diff options
| author | Jesse Vincent <jesse@fsck.com> | 2026-10-22 21:04:25 +0000 |
|---|---|---|
| committer | Jesse Vincent <jesse@fsck.com> | 2026-10-22 21:04:25 +0000 |
| commit | 8f4b3dbd2f5ef8163e4daed5ca43a4cf08eb5d8c (patch) | |
| tree | 0f65e906e767b7b26f110b0630415f6c3e409f43 /docs/README.opencode.md | |
| parent | 0f9581f6c1525b51dc1600b14d24f3db1f601446 (diff) | |
fix(opencode): tell the model skill ids are bare names (#2583)fix/2583-opencode-skill-names
Skills name each other with the Claude Code plugin namespace
(`superpowers:brainstorming`), and the using-superpowers bootstrap that
the OpenCode plugin injects says "Let's build X -> superpowers:brainstorming
first". OpenCode registers superpowers skills under bare ids
(`brainstorming`) on both flavors and its `skill` tool does an exact
lookup, so a model that copies the namespaced form gets
"Unable to load skill superpowers:brainstorming" (V2) or
`Skill "superpowers:brainstorming" not found` (V1) and carries on
without the skill. The OpenCode tool mapping said only "Invoke a skill
-> OpenCode's native skill tool" and never stated the id convention.
Reproduced on real hosts (OpenCode 2.1.2 and opencode-ai 1.19.4) with a
scripted stub provider: the namespaced call fails, the bare id loads.
Add the convention to the "Invoke a skill" line of both mappings, with
each flavor's real skill parameter (V1 `name`, V2 `id`), and mirror it
in docs/README.opencode.md. Skill prose keeps the prefix, which is
correct on Claude Code; the translation belongs in the harness mapping,
the same way the Hermes reference shows bare `skill_view("brainstorming")`.
Claude-Session: https://claude.ai/code/session_01SHANcr4A71nzuU9et4Fnba
Diffstat (limited to 'docs/README.opencode.md')
| -rw-r--r-- | docs/README.opencode.md | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/docs/README.opencode.md b/docs/README.opencode.md index 3ffdd81..f907374 100644 --- a/docs/README.opencode.md +++ b/docs/README.opencode.md @@ -148,7 +148,7 @@ Skills speak in actions rather than naming any one runtime's tools. The bootstra - "Create a todo" / "mark complete in todo list" → `todowrite` - `Subagent (general-purpose):` template → OpenCode's `task` tool with `subagent_type: "general"` (or `"explore"` for codebase exploration) -- "Invoke a skill" → OpenCode's native `skill` tool +- "Invoke a skill" → OpenCode's native `skill` tool with the bare skill name (`superpowers:brainstorming` → `name: "brainstorming"`) - "Read a file" → `read` - "Create a file" / "edit a file" / "delete a file" → `apply_patch` - "Run a shell command" → `bash` @@ -159,7 +159,7 @@ Skills speak in actions rather than naming any one runtime's tools. The bootstra - "Create a todo" → V2 has no todo tool of any kind; the mapping tells the model to track the plan in a markdown file (or the harness's plan facility) instead - `Subagent (general-purpose):` template → OpenCode's `subagent` tool with `agent: "general"` (or `"explore"`); pass `sessionID` to continue a previous subagent -- "Invoke a skill" → OpenCode's native `skill` tool +- "Invoke a skill" → OpenCode's native `skill` tool with the bare skill id (`superpowers:brainstorming` → `id: "brainstorming"`) - "Read a file" → `read` - "Create, edit, or delete files" → use `patch` with `patchText` when available; otherwise use `write` to create or overwrite files, `edit` for targeted changes, and `shell` for deletion - "Run a shell command" → `shell` (`command`, `workdir`, `timeout`, `background`) |
