com um clique
planner
Manage Kanban tasks, plan modes, and project workflows in Dataspheres AI
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Menu
Manage Kanban tasks, plan modes, and project workflows in Dataspheres AI
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
Local dev skill for the Dataspheres AI Content API. Wraps /api/v1/ REST endpoints for local-to-production content workflows. Use when the user wants to push pages, generate release notes from git log, list pages, or update content in a datasphere from their local machine.
Full newsletter lifecycle — create, configure all settings (frequency, personalization, AI model, web search, reply threading, plan mode wiring), manage subscribers, attach forms, draft and manage issues, preview personalized letters, enable private chat and email replies, and test in dev.
Drive the Dataspheres AI platform from Claude Code — read conversation history, post messages as the user (via API key), poll for ARI replies, read the Reality Engine debug log, update the plan and outcomes, and control orchestration flow. Use when you need Claude Code to interact with ARI or inspect/modify a running reality session.
Knowledge-graph tools for Dataspheres AI — build typed graphs, relate nodes with VISUAL or executable TASK edges, group into colored container bubbles, auto-detect article hero images, embed graphs in pages, run scheduled searches, and report.
Sequencers tools for Dataspheres AI
Skill for producing high-fidelity, interactive blog posts, research reports, and intelligent reports on the Dataspheres AI platform. Drives ARI and ari-dai-skills to use the full tool suite — web search, image generation, YouTube embeds, code blocks, Mermaid diagrams, datasets, live data cards, citations, and SEO metadata — to produce publication-ready interactive pages.
| name | planner |
| description | Manage Kanban tasks, plan modes, and project workflows in Dataspheres AI |
| argument-hint | [action] [options] |
The dai planner skill lets you manage tasks, columns, and board configurations — all dai, every dai.
create_task(title="Fix auth bug", status_group_id="<id>", priority="HIGH", tags=["backend"])
bulk_create_tasks(tasks=[
{"title": "Task 1", "statusGroupId": "<id>", "priority": "HIGH"},
{"title": "Task 2", "statusGroupId": "<id>", "priority": "MEDIUM"},
])
list_tasks(plan_mode_id="<id>", limit=50)
update_task(task_id="<id>", status_group_id="<done-group-id>")
search_tasks(query="auth bug")
list_plan_modes()
Templates: default | ops | sprint | research | sales | editorial | crm
create_plan_mode(name="Sprint Q2", template="sprint", tag_filter=["q2", "sprint"])
tag_filter scopes which tasks appear in this board. Infer it from the name automatically.
columns overrides template when both are provided.
create_plan_mode(name="Wedding Planning", tag_filter=["wedding"], columns=[
{"name": "Ideas & Vision", "color": "#8B5CF6", "isDoneState": false},
{"name": "To Book / Confirm", "color": "#F59E0B", "isDoneState": false},
{"name": "In Progress", "color": "#3B82F6", "isDoneState": false},
{"name": "Vendor Confirmed", "color": "#22C55E", "isDoneState": false},
{"name": "Done", "color": "#6B7280", "isDoneState": true},
])
tag_filter and columns are full replacements. add_columns is append-only.
Always call list_plan_modes first before using columns — omitted columns are deleted
and their tasks remapped to column[0] of the new list.
