Sync clarion-setup: single-prompt install flow#88
Merged
jingerzz merged 1 commit intoMay 19, 2026
Merged
Conversation
Upstream PR jingerzz/clarion-intelligence-system#21: restructures the Clarion install UX so a new user types one chat prompt ("set up Clarion") and is asked for input exactly once, near the end, batched: SEC EDGAR name+email AND the ZO_API_KEY secret confirmation. Everything else — repo clone, library install, data tree, sibling skill auto-install, service registration, persona install, rule install, config.json update, service restart, verification — happens autonomously in a continuous flow. Enabled by Zo's agent tools (create_persona, list_personas, delete_persona, create_rule, list_rules, delete_rule, service_doctor) — previously the persona/rule install was a separate manual paste into Zo Settings, now it's autonomous. Step 6 pre-check makes clean re-runs fully autonomous: if config.json has a real sec_user_agent AND service_doctor shows RUNNING, the human checkpoint is skipped entirely. Also bundles the SEC user-agent silent-placeholder fix — every Clarion install was previously hitting SEC EDGAR with clarion@example.com; now the setup prompts for the user's real identification. Also folds in the service_doctor correction from PR zocomputer#87/upstream zocomputer#20: it's an agent tool, not a shell command. SKILL.md now calls it as service_doctor(service="sec-indexer"). Frontmatter description updated to mention persona/rule install and the batched human checkpoint, so the registry catalog will reflect the new behavior after manifest regen.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Syncs `External/clarion-setup/SKILL.md` to upstream `jingerzz/clarion-intelligence-system@7430985` (PR #21).
What changes for a new Clarion user
Before: three user prompts (install skill, set up Clarion, paste personas+rules block) + inline pause for the `ZO_API_KEY` secret + a silent placeholder for SEC EDGAR identification (`clarion@example.com` shipped in every install's config).
After: one chat prompt (set up Clarion) + one batched human checkpoint near the end (SEC name+email AND `ZO_API_KEY`). Everything else autonomous.
Enabled by
Zo's agent tools `create_persona`, `list_personas`, `delete_persona`, `create_rule`, `list_rules`, `delete_rule`, and `service_doctor`. Previously persona/rule install required manual paste into Zo Settings → AI; now it's an agent call in the clarion-setup flow.
Idempotency
Step 6's pre-check (sec_user_agent non-placeholder + service_doctor RUNNING) makes clean re-runs fully autonomous — no human checkpoint at all on a re-run where nothing's broken. Persona/rule install steps 4 and 5 use `list_*` first and ask the user before replacing any customized entries.
SEC user-agent fix bundled
Closes a silent gap: previously, every Clarion install shipped `config.json` with `sec_user_agent: "Clarion Intelligence System (clarion@example.com)"` as default. Step 6 now prompts the user for their real name+email, and the agent writes it to config.json before the Step 7b restart picks it up. Per SEC's fair-access policy, every API consumer should identify themselves.
service_doctor correction folded in
Following up on PR #87 (synced from upstream #20): the SKILL.md previously framed `service_doctor` as a shell command. Per the Zo team, it's an agent tool. SKILL.md now calls it as `service_doctor(service="sec-indexer")` and inspects logs via shell separately.
Validation
`bun validate` — clean on `clarion-setup` (the 15 pre-existing warnings on other skills are untouched).
Footprint
Single file: `External/clarion-setup/SKILL.md` (+146/-58 lines). No code, no schema. Frontmatter description updated, so the manifest-regen bot should fire and the registry catalog will reflect the new install behavior.