Agent skill

Summarize Status

by paperclipai in paperclipai/paperclip

Write a short, colloquial summary for a Paperclip summary slot: open with the 1–3 specific, concrete actions the reader needs to take right now to unblock the work, then a brief plain-language…

MITAuto-check passedWriting & Content

Install Summarize Status

skills CLI
$ npx skills add paperclipai/paperclip --skill summarize-status -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install paperclipai/paperclip summarize-status --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/paperclipai/paperclip.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/skills-catalog/catalog/bundled/paperclip-operations/summarize-status .claude/skills/summarize-status && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
summarize-status
GitHub stars
99k
Token cost
~2.2k tokens
SKILL.md length
1,083 words
Files
1
Skills in repo
60
Repo updated
First seen
Licence
MIT

At a glance

Write a short, colloquial summary for a Paperclip summary slot: open with the 1–3 specific, concrete actions the reader needs to take right now to unblock the work, then a brief plain-language…

  • Works in 5 steps: Read the current slot for the scope you… → Understand the scope. Start from the… → Write the summary: the 1–3 concrete… → …
  • Tasks that involve Plain language and style rules
  • SKILL.md covers When to use, When not to use, Inputs and API quick reference, plus 1 more section
  • Calls jq and curl; needs PAPERCLIP_API_KEY

What it does

Summarize Status is an agent skill from paperclipai/paperclip. Write a short, colloquial summary for a Paperclip summary slot: open with the 1–3 specific, concrete actions the reader needs to take right now to unblock the work, then a brief plain-language status, streaming progress as it works.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Writing & Content, covering Plain language and style rules. The repository describes itself as: The open-source app everyone uses to manage agents at work. The licence is MIT.

When your agent uses it

  • Tasks that involve Plain language and style rules

Example prompts

  • “/summarize-status”

Requirements

  • A credential in PAPERCLIP_API_KEY

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Read the current slot for the scope you were given. The response includes the latest document body and latestRevisionId; use those directly.
  2. Understand the scope. Start from the snapshot if the generation issue has one, and read whatever issues, comments, or blocker chains you…
  3. Write the summary: the 1–3 concrete actions first, each with context and an inline link; then the brief conversational status. Colloquial…
  4. Write the revision back to the slot with markdown, a one-line changeSummary describing what moved since the last revision, baseRevisionId…
  5. Close out the generation issue: leave a short comment (scope summarized, revision written, the top action in one clause) and mark it done…

What it can do on your machine

Read from SKILL.md and the folder at commit 3ec7309. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • jq
    • curl

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • PAPERCLIP_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Summarize Status loads about 2.2k tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 1,083 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~62
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from paperclipai/paperclip at commit 3ec7309, republished under its MIT licence (© paperclipai). 1,083 words, ~2,207 tokens.

Download SKILL.mdSave it as .claude/skills/summarize-status/SKILL.md (or your agent's skills folder).
name
summarize-status
description
Write a short, colloquial summary for a Paperclip summary slot: open with the 1–3 specific, concrete actions the reader needs to take right now to unblock the work, then a brief plain-language status, streaming progress as it works.
key
paperclipai/bundled/paperclip-operations/summarize-status
recommendedForRoles
- general - manager
tags
- paperclip - summary - status - reporting - operations

Summarize status

You are the Summarizer. Turn the current state of a Paperclip scope — a project, the workspaces overview, a project workspace, or a specific execution workspace — into a short, honest, human-readable Markdown summary and write it back to that scope's summary slot as a new revision.

Open with what the reader needs to do. The first thing in every summary is 1–3 specific, concrete, actionable items the reader should do right now to unblock this tree of work — "merge the install PR", "answer the org-accounts question", "approve the OAuth plan". Each item says what to do and why it's the thing holding up progress, with an inline link. This is the whole point of the summary: someone glances at the card and knows exactly what to do next. If genuinely nothing needs them, say so plainly in one line and name the next thing worth watching — never pad with filler actions.

After the actions, give a brief status: a paragraph or two of plain conversational language on where things stand and what's moving. Write for a reader who has not memorized every issue id or thread — give enough context inline that each point makes sense without clicking, and link the few issues you mention where you mention them.

