dashboard-handoff
Skill24 starsChanged 2 months agoMITView on GitHub
Post-edit dashboard verification for B-N work touching F:\.ELAI_workflow\.elai_cc\crates\dashboard-v2\. Triggers after Write/Edit on dashboard files when transitioning to AUDITING. Spawns dashboard-smoker agent for svelte-check + cargo check + optional manual tauri:dev launch. Aggregates results into the audit context.
- Installs packages
In this repository43 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- anti-spiralSkill
- auto-orchestrateSkill
- b-plan-runnerSkill
- cookSkill
- grillSkill
- idea-intakeSkill
- impact-checkSkill
- improvement-conjectureSkill
- incremental-evalSkill
- operatorSkill
- oracleSkill
- orchestrateSkill
- paper-to-planSkill
- pdfSkill
- planning-workflowSkill
- prompt-transformSkill
- rag-toolsSkill
- seeSkill
- sequential-opus-orchestratorSkill
- spec-evalSkill
- teachSkill
- anti-spiralSkill
- auto-orchestrateSkill
- b-plan-runnerSkill
- cookSkill
- dashboard-handoffSkill
- grillSkill
- idea-intakeSkill
- impact-checkSkill
- improvement-conjectureSkill
- incremental-evalSkill
- operatorSkill
- oracleSkill
- orchestrateSkill
- paper-to-planSkill
- pdfSkill
- planning-workflowSkill
- prompt-transformSkill
- seeSkill
- sequential-opus-orchestratorSkill
- teachSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 30
If drift: surface to user before spawning the smoker.
- Distinctive: line 38
Read its return + the dashboard-smoke.md it writes.
- Very specific: line 43
If user requests visual verification (e.g., "check the orbit visualizer"): Re-spawn dashboard-smoker with trigger="manual".
- Distinctive: line 54
Never run pnpm install or npm install — Anti-Slopsquatting.
- Distinctive: line 55
Never modify dashboard source from this skill — read-only verification.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Dashboard handoff
Trigger: in EXECUTING -> AUDITING transition, any of these were edited
- F:.ELAI_workflow.elai_cc\crates\dashboard-v2\src-tauri\src*.rs
- F:.ELAI_workflow.elai_cc\crates\dashboard-v2\src***.svelte
- F:.ELAI_workflow.elai_cc\crates\dashboard-v2\src\lib\api*.ts
- F:.ELAI_workflow.elai_cc\crates\dashboard-v2\src\lib\drawers*.svelte
Skip if no dashboard-v2 file was edited.
PROTOCOL
- Aggregate the windows / components changed in this EXECUTING pass. Use git diff or scan the session's edit log:
- windows_changed: from src/lib/windows/.svelte and src/screens/.svelte
- components_changed: from src/lib/drawers/.svelte, src/lib/orbit/, src/lib/layout/*
- tauri_commands_changed: from src-tauri/src/*.rs
- Cross-language pair sanity check. For each src-tauri/src/*.rs change, verify the corresponding src/lib/api/stub.ts has been updated (or has cross-lang-skip annotation). Use cross_lang_diff.py: python F:.ELAI_workflow.Codex\tools\cross_lang_diff.py --git-staged If drift: surface to user before spawning the smoker.
- Spawn dashboard-smoker agent (.Codex/agents/dashboard-smoker.md) with:
session_id: <session_id>
windows_changed:
<list>components_changed:<list>trigger: "post-edit" - Read its return + the dashboard-smoke.md it writes. Possible verdicts: PASS: svelte-check + cargo check both clean. Proceed to AUDITING. FAIL: errors present. Treat as a BLOCK pre-audit. Trigger fixer pre-audit (skip the auditor; go straight to fixer). DEGRADED: tool missing (pnpm/svelte-check). Surface to user — they may need to install pnpm or skip dashboard checks.
- If user requests visual verification (e.g., "check the orbit visualizer"):
Re-spawn dashboard-smoker with trigger="manual". The smoker will start
pnpm tauri:devin background. The smoker returns the localhost URL. Tell user: "Tauri dev running at<URL>. Open in browser, verify the changes manually. Reply 'done' when finished." Cleanup: when user replies done, kill the background tauri process. - Append the smoke report path to the auditor's input. The auditor reads dashboard-smoke.md as evidence in REVIEW_CODE sub-state.
INTEGRATION WITH B-PLAN-RUNNER b-plan-runner skill step 9 (AUDITING) checks if dashboard files were touched. If yes, runs dashboard-handoff before spawning auditor.
QUALITY RULES
- Never run pnpm install or npm install — Anti-Slopsquatting.
- Never modify dashboard source from this skill — read-only verification.
- Cleanup: always kill background tauri:dev when done. Use Bash run_in_background tracking.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

