New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Seed Demo Data

by overmind-core in overmind-core/overmind

Run or modify the seeddemo management command (the one-project Support Copilot demo) without breaking the beat-safety invariants that keep celery workers from re-driving seeded rows.

AGPL-3.0Auto-check passedAI & LLM Engineering

Install Seed Demo Data

skills CLI
$ npx skills add overmind-core/overmind --skill seed-demo-data -a claude-code

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

GitHub CLI
$ gh skill install overmind-core/overmind seed-demo-data --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/overmind-core/overmind.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/seed-demo-data .claude/skills/seed-demo-data && 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
seed-demo-data
GitHub stars
603
Token cost
~973 tokens
SKILL.md length
467 words
Files
1
Skills in repo
20
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Run or modify the seeddemo management command (the one-project Support Copilot demo) without breaking the beat-safety invariants that keep celery workers from re-driving seeded rows.

  • Seeding demo data
  • SKILL.md covers Run, Beat-safety invariants — never… and Mechanics
  • Calls docker
  • Editing overbae/management/commands/seeddemo.py

What it does

Seed Demo Data is an agent skill from overmind-core/overmind. Run or modify the seeddemo management command (the one-project Support Copilot demo) without breaking the beat-safety invariants that keep celery workers from re-driving seeded rows. Use when seeding demo data or editing overbae/management/commands/seeddemo.py.

Its SKILL.md is about 970 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 AI & LLM Engineering, covering Background jobs. The repository describes itself as: The platform for continuously improving AI agents. The licence is AGPL-3.0.

When your agent uses it

  • Seeding demo data
  • Editing overbae/management/commands/seeddemo.py

Example prompts

  • “/seed-demo-data”

Requirements

  • Python 3
  • Docker

What it can do on your machine

Read from SKILL.md and the folder at commit 3dec73c. 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:

    • docker

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

  • Network

    No URLs in SKILL.md. Its commands use docker, 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 no API keys, tokens, secrets or passwords.

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

Context cost

Seed Demo Data loads about 973 tokens when it runs. Until then it costs about 70 tokens; SKILL.md has 467 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~70
When it runs · the whole SKILL.md, loaded when a task matches
~973

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 overmind-core/overmind at commit 3dec73c, republished under its AGPL-3.0 licence (© overmind-core). 467 words, ~973 tokens.

Download SKILL.mdSave it as .claude/skills/seed-demo-data/SKILL.md (or your agent's skills folder).
name
seed-demo-data
description
Run or modify the seed_demo management command (the one-project Support Copilot demo) without breaking the beat-safety invariants that keep celery workers from re-driving seeded rows. Use when seeding demo data or editing overbae/management/commands/seed_demo.py.

Demo seed (manage.py seed_demo)

Seeds one project — Support Copilot at Ledgerline, a fictional payments company — with thirty days of traffic across three capabilities (ticket triage, KB answering, dispute resolution) and every downstream surface filled: tasks, executions and verdicts, sessions, datasets with cell chains and chats, eval runs, optimiser runs (harness, backtest, hybrid), training jobs with judge evals and class metrics, deployed models with inference traffic, and the credits ledger.

Run

bash
docker compose exec api python manage.py seed_demo [--owner EMAIL]

~10 min, deterministic (seeded RNG, uuid5 ids for capabilities, jobs and groups, timestamps anchored to NOW) and idempotent: the reset deletes the project by slug (plus the retired Undermind demo slugs), the @ledgerline.dev team users, and the owner's non-free-credit ledger rows before it seeds. The project belongs to --owner (default frey@overmindlab.ai); the account is created with password password when it does not exist. Plaintext API keys print at the end.

