0xWheatyz/handler
1
0
Fork 0
mirror of https://github.com/0xWheatyz/handler.git synced 2026-08-30 03:31:36 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add install-from-prompt to the Skills tab

Browse Source 
Skill marketplaces (SkillsMP and friends) publish an install prompt meant to
be pasted into an interactive claude, which fetches the skill's files and
places them under a skills directory. Handler has no interactive claude and
its skills are DB rows, so the Skills tab gains an "Install from a marketplace
prompt" card wired to a new skill_install command: the worker runs the pasted
prompt through a one-off headless claude in a throwaway staging directory
(sandboxed by a generated settings.json allowing fetch/clone tooling with
acceptEdits), then imports whatever <skill>/SKILL.md landed as managed rows —
reinstalling a skill updates it in place.

Headless means nobody can answer questions mid-install, so the wrapper prompt
front-loads the answers a human would give: install into the staging dir,
always user scope (Handler distributes skills to workers itself), pick the
instructions' defaults, never stop to ask, and end with a report of the
choices made — surfaced in the command result for after-the-fact review, with
the imported skill editable/disableable in the UI.

Multi-file skills survive the import: a new claude_skill_files table
(migration 0011, alongside the command-type constraint change) captures
auxiliary files (references/, scripts/, ...), the launch-time sync rebuilds
each managed skill dir from them, and skill cards list what a skill ships
with. The one-off run's timeout defaults under worker_stale_after so a slow
install can't get the worker's live runs falsely reaped.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_019f42XmjtVsc3zQ9Dhn6DqZ
This commit is contained in:
Claude
2026-07-23 15:06:22 +00:00
parent 07d8c3aa19
commit 6a14823c26
41 changed files with 731 additions and 55 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+7 -1
View File
@@ -259,7 +259,13 @@ What the dashboard can now do (all state-changing actions require `ADMIN_TOKEN`)
(marker-file managed, so hand-installed skills survive), enabled connectors become the
run's `--mcp-config` file (nothing lands in the repo tree), and plugins/permissions fold
into the generated per-agent `settings.json` — so a change in the UI reaches the next
launch of every agent, no redeploy.
launch of every agent, no redeploy. Skills can also be **installed from a marketplace
prompt** (SkillsMP and friends): paste the page's install prompt and a `skill_install`
command runs it through a one-off headless claude in a staging dir on the worker, then
imports whatever `<skill>/SKILL.md` (+ auxiliary files) landed as managed rows.
Headless means nobody can answer questions mid-install, so the wrapped prompt makes the
choices a human would be asked — always user scope, the instructions' defaults — and
reports them in the command result for after-the-fact review.
The command queue is exposed over HTTP as `POST …/agents/spawn`, `POST …/agents/{n}/kill`,
`POST …/approvals`, `POST …/forge-init`, `POST …/poll-ci`, `POST …/sync`,