Kill The Standup logo

Kill The Standup

Organization
Varnan-Tech
kill-the-standup

Reads yesterday's Linear issues and GitHub commits for the authenticated user, formats a standup update (done / doing / blockers), and posts it to Slack. Use when asked to write a standup, generate a standup update, post to the standup channel, summarize yesterday's work, or automate the daily standup. Trigger when a user says "write my standup", "post standup", "generate standup update", "what did I do yesterday", or "kill the standup".

Overview

PublisherVarnan-Tech
Repositoryopendirectory
Skill namekill-the-standup
Stars
674
Forks
74
Bundled files
2
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Varnan-Tech on GitHub. Read the source before you install it.

Installation

Install the Kill The Standup AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Varnan-Tech/opendirectory/tree/main/skills/kill-the-standup
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Varnan-Tech/opendirectory.git /tmp/opendirectory
mkdir -p .claude/skills
cp -r /tmp/opendirectory/skills/kill-the-standup .claude/skills/kill-the-standup
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Kill The Standup in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Kill The Standup on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Kill The Standup is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Kill the Standup

Read yesterday's Linear issues and GitHub commits. Format a standup update. Post it to Slack.


Step 1: Setup Check

Confirm required env vars are set:

bash
echo "LINEAR_API_KEY: ${LINEAR_API_KEY:+set}"
echo "SLACK_WEBHOOK_URL: ${SLACK_WEBHOOK_URL:+set}"
echo "GITHUB_REPO: ${GITHUB_REPO:-not set}"
echo "GITHUB_USERNAME: ${GITHUB_USERNAME:-not set}"

If LINEAR_API_KEY is missing: Stop. Tell the user: "LINEAR_API_KEY is required. Get it from Linear → Settings → API → Personal API keys. Add it to your .env file."

If SLACK_WEBHOOK_URL is missing: Stop. Tell the user: "SLACK_WEBHOOK_URL is required. Create an Incoming Webhook at api.slack.com/apps → Your App → Incoming Webhooks. Add it to your .env file."

If GITHUB_REPO is missing: Continue. GitHub commits will be skipped. Note this to the user.


Step 2: Fetch Linear Activity

Compute yesterday's date in ISO 8601 format (e.g. 2026-04-09T00:00:00.000Z).

Get current user ID:

bash
curl -s -X POST https://api.linear.app/graphql \
  -H "Authorization: Bearer $LINEAR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "query { viewer { id name email } }"}'

Extract the id field from the response. Store as LINEAR_USER_ID.

Fetch issues assigned to me, updated since yesterday:

bash
curl -s -X POST https://api.linear.app/graphql \
  -H "Authorization: Bearer $LINEAR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "query($since: DateTime!, $userId: ID!) { issues(first: 50, filter: { assignee: { id: { eq: $userId } } updatedAt: { gte: $since } }) { edges { node { identifier title state { name } url completedAt updatedAt createdAt } } } }",
    "variables": {"since": "YESTERDAY_ISO", "userId": "LINEAR_USER_ID"}
  }'

Categorize issues:

  • completedAt is non-null → Done
  • state.name is "In Progress", "Started", or "In Review" → Doing
  • state.name is "Cancelled" → skip
  • state.name is "Todo" or "Backlog" → skip (not worked on)

If zero issues: note "No Linear activity found for yesterday."


Step 3: Fetch GitHub Commits

Skip this step silently if GITHUB_REPO is not set.

If GITHUB_REPO is set:

bash
gh api "repos/$GITHUB_REPO/commits?author=${GITHUB_USERNAME:-$(gh api user --jq .login)}&since=YESTERDAY_ISO&per_page=30" \
  --jq '[.[] | {message: .commit.message, url: .html_url}]'

Process commits:

  • Extract the first line of each commit message (everything before the first newline)
  • Skip merge commits: drop any message starting with "Merge"
  • Deduplicate by message text

If GITHUB_REPO is set but returns zero commits: note "No commits found yesterday."


Step 4: Format Standup

Read references/standup-format.md in full before writing.

Produce the standup in this exact structure:

**Done**
- [ENG-123] Title of completed issue
- fix: commit message here

**Doing**
- [ENG-124] Title of in-progress issue

**Blockers**
No blockers.

Rules from standup-format.md:

  • No first-person pronouns ("I", "we")
  • Past tense for Done items, present continuous for Doing items
  • Each Linear item uses the [IDENTIFIER] Title format
  • Each GitHub commit uses the first line of the commit message
  • If no Done items: write "Nothing completed." under Done
  • If no Doing items: write "Nothing in progress." under Doing
  • If no blockers: write "No blockers."
  • Under 200 words total

Step 5: Post to Slack or Output

Present the formatted standup to the user.

Ask: "Post this to Slack, or output only?"

On confirmation to post:

bash
curl -s -X POST "$SLACK_WEBHOOK_URL" \
  -H "Content-Type: application/json" \
  -d '{
    "blocks": [
      {
        "type": "section",
        "text": {
          "type": "mrkdwn",
          "text": "*Standup — DATE_HERE*\n\n*Done*\nITEMS\n\n*Doing*\nITEMS\n\n*Blockers*\nITEMS"
        }
      }
    ]
  }'

Pass the body via a temp file or heredoc to avoid shell quoting issues with special characters in commit messages or issue titles:

bash
cat > /tmp/standup-payload.json << 'ENDJSON'
{
  "blocks": [
    {
      "type": "section",
      "text": {
        "type": "mrkdwn",
        "text": "STANDUP_CONTENT_HERE"
      }
    }
  ]
}
ENDJSON
curl -s -X POST "$SLACK_WEBHOOK_URL" -H "Content-Type: application/json" -d @/tmp/standup-payload.json

After posting: "Standup posted."

On "output only": Print the standup in a code block for copy-paste.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Kill The Standup AI skill do?

Reads yesterday's Linear issues and GitHub commits for the authenticated user, formats a standup update (done / doing / blockers), and posts it to Slack. Use when asked to write a standup, generate a standup update, post to the standup channel, summarize yesterday's work, or automate the daily standup. Trigger when a user says "write my standup", "post standup", "generate standup update", "what did I do yesterday", or "kill the standup".

Why use Kill The Standup on TypingMind?

Because you install it once and use it with any model. Kill The Standup is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Kill The Standup in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Varnan-Tech/opendirectory/tree/main/skills/kill-the-standup. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Kill The Standup?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Kill The Standup?

As many as you like. As long as a model supports skills, you can use Kill The Standup with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Kill The Standup AI skill free?

Yes. It is published on GitHub by Varnan-Tech under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