Beat-safety invariants — never break these

Celery beat + reconcilers stay running against the seeded DB. Violations cause workers to re-drive seeded rows against real providers and spend credits:

  • Every EvalRun / FinetuningJob / OptimizerExperiment / dataset Cell is TERMINAL (reconcilers re-drive non-terminal rows within 10–60s).
  • sweep_unscored_traces selects roots by a two-hour received_at lookback and re-scores a trace whose latest ScoringPass.started precedes the root's received_at. So every trace is at least three hours old, every span's received_at is backdated in the same _flush() that inserts it (the sweep runs every two minutes; a batch left at "now" for even one tick gets scored and its TaskExecution collides with the seed's), and every scored trace has a ScoringPass whose started is after its spans landed.
  • A capability sync fires the evaluator preload and rebind hooks (sync_card_evaluators_task, preload_capability_eval_set, enqueue_capability_eval_preload_on_commit, identity.enqueue_rebind) and the sync_evaluators_on_card_change signal; the seed patches them to no-ops and disconnects the signal. Evaluator updated_at is backdated too, or the "contract changed after the pass" rule rescores everything.
  • The training monitor syncs each FinetuningJobEval score from its own EvalRun summary, so every job eval links to a single-variant run (bench_runs); a shared two-variant run collapses baseline and final to the pooled score.
  • Connectors keep auto_sync_enabled=False.
Show full SKILL.md (128 more words)Show less

Mechanics

  • auto_now_add/auto_now columns are backdated via the raw-SQL backdate() helper (executemany), not via the ORM.
  • Datasets land through services/datasets/land and run through notebook/run.execute, so every dataset has an active cell with a real frame. Historical demo consumption stamps used_at directly and pins cells, including each training job's eval_cell; it does not fabricate a semantic quality review. Live use reports missing reviews as warnings. The reset deletes jobs, experiments and eval runs before the project.
  • Eval run summaries come from the real aggregate_run task applied inline; scores per variant are Score rows, so per-variant numbers are read from run.scores, never recomputed from the summary.
  • When building the file in parts, formatter tooling can prune imports that are only used by later parts — restore the import block at the end.

© overmind-core, AGPL-3.0. 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 .agents/skills/seed-demo-data of overmind-core/overmind.

Open the folder on GitHubat commit 3dec73c

Compare with similar skills

Seed Demo Data 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.

Seed Demo Data compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Seed Demo Data this skillovermind-core/overmind603—~973Automated safety check: PassAGPL-3.0
SEO Intake And Mapmarkfulton/ai-employees498—~24kAutomated safety check: PassMIT
Trigger.dev Agent Patternspapermark/papermark9.2k—~2kAutomated safety check: PassCustom licence
Robust Error Handling In Scriptsaiming-lab/MetaClaw3.5k—~225Automated safety check: PassMIT
ModalK-Dense-AI/scientific-agent-skills48k1 repos~4.5kAutomated safety check: NotesApache-2.0
Openai APIcoco-research/coco503—~7.6kAutomated safety check: NotesCustom licence

Similar skills

  • SEO Intake And Map

    markfulton/ai-employees

    Monthly, browser conditional. An agent skill from markfulton/ai-employees.

    498 GitHub stars~24k tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check passed

  • Trigger.dev Agent Patterns

    papermark/papermark

    Patterns for building LLM agents on Trigger.dev tasks: prompt chaining, routing, parallel workers, orchestrator-workers, evaluator loops and human approval gates.

    9.2k GitHub stars~2k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed

  • Robust Error Handling In Scripts

    aiming-lab/MetaClaw

    A skill your agent uses when writing shell scripts, Python automation, or any unattended batch job.

    3.5k GitHub stars~225 tokensUpdated 4 mo ago
    DevelopmentAuto-check passed

  • Modal

    K-Dense-AI/scientific-agent-skills

    Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs.

    48k GitHub starsUsed in 1 repo~4.5k tokens
    Backend & APIsAuto-check: notes

  • Openai API

    coco-research/coco

    A skill your agent uses when implementing GPT chat, streaming, function calling, embeddings for RAG, images, audio or batch jobs, or troubleshooting 429 rate limits and API or TypeScript errors.

    503 GitHub stars~7.6k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check: notes

  • RAG Skills

    llama-farm/llamafarm

    RAG-specific best practices for LlamaIndex, ChromaDB, and Celery workers.

