Type registry, schemas, and content guidance for development artifacts — projects, epics, stories, tasks, specs, ADRs, spikes, work-items, workstreams, milestones. Load when authoring a new artifact, validating one, or resolving the type system. For simple reads (get/list/find), read the artifact file directly without loading this skill.
68
85%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Passed
No findings from the security scan
Entry point for working with development artifacts. Load this skill when authoring a new artifact or resolving the type system. For simple reads, work directly with the artifact file.
| Type | Reference | Canonical path | When |
|---|---|---|---|
| project | project.md | docs/development/projects/<slug>.md | Bounded deliverable; coordination hub |
| epic | epic.md | docs/development/epics/<slug>.md | Themed group of stories |
| story | story.md | docs/development/stories/<slug>.md | User-frame increment with testable ACs |
| task | task.md | docs/development/tasks/<slug>.md | Engineering-frame technical change |
| work-item | work-item.md | docs/development/work-items/<slug>.md | Standalone bug, chore, or enhancement |
| spike | spike.md | docs/development/spikes/<slug>.md | Time-boxed investigation |
| spec | spec.md | docs/development/specs/<slug>.md | Technical specification |
| adr | adr.md | docs/development/adrs/adr-NNN-<slug>.md | Architecture decision record (sequential numbering, project-wide) |
| workstream | workstream.md | docs/development/workstreams/<slug>.md | Parallel delivery track within a project |
| milestone | milestone.md | docs/development/milestones/<slug>.md | Sequenced project checkpoint |
Slugs are kebab-case derived from the artifact name. ADRs use sequential numbering across the entire project — check existing ADRs (and unmerged branches) to find the next integer.
The paths above are canonical. Do not write to per-project subdirectories, adjacent docs trees, or any other location. The flat-by-type layout is what makes typed-link traversal and ADR numbering work.
If a caller — user, agent, or another skill — specifies a non-conforming path, surface the conflict before writing. Silent compliance with a wrong path breaks tools that walk the work graph. Users and orchestrating agents routinely guess paths wrong; the schema is the source of truth.
632c389
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.