product-senseSkill
- pm-storytellingSkill
- pm-transversal-analysisSkill
- pm-transversal-commsSkill
- pm-transversal-docsSkill
- pm-transversal-stakeholderSkill
- repo-doctorSkill
- anti-slopSkill
- data-science-analystSkill
- humanize-deliverablesSkill
- humanizerSkill
- inference-disciplineSkill
- pm-archetype-aiSkill
- pm-archetype-enterpriseSkill
- pm-archetype-growthSkill
- pm-archetype-platformSkill
- pm-phase-defineSkill
- pm-phase-deliverSkill
- pm-phase-developSkill
- pm-phase-discoverSkill
- pm-prioritization-regua-comumSkill
- pm-product-senseSkill
- pm-storytellingSkill
- pm-transversal-analysisSkill
- pm-transversal-commsSkill
- pm-transversal-stakeholderSkill
- repo-doctorSkill
- umbertoSkill
- anti-slopSkill
- data-science-analystSkill
- humanize-deliverablesSkill
- humanizerSkill
- inference-disciplineSkill
- pm-archetype-aiSkill
- pm-archetype-enterpriseSkill
- pm-archetype-growthSkill
- pm-archetype-platformSkill
- pm-phase-defineSkill
- pm-phase-deliverSkill
- pm-phase-developSkill
- pm-phase-discoverSkill
- pm-prioritization-regua-comumSkill
- pm-product-senseSkill
- pm-storytellingSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 122
Every phase: pm-phase-define publishes strategy/DACI in Confluence.
≈ “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
PM Transversal — Confluence & Jira documentation
Transversal skill. Applies to every Double Diamond phase. The question is never "do we need docs?" — it's "where does this live, what template, and how does it stay alive?"
Progressive loading
Load this SKILL.md first. For large or specialized tasks, use references/progressive-loading.md to choose the narrowest supporting reference before reading more.
When to use this skill
Invoke when:
- a Confluence page is being created for a PRD, strategy, DACI, launch plan, release notes, FAQ, or retro
- a Jira epic/story/task is being structured or restructured
- documentation is drifting from reality and needs a hygiene pass
- PM → Eng handoff artefacts need consistent structure across tickets
- linking (PRD ↔ epic ↔ design ↔ tracking plan ↔ release notes) needs to be designed
This skill is about how to write and structure — not about executing API calls. If MCP Atlassian/Rovo integration is available, the skill can be paired with those tools to actually create/update pages and tickets; otherwise the output is content ready to paste.
Prime directive
Docs that teammates read > docs that are thorough but ignored. Structure, voice, and linking are hard skills. Dumping a slack log into a Confluence page is not documentation; it's a graveyard.
Core sub-skills
1. Confluence structure
The anatomy of a PM Confluence page: title convention, metadata block, TL;DR, context, decision/recommendation, appendices. Scan-friendly before it is deep.
Outputs: page template, information architecture for a product space, cross-page linking convention.
Anti-patterns: walls of text, no TL;DR, decision buried at the bottom, no "last updated" signal, no links to related pages.
→ Deep-dive: references/confluence-structure.md
2. Confluence templates
Concrete templates for the artefacts PMs produce most: PRD, strategy memo, DACI, launch plan, release notes, retrospective, FAQ. Each template is scan-friendly and consistent with the phase skills.
Outputs: ready-to-paste Confluence markdown/wiki markup for each artefact, with placeholders.
→ Deep-dive: references/confluence-templates.md
3. Jira ticket hygiene
Ticket structure that survives refinement: title, problem, acceptance criteria, scope, links, labels, components, estimate, definition-of-done. Epic/story/task hierarchy matching the backlog grain.
Outputs: ticket template by type, epic structure, labelling convention, "definition of ready" checklist.
Anti-patterns: tickets without acceptance criteria, giant stories disguised as tasks, no links to PRD, inconsistent labels, estimates pulled from thin air.
→ Deep-dive: references/jira-ticket-hygiene.md
4. Jira linking and automation hints
Cross-ticket linking (blocks/is blocked by, relates to, duplicates), parent/child relationships, automations worth having (transition on label, notify on stall, auto-close stale bugs), and how to keep Confluence-Jira bidirectional links alive.
Outputs: linking map, automation recipe list, Confluence ↔ Jira integration hints.
→ Deep-dive: references/jira-linking-automation.md
Workflow
- Classify the artefact — which Confluence page or Jira ticket type? Pull the matching template.
- Anchor on the source of truth — a PRD page is the source of truth for scope; Jira is the source of truth for status. Don't duplicate what lives elsewhere.
- Write TL;DR first — the first paragraph should let a busy colleague decide whether to read more.
- Link explicitly — every PRD has epic links; every epic has PRD link; every release note has launch-plan link. Orphan docs rot.
- Keep "last updated" honest — add a status block (draft / in review / decided / implemented / archived).
- When MCP Atlassian is available — use
createConfluencePage/createJiraIssue/editJiraIssue(tool names are themcp__<server>__<tool>suffix; the server prefix varies by environment) to persist; otherwise output content for paste.
Output contract (Confluence page)
# [Page title — convention: {Space-code} / {Type} / {Topic}]
**Status:** Draft | In review | Decided | Implemented | Archived
**Owner:** @name
**Last updated:** YYYY-MM-DD
**Related:** links to Jira epic, design, tracking plan, previous page
## TL;DR
One paragraph. Recommendation + why.
## Context
What prompted this. 3–5 sentences.
## [Body — matches the phase skill artefact contract]
## Open questions
## Appendix / sourcesOutput contract (Jira ticket)
[Type] [Short title — imperative + user value, e.g. "Allow users to export CSV from dashboard"]
**Problem / user value:**
**Acceptance criteria:**
- [ ] ...
- [ ] ...
**Scope IN:**
**Scope OUT:**
**Links:** PRD, design, tracking-plan event, parent epic
**Labels:** area/X, priority/Y, discovery-phase/Z
**Components:** ...
**Estimate:** ...
**Definition of Done:**
- [ ] instrumentation live
- [ ] docs updated
- [ ] release notes drafted (if user-facing)Integration
- Every phase:
pm-phase-definepublishes strategy/DACI in Confluence;pm-phase-developpublishes PRDs and opens Jira epics;pm-phase-deliverpublishes release notes and monitoring dashboards with Confluence context. - Transversais:
pm-transversal-stakeholderpublishes DACI via this skill's Confluence template;pm-transversal-analysispublishes interview synthesis in Confluence insight repo. - MCP tools: when an Atlassian MCP server is available (the
mcp__<server>__prefix varies by environment), this skill's templates can be pushed directly. - Agents:
@pm-orchestratoruses this skill on every PRD + ticket creation;@pm-kickofffor discovery-page publication; archetype agents for area-specific templates.
Communication modes follow ../../docs/patterns/COMMUNICATION_MODES.md. Per-skill: Lean (default) is a compact template with TL;DR + body + open questions; Standard is a full Confluence page with appendices; Caveman is the ticket-sized minimum viable write-up.
Success criteria
- teammates find the right doc in < 30 seconds
- tickets arrive at sprint planning already refined
- PRD ↔ epic ↔ design ↔ release-notes links are bidirectional and alive
- archived pages are archived (not rotting as "most recent")
- onboarding new team members becomes markedly easier
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.