Use your judgment about what matters. Read whatever you need — issue bodies, comments, blocker chains — to actually understand where things are; you can't pick the right actions from titles alone. Then be ruthless about what makes the page: focus on what's most important and leave the rest off. The card renders next to the board, which already lists every issue, so a summary that reads like a task list has failed. Keep it short enough to read in one glance, with only a handful of inline links.

This is a read-and-report loop. You never change the underlying issues, workspaces, or code — you only write one Markdown revision back to the slot you were asked to summarize.

When to use

  • A summary-generation issue is assigned to you naming a scope (project, workspaces_overview, project_workspace, or execution_workspace) and slot (header).
  • A board user clicked Generate / Refresh on a summary card and Paperclip created work for you.
  • A paused refresh routine you own is manually run or its schedule is enabled by an operator.

When not to use

  • You were asked to change issue state, reassign work, or edit code. That is out of scope — summarize only.
  • No scope was given, or the scope is in another company. Refuse and ask for a scoped generation issue. Every read stays company-scoped.
  • You are asked to invent status the source data does not support. Never fabricate — an empty scope gets an honest "nothing needs you" summary. And never surface secrets (API keys, tokens, credentials) that appear in issue bodies or configs.

Inputs

From the generation issue / run context:

  • scopeKind — project, workspaces_overview, project_workspace, or execution_workspace.
  • scopeId — the project, project-workspace, or execution-workspace id. Omitted for workspaces_overview (it has no scopeId).
  • slotKey — currently always header.
  • generationIssueId — the issue that requested this summary; pass it back so the slot records what produced the revision.
  • The previous revision (if any) — read it so you can tell what's new and lead with that instead of repeating what the reader already saw.
  • Generation issues often include a Prebuilt scope snapshot of the scope's issues — a useful starting point, but fetch and read whatever else you need to understand the state.

API quick reference

Use these routes directly. Do not guess unscoped /api/issues or alternate summary paths:

  • Read the current slot: GET /api/companies/{companyId}/summary-slots/{scopeKind}/{slotKey}?scopeId=...
  • Read revision history only when the current-slot response is missing its latest document: GET /api/companies/{companyId}/summary-slots/{scopeKind}/{slotKey}/revisions?scopeId=...
  • Gather project issues: GET /api/companies/{companyId}/issues?projectId=...
  • Gather execution-workspace issues: GET /api/companies/{companyId}/issues?executionWorkspaceId=...
  • Write the new revision: PUT /api/companies/{companyId}/summary-slots/{scopeKind}/{slotKey} with scopeId, markdown, changeSummary, baseRevisionId, generationIssueId, and model in the JSON body.

For workspaces_overview, omit scopeId from the read query and send it as null in the write body. All calls use the run-scoped Paperclip API URL and bearer token already present in the environment.

Complete project-slot write example:

sh
COMPANY_ID="<company-id>"
PROJECT_ID="<project-id>"
GENERATION_ISSUE_ID="<generation-issue-id>"
BASE_REVISION_ID="<previous-revision-id-or-empty>"
MODEL="<model-used>"

SUMMARY_MARKDOWN=$(cat <<'MARKDOWN'
**Nothing needs you right now.** Quiet scope — nothing is in flight and nothing is waiting on you. The next thing worth watching is the first issue landing in this project.
MARKDOWN
)

jq -n \
  --arg scopeId "$PROJECT_ID" \
  --arg markdown "$SUMMARY_MARKDOWN" \
  --arg changeSummary "First summary for this scope" \
  --arg baseRevisionId "$BASE_REVISION_ID" \
  --arg generationIssueId "$GENERATION_ISSUE_ID" \
  --arg model "$MODEL" \
  '{
    scopeId: $scopeId,
    markdown: $markdown,
    changeSummary: $changeSummary,
    baseRevisionId: (if $baseRevisionId == "" then null else $baseRevisionId end),
    generationIssueId: $generationIssueId,
    model: $model
  }' |
curl -sS -X PUT \
  -H "Authorization: Bearer $PAPERCLIP_API_KEY" \
  -H "Content-Type: application/json" \
  "$PAPERCLIP_API_URL/api/companies/$COMPANY_ID/summary-slots/project/header" \
  --data-binary @-
Show full SKILL.md (421 more words)Show less

Procedure

Your assistant text streams live to the summary card while the reader waits, so narrate as you work:

  • Post the first status update immediately, before doing anything else. Take the first task you can see in the context you were handed and emit a STATUS: line naming it, e.g. STATUS: considering "Fix login redirect loop"…. Its whole job is to show the reader something is happening the moment work starts.

