edkuksa/skills
1
0
Fork 0
mirror of https://github.com/mattpocock/skills.git synced 2026-09-12 10:28:06 +07:00
Code Issues Packages Projects Releases Wiki Activity

skill: make wizard model-invoked

Browse Source 
The agent can now reach for wizard the moment it hits a step only a
human can perform, instead of writing numbered instructions into the
chat. Typing /wizard is unaffected — model-invocation only adds the
agent's reach.

The description is rewritten as the pointer that decides when it fires:
a short statement of the artifact, four trigger branches, and an
explicit non-trigger for steps the agent can perform itself.

Behaviour is unchanged — same name, same template.sh, same four process
steps, same stage-list confirmation, which now doubles as the proposal
when the agent fires it mid-build.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Matt Pocock
2026-08-05 13:02:28 +01:00
co-authored by Claude Opus 5
parent 44d845d6c9
commit 61accb0e66
8 changed files with 22 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/engineering/wizard.md
+8 -2
View File
@@ -6,7 +6,7 @@ You reach for it only where a human is genuinely in the loop. If the agent could
## When to reach for it
You invoke this by typing `/wizard` — the agent won't reach for it on its own.
You can type `/wizard`, and the agent can also reach for it on its own. When it hits a step only you can perform — a key it can't mint, a dashboard it can't click — it builds you a wizard instead of writing the instructions into the chat, where they scroll away.
Reach for it when the next thing blocking you is a human clicking through a dashboard:
@@ -78,7 +78,13 @@ Nowhere in particular. It's a standalone, not a chain step. The common guess is
**Does it work outside Claude Code?**
The artifact does, unconditionally: it's a plain bash script and it doesn't care what harness generated it. The skill itself is user-invoked, so you type `/wizard` in Claude Code or `$wizard` in Codex. One known gap — on Claude's desktop and web surfaces, which run in coordinator mode, every user-invoked skill is dropped from the model's listing entirely, so the assistant tells you `/wizard` isn't installed when it is. The plain `claude` CLI is unaffected. The tracking issue is [#693](https://github.com/mattpocock/skills/issues/693); the fix belongs in the harness.
The artifact does, unconditionally: it's a plain bash script and it doesn't care what harness generated it. The skill itself is model-invoked, so it's listed everywhere — type `/wizard` in Claude Code or `$wizard` in Codex, or just describe the setup you're stuck on. Being model-invoked also keeps it clear of [#693](https://github.com/mattpocock/skills/issues/693), where Claude's desktop and web surfaces drop *user-invoked* skills from the model's listing and report them as not installed.
**Didn't this used to be user-invoked?**
It did. It's now model-invoked, so the agent reaches for it unprompted when it hits a step only you can take. Nothing you could do before stopped working — model-invocation *adds* the agent's reach, it never removes yours, so `/wizard` behaves exactly as it did. What changed is the failure mode it retires: the agent hitting a credentials wall mid-build and dumping six numbered steps into the chat for you to follow by hand.
The guard against the opposite failure is in the description itself — don't invoke it for steps the agent can perform itself. Work an agent can do, an agent should do.
**It used to be in `in-progress/` — where is it now?**