status-card-query
Helps your agent create and manage status cards. It turns requests into searches and writes the first summaries.
What it does
This tool helps create and manage 'status cards' for projects. It can create a new card or update an existing one, turning simple text descriptions into structured queries to find relevant information.
When to use it
- ✓When you want to create a quick summary of important tasks from a week.
- ✓When you need to organize information about a project's progress.
- ✓When you want the AI to find and organize specific data about ongoing work.
Example of what to ask your AI
“Create a status card for launch work that was blocked or is under review this week, focusing on the next decision to be made.”
Want more? Open the sections below.
How to use
The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.
Skill link
Ready-to-paste message
How it works
You provide a description of what you want to know. The tool transforms this description into commands that the AI uses to search for specific information in project systems and then organizes this information into a summary.
Installation
Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.
In the terminal (Claude Code, Codex, Cursor), in your project folder:
npx skills add paperclipai/paperclip --skill status-card-queryOr download just the file:
curl -L https://raw.githubusercontent.com/paperclipai/paperclip/master/packages/skills-catalog/catalog/bundled/paperclip-operations/status-card-query/SKILL.md -o SKILL.mdTechnical content (original SKILL.md)
Original text by the author, straight from GitHub.
Status card query
Use this skill in one of two modes:
- Agent authoring: create or maintain a status card through the public API.
- Summarizer compilation: compile a card's prose prompt into structured company-search queries and write the first summary from the assigned generation run.
Agent-authored card recipe
Agent-authored cards require tasks:assign, remain company-scoped, and are available only when enableStatusCards is enabled. An agent may manage only cards it authored, may author at most 20 cards, and may send at most 4,000 characters in interestPrompt.
Normalize the run-provided API base and create a manual card:
PAPERCLIP_API_BASE="${PAPERCLIP_API_URL%/}"
PAPERCLIP_API_BASE="${PAPERCLIP_API_BASE%/api}"
curl -sS -X POST \
-H "Authorization: Bearer $PAPERCLIP_API_KEY" \
-H "Content-Type: application/json" \
-d '{"interestPrompt":"Blocked or in-review launch work updated this week"}' \
"$PAPERCLIP_API_BASE/api/companies/$PAPERCLIP_COMPANY_ID/status-cards"
Creation returns 201 and queues compilation automatically. Save the returned card id. To refine an owned card or request a refresh:
curl -sS -X PATCH \
-H "Authorization: Bearer $PAPERCLIP_API_KEY" \
-H "Content-Type: application/json" \
-d '{"interestPrompt":"Blocked or in-review launch work updated this week. Call out the single next decision."}' \
"$PAPERCLIP_API_BASE/api/status-cards/$STATUS_CARD_ID"
curl -sS -X POST \
-H "Authorization: Bearer $PAPERCLIP_API_KEY" \
-H "Content-Type: application/json" \
-d '{"full":false}' \
"$PAPERCLIP_API_BASE/api/status-cards/$STATUS_CARD_ID/refresh"
Do not call /query or /summary while authoring. Those write-back routes are reserved for the assigned Summarizer generation issue and run.
Summarizer compilation
You are the Summarizer compiling a status card's prose interest prompt into structured Paperclip company-search queries. The query array has union semantics: an issue matching any query belongs to the card. Prefer one narrow query; add another only when the prompt describes genuinely distinct populations.
CompanySearchQuery
Each object accepts these fields:
q: optional free-text search across matching company resources. Use it only for concepts not represented by structured filters.scope: useissuesfor status cards unless the assignment explicitly requires another supported scope.status: issue-status array.priority: issue-priority array.assigneeAgentId/assigneeUserId: a resolved assignee id.projectId: one resolved project UUID.labelId: one resolved label UUID.updatedWithin: a bounded duration such as24h,7d,4w, or3m.sort:relevance,updated,created, orpriority.limit: 1–50. Cap status-card queries at the smallest useful value, normally 20 and never above 50.offset: normally 0.
Resolve project and label names to ids before writing the query. Do not put human-readable names into projectId or labelId. If one prompt names multiple projects or labels, use separate query objects because each object has one projectId and one labelId.
Compilation guidance
- Preserve the user's intent; do not broaden “launch blockers updated this week” into every active task.
- Prefer structured filters over
qfor status, priority, assignee, project, label, and recency. - Add
updatedWithinwhenever the prompt says recent, current, this week, lately, or otherwise implies a moving window. - Keep
qshort and specific. Avoid copying the whole prose prompt into it. - Set
scope: "issues",offset: 0, and an explicit boundedlimiton every query. - Return at least one query. If the prompt cannot be compiled safely, report the ambiguity instead of inventing ids.
Exact write-back sequence
The generation issue contains statusCardId, companyId, and generationIssueId. Both writes must use the run-scoped API credentials from that same assigned issue run.
First write the compiled query:
{
"queries": [
{
"q": "launch",
"scope": "issues",
"status": ["in_progress", "blocked", "in_review"],
"updatedWithin": "7d",
"sort": "updated",
"limit": 20,
"offset": 0
}
],
"title": "Launch work updated this week",
"changeSummary": "Compiled the launch prompt into one recent active-work query.",
"generationIssueId": "<generation-issue-id>"
}
…
FAQ
What are 'status cards'?
They are organized summaries of project or task progress information, automatically created by the AI.
Can I create as many cards as I want?
An agent can manage a maximum of 20 cards that they authored themselves.
What happens if the description is too long?
The tool limits the description to 4,000 characters to ensure the AI can process it efficiently.
Details
Original description by the author
Create and maintain agent-authored Paperclip status cards, or compile a prose interest prompt into bounded CompanySearchQuery objects and write the first summary from the assigned Summarizer run.
repo: paperclipai/paperclip
Popularity
- GitHub stars
- 103k
- Ranking position
- #378
- License
- MIT
- Updated
- 10/16/2026
Comments
- …
More skills from this repository
delegate-work
Helps your agent delegate work to another agent. It's useful for breaking down complex tasks and tracking progress in an organized way.
paperclipai/paperclip
follow-up-results
Has your agent check results from previous work. It's useful for tracking task progress and adding human feedback.
paperclipai/paperclip
review-my-team
Helps your agent review the connected team. It's useful for getting a summary of the team, tasks, blockers, and pending approvals.
paperclipai/paperclip
paperclip-task-bridge
Has your agent create and manage tasks on another platform. It's useful for interacting with project management systems directly.
paperclipai/paperclip
Similar skills
dashboard-builder
Helps your agent create useful monitoring dashboards. It turns data into charts that answer important system questions.
affaan-m/ECC
dev-team
Simulates a collaborative development team where different roles respond to a problem together. It's useful for getting multiple perspectives without manually switching agents.
affaan-m/ECC
ecc-council
Has your agent convene a four-voice council for difficult decisions. It's useful when there are multiple good options and debate is needed before choosing.
affaan-m/ECC