mirror of
https://github.com/mattpocock/skills.git
synced 2026-07-29 02:52:42 +07:00
697d4ce974
Adds an `agents/openai.yaml` beside each `SKILL.md` so the skills work in Codex as well as Claude Code, without generated copies: - `interface.display_name` + `interface.short_description` for the Codex skill picker, hand-written for all 39 skills. - `policy.allow_implicit_invocation: false` on the 22 user-invoked skills — the Codex analog of `disable-model-invocation: true`, so Codex excludes them from implicit invocation while explicit `$skill` still works. - Document the dual-harness invocation model in `.agents/invocation.md`, `CLAUDE.md`, and the promoted-bucket READMEs. - Add `AGENTS.md` as a symlink to `CLAUDE.md` so Codex reads the same instructions; note Codex as a `link-skills.sh` install target. Slimmed-down rework of the approach prototyped in #522: keeps the essential cross-harness metadata, drops the Ruby validator, the runtime-detector test, per-skill `default_prompt`s, and the unrelated promotion changes. Co-authored-by: gabimoncha <gabimoncha@users.noreply.github.com> Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
21 lines
2.3 KiB
Markdown
21 lines
2.3 KiB
Markdown
# Model-invoked vs user-invoked
|
|
|
|
Every `SKILL.md` in this repo is a skill. The one axis that splits them is **invocation** — who can reach it:
|
|
|
|
- **User-invoked** — reachable **only by the human typing its name**. Set `disable-model-invocation: true` in the frontmatter (Claude Code) and `policy.allow_implicit_invocation: false` in `agents/openai.yaml` (Codex). The `description` is **human-facing**: a one-line summary read by a person browsing slash-commands. Strip trigger lists ("Use when the user says…").
|
|
- **Model-invoked** — reachable by **model or user**. The default: omit `disable-model-invocation` and the `policy` block from `agents/openai.yaml`. The `description` is **model-facing** and keeps rich trigger phrasing ("Use when the user wants…, mentions…, asks for…") so auto-invocation fires. The test for whether a skill should stay model-invoked: _could the model usefully reach for this autonomously?_ (Reuse is the reason to extract a skill, not the test.)
|
|
|
|
Each harness excludes a user-invoked skill from the model's reach in its own way, so nothing but the human can fire it — no other skill can. A user-invoked skill may invoke model-invoked skills, but it can never reach another user-invoked skill.
|
|
|
|
Every skill also carries an `agents/openai.yaml` beside its `SKILL.md`. It holds Codex UI metadata — `interface.display_name` and `interface.short_description` for the skill picker — and, for user-invoked skills, the `policy.allow_implicit_invocation: false` that pairs with `disable-model-invocation`. Keep the two in sync: a skill is user-invoked in both harnesses or neither.
|
|
|
|
Bucket `README.md`s and the top-level `README.md` group entries into **User-invoked** and **Model-invoked**.
|
|
|
|
## Dependencies between them
|
|
|
|
Dependencies are expressed as **`/skill`-style prose invocation** ("Run the `/grilling` skill"), not deep `../other-skill/FILE.md` cross-references. Shared reference docs live inside the skill that owns them; other skills reach that material by invoking the skill, not by linking across folders.
|
|
|
|
## Passive vs active domain work
|
|
|
|
Merely _reading_ `CONTEXT.md` for vocabulary is a one-line prose pointer, not the `domain-modeling` skill. Only the active build/sharpen discipline (challenge terms, edge-case scenarios, write ADRs, update `CONTEXT.md` inline) is `domain-modeling`.
|