update_plan_mode(mode_id="<id>", name="New Name")
update_plan_mode(mode_id="<id>", tag_filter=["wedding"])
# Full column replace (read current first, include everything you want to keep)
update_plan_mode(mode_id="<id>", columns=[
{"name": "Ideas & Vision", "color": "#8B5CF6", "isDoneState": false},
{"name": "To Book / Confirm", "color": "#F59E0B", "isDoneState": false},
{"name": "In Progress", "color": "#3B82F6", "isDoneState": false},
{"name": "Vendor Confirmed", "color": "#22C55E", "isDoneState": false},
{"name": "Signed & Done", "color": "#6B7280", "isDoneState": true},
])
# Append-only — safe without reading first
update_plan_mode(mode_id="<id>", add_columns=[
{"name": "Awaiting Review", "color": "#F59E0B", "isDoneState": false},
])
create_status_group(name="Blocked", color="#EF4444", plan_mode_id="<id>", is_done_state=false)
list_status_groups(plan_mode_id="<id>")
add_comment(task_id="<id>", content="Done — tested on staging ✅")
# With screenshot attachments (hosted HTTPS URLs)
add_comment(task_id="<id>", content="Reproduced on staging — see screenshot",
screenshots=["https://cdn.example.com/bug-shot.png"])
content field)Task descriptions support full Tiptap HTML — the same schema as pages. Use this to write detailed specs, acceptance criteria, or reference material directly on the card.
<!-- Interactive checklist (renders as real, clickable checkboxes) -->
<h2>Acceptance Criteria</h2>
<ul class="tiptap-task-list" data-type="taskList">
<li class="tiptap-task-item" data-checked="false" data-type="taskItem"><label><input type="checkbox"><span></span></label><div><p>User can reset password via email link</p></div></li>
<li class="tiptap-task-item" data-checked="false" data-type="taskItem"><label><input type="checkbox"><span></span></label><div><p>Link expires after 24 hours</p></div></li>
<li class="tiptap-task-item" data-checked="false" data-type="taskItem"><label><input type="checkbox"><span></span></label><div><p>Errors shown inline, not as alerts</p></div></li>
</ul>
<!-- ⚠️ data-type="taskList" on the <ul> AND data-type="taskItem" on every <li> are REQUIRED.
A <li class="tiptap-task-item"> WITHOUT data-type="taskItem" renders as a plain bullet —
no checkbox. Full format + rules: see the rich-content skill § Interactive Task Checklists. -->
<!-- Code reference -->
<h2>Relevant Code</h2>
<pre><code class="language-typescript">// auth/reset.ts — current implementation
export async function sendResetLink(email: string) { ... }
</code></pre>
<!-- Mermaid diagram — flow or sequence diagrams work well for specs -->
<div data-type="mermaid" data-source="sequenceDiagram
User->>API: POST /auth/reset
API->>Email: Send link
User->>API: GET /auth/reset?token=xyz
API->>User: Redirect to /new-password"></div>
<!-- Embedded data card (live chart) -->
<div data-type="dataCard"
data-datacard-id="card_abc"
data-dataset-id="ds_xyz"
data-datasphere-id="ds_default">[Data Card: Error Rate]</div>
<!-- Link to a related page -->
<p>See <a href="https://dataspheres.ai/app/my-ds/pages/auth-design">Auth Design Doc</a> for context.</p>
content FieldComments support plain text and basic inline formatting. For visual evidence (screenshots, screen recordings), use the screenshots array — these render as inline image attachments on the task card.
# Plain text — most common
add_comment(task_id="t1", content="Fixed in PR #42 — deploying to staging now.")
# With screenshots — pass hosted HTTPS URLs (generate_media_image or upload_file first)
add_comment(
task_id="t1",
content="Reproduced on Chrome/Windows. Screenshot attached.",
screenshots=["https://cdn.example.com/bug-chrome.png", "https://cdn.example.com/bug-win.png"],
)
Generate an image, then attach to a comment:
img = generate_media_image(prompt="Architecture diagram, dark theme, clean lines")
add_comment(task_id="t1", content="Proposed architecture:", screenshots=[img["url"]])
Upload a local file, then attach:
result = upload_file("/path/to/screenshot.png")
add_comment(task_id="t1", content="Screen recording from QA:", screenshots=[result["url"]])
HIGH | MEDIUM | LOW
For spec-driven development with the 5-column lifecycle (North Stars → Epics → Execution → Validation → Done), use the all-dai-sdd skill which wraps the planner with the full lifecycle protocol.
dai use <uri>