  • Emit a fresh STATUS: line every time your attention moves — each cluster you weigh, each candidate action you're sizing up, each step of the write-back. One short line of plain assistant text, not inside a tool call. Long silent stretches between tool calls are a failure of this protocol even when the final summary is good.

  • Before the slot write, emit the complete final Markdown as plain assistant text between these exact sentinels, each on its own line, then perform the write with exactly the same Markdown (tool-call arguments don't stream; assistant text does):

    text
    <<<SUMMARY-DRAFT>>>
    <complete final Markdown>
    <<<END-SUMMARY-DRAFT>>>

    If a status line or sentinel is skipped, the UI falls back to its spinner; the summary-slot write remains the only authoritative summary.

Steps:

  1. Read the current slot for the scope you were given. The response includes the latest document body and latestRevisionId; use those directly.
  2. Understand the scope. Start from the snapshot if the generation issue has one, and read whatever issues, comments, or blocker chains you need to genuinely understand where things are and what's stuck on a human. Decide what's most important — what 1–3 actions would actually unblock this tree of work right now.
  3. Write the summary: the 1–3 concrete actions first, each with context and an inline link; then the brief conversational status. Colloquial, not clinical — write the way you'd catch a colleague up out loud, no status jargon ("in_review", "P2").
  4. Write the revision back to the slot with markdown, a one-line changeSummary describing what moved since the last revision, baseRevisionId from step 1 (so concurrent writes are detected), generationIssueId, and model (the model you actually ran on). Writing the revision is the deliverable — do not also comment the whole summary onto unrelated issues. Stay well under the 200 KB slot limit; a good header summary is under 1 KB.
  5. Close out the generation issue: leave a short comment (scope summarized, revision written, the top action in one clause) and mark it done. If you could not read the scope, mark it blocked and name the exact unblock owner and action.

© paperclipai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in packages/skills-catalog/catalog/bundled/paperclip-operations/summarize-status of paperclipai/paperclip.

Open the folder on GitHubat commit 3ec7309

Compare with similar skills

Summarize Status next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Summarize Status compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Summarize Status this skillpaperclipai/paperclip99k—~2.2kAutomated safety check: PassMIT
Asd Ste100danyuchn/asd-ste100-skill4.3k—~4.1kAutomated safety check: PassMIT
Ponytail AuditDietrichGebert/ponytail160k—~1.4kAutomated safety check: PassMIT
Technical Writing Standardcursor/plugins11k10 repos~2.4kAutomated safety check: PassNone
Natural Japanese Business Writingcoji/natural-japanese1.9k—~2.1kAutomated safety check: PassMIT
PgjevrealZachi/pg-jev1.1k—~2.9kAutomated safety check: PassCustom licence

Similar skills

  • Asd Ste100

    danyuchn/asd-ste100-skill

    A skill your agent uses when English text must be parsed without a human to resolve ambiguity — tool descriptions, error messages, inter-agent instructions, system prompts, status reports — and…

    4.3k GitHub stars~4.1k tokensUpdated 6 days ago
    Writing & ContentAuto-check passed
  • Ponytail Audit

    DietrichGebert/ponytail

    Quality audit of a whole repo: bugs, security holes, what breaks under real load, risky code without tests, slow paths, and what to delete, merge or split.

    160k GitHub stars~1.4k tokensUpdated today
    Writing & ContentAuto-check passed
  • Official

    Applies four layers of technical-writing rules to docs, RFCs, readmes, PR descriptions and commit messages so a tired engineer follows them on the first read.

    11k GitHub starsUsed in 10 repos~2.4k tokens
    Writing & ContentAuto-check passed
  • Writes and edits Japanese business documents so they read clearly and naturally, removes AI-sounding phrasing and can score how AI-like a text reads.

    1.9k GitHub stars~2.1k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed
  • Pgjev

    realZachi/pg-jev

    Install, configure, query and explain pgjev (the jev PostgreSQL extension that filters, ranks and classifies rows with plain-language conditions via TypeSafe's Jev model).

