epic-overview
Skill1 starsChanged 6 months agoMITView on GitHub
Generate a grouped overview of all active epics and initiatives your team owns, organized by strategic objective or project area. Shows what each initiative is, which epics roll up to it, who owns them, progress, and flags unassigned or stale work. Default output is conversational; optionally save to vault or file.
In this repository30 other files it gives its agents.
- setupSkill
- enrich-prsSkill
- epic-cleanupSkill
- oncall-reviewSkill
- sprint-managementSkill
- sprint-statusSkill
- team-activitySkill
- team-data-syncSkill
- direct-report-prepSkill
- interview-analysisSkill
- interview-prepSkill
- peer-prepSkill
- project-statusSkill
- team-analysisSkill
- today-prioritiesSkill
- weekly-snippetSkill
- bus-factorSkill
- contribution-velocitySkill
- nine-boxSkill
- project-people-mapSkill
- review-cardsSkill
- review-cyclesSkill
- review-networkSkill
- team-health-reportSkill
- task-rolloverSkill
- context-checkSkill
- prep-my-daySkill
- initiative-breakdownSkill
- product-briefSkill
- technical-deep-diveSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
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 29
Default: conversational (printed to screen).
- Distinctive: line 55
Create logical groupings that represent strategic objectives or project areas.
- Distinctive: line 91
If user asks to save: Write to specified location (e.g., vault note, project file).
- Distinctive: line 98
Flag unassigned work: Every epic should have a DRI.
- Distinctive: line 99
Include everything open: Don't filter by "active" here.
- Distinctive: line 100
Dead epics go at the bottom: Don't bury them in their group where they clutter the active work view.
≈ “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
Epic Overview
Produce a structured view of all active epics and initiatives, grouped by their parent objective or project area. Each group gets a short description of what it is, then lists every epic under it with owner, progress, and a one-liner explanation.
When to use
- "Epic overview", "show me all our epics", "what initiatives are we running"
- "Map our work", "project portfolio", "what does the team own"
- Onboarding context: "give someone a picture of everything we're working on"
Prerequisites
- GitHub CLI (
gh) authenticated with org access - Team repo with issues labeled
epic,initiative, orbatch - Team roster (
team.json) for DRI identification
Output
Default: conversational (printed to screen). User can ask to save it to a vault note, markdown file, or paste destination.
Process
Step 1: Gather all open epics and parent issues
Query the team repo for:
- All open issues with label: epic, initiative, or batch
- All open issues with sub_issues_summary.total > 0 (acting as parent issues)For each, capture: number, title, assignees, labels, updated_at, sub_issues progress.
Step 2: Identify DRI
DRI = first assignee on the issue. If no assignee, mark as "unassigned."
Step 3: Group by initiative/objective
Analyze the epics by:
- Labels (e.g.,
virtual-registry,authentic-contributions,Releases) - Title patterns and naming conventions
- Parent-child relationships (sub-issues of larger epics)
- Shared assignees and project area context
Create logical groupings that represent strategic objectives or project areas. Each group should have:
- A meaningful name (not just a label echo)
- A 1-2 sentence description of what the objective is
Common grouping patterns:
- Product feature area (e.g., "Releases & Immutability")
- Customer integration (e.g., "Partner Integration / Virtual Registry")
- Infrastructure domain (e.g., "Signing Infrastructure")
- Operational category (e.g., "Maintenance & Reliability")
Step 4: Write the overview
For each group:
## [Initiative Name]
[1-2 sentence description of what this initiative is and why it matters.]
- [#N Title](url) — @dri
[One sentence: what this epic actually does.] Progress: X/Y (Z%).
- [#N Title](url) — unassigned
[Description.] Progress: X/Y (Z%).Step 5: Surface unknowns
At the end, include a section for:
- Epics that don't clearly fit any group
- Stale epics (no activity 60+ days) that may be dead
- Completed epics (100% or all sub-issues closed) that should be closed
Step 6: Output
Default: Print to screen as markdown.
If user asks to save: Write to specified location (e.g., vault note, project file). Include a date header so it's clear when the overview was generated.
Content guidelines
- One sentence per epic. The overview is for scanning, not deep reading. Just say what it does.
- Group by what makes sense, not by label. Sometimes one label covers multiple objectives; sometimes multiple labels are really one thing.
- Show progress honestly. X/Y sub-issues with percentage. If 0/0, say "no sub-issues tracked."
- Flag unassigned work. Every epic should have a DRI. Unassigned = a decision to make.
- Include everything open. Don't filter by "active" here. The point is the complete picture, including work that's stalled or forgotten.
- Dead epics go at the bottom. Don't bury them in their group where they clutter the active work view.
Relationship to other skills
- epic-cleanup: Cleanup is the actionable version (tasks to assign, close, decide). Overview is the reference map.
- project-status: Status covers the last 7 days of movement. Overview is the static "what exists" view regardless of recent activity.
- sprint-status: Sprint is scoped to the current iteration. Overview is all open work.
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.

