add-epic
Skill0 starsChanged 2 months agoMITView on GitHub
This skill should be used when the user asks to "add an epic", "create an epic", "start a new epic", "make an epic", "open an epic", "file an issue epic", "set up an epic", or references EPICS_ROOT/. Creates a new epic - a GitHub-style container for organising related queries and work - under EPICS_ROOT/<epic>, with an EPIC.md template and an issues/<issue> directory to hold the issue work scoped to that epic.
In this repository6 other files it gives its agents.
- skills/AGENTS.mdAGENTS.md
- add-commentSkill
- add-issueSkill
- issue-managerSkill
- issue-subagent-orchestrationSkill
- research-project-epic-managerSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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
- Very specific: line 21
Create a new epic under EPICS_ROOT/.
- Distinctive: line 37
Use when the user wants to start tracking a discrete body of related work - for example "add a new feature", "build a dashboard", "fix the …
- Very specific: line 49
Run the creation script (it lives in this skill's scripts/ directory - the skill loader provides the skill's base path when the skill is …
≈ “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
Add Epic
Create a new epic under EPICS_ROOT/. An epic is a directory that
groups a body of related work (issues, PRs, decisions) around a shared goal,
mirroring how a GitHub project/repo organises user queries.
Layout
Each epic lives at EPICS_ROOT/<epic> and contains:
<epic>/
|-- EPIC.md # describes the epic (from template)
`-- issues/ # container for issue dirs scoped to this epicWhen to use this skill
Use when the user wants to start tracking a discrete body of related work -
for example "add a new feature", "build a dashboard", "fix the auth flow",
"set up an epic for the reports work". Use the add-issue skill when the
user then wants to plan individual pieces of work inside the epic.
Procedure
- Slugify the epic name:
epic=$(echo "<epic name>" | tr '[:upper:]' '[:lower:]' | tr -cs 'a-z0-9' '-') - Run the creation script (it lives in this skill's
scripts/directory - the skill loader provides the skill's base path when the skill is loaded):
The script createspython3 <skill-dir>/scripts/add-epic.py "<epic name>"EPICS_ROOT/<epic>/EPIC.mdfrom theassets/EPIC.template.mdtemplate and an emptyissues/directory. - Verify:
ls EPICS_ROOT/<epic>/{EPIC.md,issues/} cat EPICS_ROOT/<epic>/EPIC.md
The EPIC.md starts as a well-organised template with Status, Goals,
Non-Goals, Scope, Auto Issue Generation, Issues, Milestones, Decisions, Risks,
and cross-links - fill in each section as the epic evolves.
Additional Resources
assets/ISSUE.template.md- the issue template used by theadd-issueskill (kept here for reference/linking).
Reference Files
assets/EPIC.template.md- the EPIC.md skeleton filled in by the script.
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.

