skill folder
# minimal
skills/sus-spec/
SKILL.md
# with one reference
skills/sus-spec/
SKILL.md
references/
task-template.mdDefine the load boundary and operating rules. Keep repo policy in the repo.
Keep the entry point in SKILL.md. Move support material to references only when it would bury the load rule.
skill folder
# minimal
skills/sus-spec/
SKILL.md
# with one reference
skills/sus-spec/
SKILL.md
references/
task-template.mdTreat the description as the load contract. Name the work it should match and the work it should skip.
SKILL.md
--- name: sus-spec description: Write, revise, or structurally check a verifiable Suspec spec. Use when intent must become requirements or acceptance criteria, or unresolved behavior blocks implementation. Do not use for direct implementation, small clear work, factual verification, or implementation design. ---
Hard imperatives only. Add a section when it changes behavior, not because the template had one.
Put executable behavior under Method. Add other sections only when they carry behavior.
Skills install individually. Never name, require, invoke, or assume a sibling.
A useful next job may match another skill's trigger, but must still work when that skill is absent.
Put long templates or examples in references/. Keep them one hop away from SKILL.md.
Use a template for long work that needs state: plans, evidence, attempts, decisions, and follow-up.
A Suspec skill must work in any repo. Put local commands and product knowledge in that repo's AGENTS.md. Do not smuggle a project into a global skill.
engineering-domain knowledge (auth patterns, caching, runbooks)
stack- or vendor-specific skills
internal product docs
automation, scripts, or CI in the catalog
core or loader skills that other skills depend on
skills designed to always load
The catalog has universal methods and canonical artifact authors. Read the source; it is shorter than guessing.