    1.1k GitHub stars~2.9k tokensUpdated 3 days ago
    Writing & ContentAuto-check passed
  • Defensive Writing Editor

    lennney/stop-that-shit

    Cuts defensive disclaimers, stacked hedging and self-protective narration from proposals and summaries, keeping only limits that affect the reader's decision.

    2.5k GitHub starsUsed in 1 repo~1.2k tokens
    Writing & ContentAuto-check passed

More from paperclipai/paperclip

All 60 skills in this repo
  • Garden Inbox

    paperclipai/paperclip

    Scan a Paperclip user's Mine inbox, classify reversible archive candidates, request checkbox confirmation, and archive only accepted selections.

    99k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Paperclip

    paperclipai/paperclip

    Interact with the Paperclip control plane API for task coordination and governance.

    99k GitHub stars~9.6k tokensUpdated today
    Auto-check passed
  • Paperclip

    paperclipai/paperclip

    A skill your agent uses for Paperclip-managed tasks and heartbeats: reading task context, delivering task documents or files, updating completion or blockers, coordinating or delegating work, and…

    99k GitHub stars~17k tokensUpdated today
    Auto-check passed
  • Design Guide

    paperclipai/paperclip

    Paperclip UI design system guide for building consistent, reusable frontend components.

    99k GitHub starsUsed in 1 repo~3.1k tokens
    Auto-check passed
  • Paperclip Page

    paperclipai/paperclip

    Publish static HTML pages and asset folders to the Paperclip S3/CloudFront page host.

    99k GitHub stars~1k tokensUpdated today
    Auto-check passed
  • Paperclip Create Agent

    paperclipai/paperclip

    Create new agents in Paperclip with governance-aware hiring.

    99k GitHub starsUsed in 1 repo~2.1k tokens
    Auto-check passed

Questions about Summarize Status

What does Summarize Status do?

Write a short, colloquial summary for a Paperclip summary slot: open with the 1–3 specific, concrete actions the reader needs to take right now to unblock the work, then a brief plain-language…. Summarize Status is an agent skill from paperclipai/paperclip. Write a short, colloquial summary for a Paperclip summary slot: open with the 1–3 specific, concrete actions the reader needs to take right now to unblock the work, then a brief plain-language status, streaming progress as it works.

When should I use Summarize Status?

Summarize Status fits situations like: tasks that involve Plain language and style rules.

How do I install Summarize Status in Claude Code?

Run `npx skills add paperclipai/paperclip --skill summarize-status -a claude-code`. Or copy the skill folder (packages/skills-catalog/catalog/bundled/paperclip-operations/summarize-status in paperclipai/paperclip) into .claude/skills/summarize-status in your project. Claude Code loads it when a task matches its description.

How do I install Summarize Status in Codex?

Run `npx skills add paperclipai/paperclip --skill summarize-status -a codex`. Or copy the skill folder (packages/skills-catalog/catalog/bundled/paperclip-operations/summarize-status in paperclipai/paperclip) into .agents/skills/summarize-status in your project. Codex loads it when a task matches its description.

Can I use Summarize Status in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add paperclipai/paperclip --skill summarize-status -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/summarize-status, .gemini/skills/summarize-status, .github/skills/summarize-status and .opencode/skills/summarize-status in your project.

What does Summarize Status need to run?

Going by SKILL.md and its folder, Summarize Status needs the command-line tools its instructions call (jq and curl) and credentials named PAPERCLIP_API_KEY. Our summary lists: A credential in PAPERCLIP_API_KEY.

Does Summarize Status access the network?

SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Summarize Status safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Summarize Status use?

Summarize Status is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Summarize Status use?

About 2.2k tokens (SKILL.md is roughly 8.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Summarize Status?

Skills that share tags, products or a category with Summarize Status: Asd Ste100 (danyuchn/asd-ste100-skill, 4.3k stars), Ponytail Audit (DietrichGebert/ponytail, 160k stars), Technical Writing Standard (cursor/plugins, 11k stars) and Natural Japanese Business Writing (coji/natural-japanese, 1.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Summarize Status?

paperclipai (a GitHub organization) maintains it in paperclipai/paperclip, which has 99,357 GitHub stars. The repository holds 60 skills in this directory. The repository was last updated on October 10, 2026.

Source: paperclipai/paperclip on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.