    836 GitHub stars~1.3k tokensUpdated 4 mo ago
    AI & LLM EngineeringAuto-check passed

More from overmind-core/overmind

All 20 skills in this repo

  • API Endpoints

    overmind-core/overmind

    End-to-end workflow for adding or changing a backend API endpoint — which module the serializer and view belong in, URL registration, OpenAPI client regeneration, and typed consumption from the…

    603 GitHub stars~830 tokensUpdated yesterday
    Auto-check: notes

  • Finetuning Model Onboarding

    overmind-core/overmind

    Rules for adding a new model or model family to the finetuning pipeline, or changing finetuning behavior for an existing one — engine-agnostic customization via family hooks instead of if/else in…

    603 GitHub stars~3.2k tokensUpdated yesterday
    Auto-check passed

  • Frontend Design

    overmind-core/overmind

    Overmind Console design system — semantic tokens, shared primitives, geometry and icons, the border-contrast floor, the duplicated table implementations, and the verification scripts.

    603 GitHub stars~1.8k tokensUpdated yesterday
    Auto-check passed

  • MCP

    overmind-core/overmind

    End-to-end workflow for adding or changing Overmind MCP tools, resources, prompts, authentication, or result contracts — server layers, catalog registration, MCP-impact classification, and required…

    603 GitHub stars~4.3k tokensUpdated yesterday
    Auto-check passed

  • PR Etiquette

    overmind-core/overmind

    How to open a complete pull request on overmind-core/overmind — the CI gates, the cross-cutting surfaces a change must carry with it (MCP, blast radius, the docs repo), gh pr edit being broken here…

    603 GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed

  • Overmind Agent

    overmind-core/overmind

    Inspect an Overmind project's agent map, capabilities, behaviour contracts, repository provenance and evaluation coverage.

    603 GitHub stars~797 tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Seed Demo Data

What does Seed Demo Data do?

Run or modify the seeddemo management command (the one-project Support Copilot demo) without breaking the beat-safety invariants that keep celery workers from re-driving seeded rows. Seed Demo Data is an agent skill from overmind-core/overmind. Run or modify the seeddemo management command (the one-project Support Copilot demo) without breaking the beat-safety invariants that keep celery workers from re-driving seeded rows.

When should I use Seed Demo Data?

Seed Demo Data fits situations like: seeding demo data; editing overbae/management/commands/seeddemo.py.

How do I install Seed Demo Data in Claude Code?

Run `npx skills add overmind-core/overmind --skill seed-demo-data -a claude-code`. Or copy the skill folder (.agents/skills/seed-demo-data in overmind-core/overmind) into .claude/skills/seed-demo-data in your project. Claude Code loads it when a task matches its description.

How do I install Seed Demo Data in Codex?

Run `npx skills add overmind-core/overmind --skill seed-demo-data -a codex`. Or copy the skill folder (.agents/skills/seed-demo-data in overmind-core/overmind) into .agents/skills/seed-demo-data in your project. Codex loads it when a task matches its description.

Can I use Seed Demo Data 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 overmind-core/overmind --skill seed-demo-data -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/seed-demo-data, .gemini/skills/seed-demo-data, .github/skills/seed-demo-data and .opencode/skills/seed-demo-data in your project.

What does Seed Demo Data need to run?

Going by SKILL.md and its folder, Seed Demo Data needs the command-line tools its instructions call (docker). Our summary lists: Python 3; Docker.

Does Seed Demo Data access the network?

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

Is Seed Demo Data 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 Seed Demo Data use?

Seed Demo Data is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Seed Demo Data use?

About 973 tokens (SKILL.md is roughly 3.9k 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 Seed Demo Data?

Skills that share tags, products or a category with Seed Demo Data: SEO Intake And Map (markfulton/ai-employees, 498 stars), Trigger.dev Agent Patterns (papermark/papermark, 9.2k stars), Robust Error Handling In Scripts (aiming-lab/MetaClaw, 3.5k stars) and Modal (K-Dense-AI/scientific-agent-skills, 48k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Seed Demo Data?

overmind-core (a GitHub organization) maintains it in overmind-core/overmind, which has 603 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on October 8, 2026.

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