Ds Figma Handover
mqtt-viewer/mqtt-viewer
Diff the Figma component library against the MQTT Viewer frontend and produce a handover doc listing exactly what code needs to change.
Bring the Open Data Capture stack up on this machine — pnpm dev (api, gateway, web), a fresh clone from zero, the standalone playground, storybook or outreach dev servers, or a local instance with…
Install Odc Run Locally
$ npx skills add DouglasNeuroInformatics/OpenDataCapture --skill odc-run-locally -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install DouglasNeuroInformatics/OpenDataCapture odc-run-locally --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/DouglasNeuroInformatics/OpenDataCapture.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/odc-run-locally .claude/skills/odc-run-locally && rm -rf skills-srcUse ~/.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/
Install the "odc-run-locally" agent skill from https://github.com/DouglasNeuroInformatics/OpenDataCapture/tree/main/.agents/skills/odc-run-locally into .claude/skills/odc-run-locally/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "odc-run-locally", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/DouglasNeuroInformatics/OpenDataCapture/tree/main/.agents/skills/odc-run-locallyType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add DouglasNeuroInformatics/OpenDataCapture --skill odc-run-locally -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install DouglasNeuroInformatics/OpenDataCapture odc-run-locally --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DouglasNeuroInformatics/OpenDataCapture.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/odc-run-locally .agents/skills/odc-run-locally && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "odc-run-locally" agent skill from https://github.com/DouglasNeuroInformatics/OpenDataCapture/tree/main/.agents/skills/odc-run-locally into .agents/skills/odc-run-locally/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "odc-run-locally", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add DouglasNeuroInformatics/OpenDataCapture --skill odc-run-locally -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install DouglasNeuroInformatics/OpenDataCapture odc-run-locally --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DouglasNeuroInformatics/OpenDataCapture.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/odc-run-locally .cursor/skills/odc-run-locally && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "odc-run-locally" agent skill from https://github.com/DouglasNeuroInformatics/OpenDataCapture/tree/main/.agents/skills/odc-run-locally into .cursor/skills/odc-run-locally/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "odc-run-locally", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/DouglasNeuroInformatics/OpenDataCapture.git --path .agents/skills/odc-run-locally--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add DouglasNeuroInformatics/OpenDataCapture --skill odc-run-locally -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install DouglasNeuroInformatics/OpenDataCapture odc-run-locally --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DouglasNeuroInformatics/OpenDataCapture.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/odc-run-locally .gemini/skills/odc-run-locally && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "odc-run-locally" agent skill from https://github.com/DouglasNeuroInformatics/OpenDataCapture/tree/main/.agents/skills/odc-run-locally into .gemini/skills/odc-run-locally/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "odc-run-locally", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install DouglasNeuroInformatics/OpenDataCapture odc-run-locallyInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add DouglasNeuroInformatics/OpenDataCapture --skill odc-run-locally -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/DouglasNeuroInformatics/OpenDataCapture.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/odc-run-locally .github/skills/odc-run-locally && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "odc-run-locally" agent skill from https://github.com/DouglasNeuroInformatics/OpenDataCapture/tree/main/.agents/skills/odc-run-locally into .github/skills/odc-run-locally/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "odc-run-locally", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add DouglasNeuroInformatics/OpenDataCapture --skill odc-run-locally -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install DouglasNeuroInformatics/OpenDataCapture odc-run-locally --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DouglasNeuroInformatics/OpenDataCapture.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/odc-run-locally .opencode/skills/odc-run-locally && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "odc-run-locally" agent skill from https://github.com/DouglasNeuroInformatics/OpenDataCapture/tree/main/.agents/skills/odc-run-locally into .opencode/skills/odc-run-locally/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "odc-run-locally", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
odc-run-locally- GitHub stars
- 119
- Token cost
- ~1k tokens
- SKILL.md length
- 474 words
- Files
- 2
- Skills in repo
- 16
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Bring the Open Data Capture stack up on this machine — pnpm dev (api, gateway, web), a fresh clone from zero, the standalone playground, storybook or outreach dev servers, or a local instance with…
- Tasks that involve Microservices
- SKILL.md covers The four prerequisites, in…, Then follow the playbook and Getting data into a local…
- Calls pnpm and curl; needs SECRET_KEY
What it does
Odc Run Locally is an agent skill from DouglasNeuroInformatics/OpenDataCapture. Bring the Open Data Capture stack up on this machine — pnpm dev (api, gateway, web), a fresh clone from zero, the standalone playground, storybook or outreach dev servers, or a local instance with data in it. Use also when a dev server dies at startup, or the browser gets ECONNREFUSED from the api.
Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It sits in Frontend & Design, covering Microservices. It works with pnpm and Storybook. The repository describes itself as: An electronic data capture platform for administering remote and in-person clinical instruments. The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Microservices
Example prompts
- “/odc-run-locally”
Requirements
- Docker
- A credential in SECRET_KEY
What it can do on your machine
Read from SKILL.md and the folder at commit 432dec8. 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:
pnpmcurl
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pnpm and 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:
SECRET_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Odc Run Locally loads about 1k tokens when it runs. Until then it costs about 79 tokens; SKILL.md has 474 words of instructions outside code blocks.
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: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NoteMentions a .env fileSKILL.md:12
**1. `.env` exists — and `pnpm generate:env` is a first-clone command only.** It rewrites `.env` - NoteMentions a .env fileSKILL.md:19
generated `.env` points it at `http://localhost:9000`, where nothing listens, and
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 DouglasNeuroInformatics/OpenDataCapture at commit 432dec8, republished under its Apache-2.0 licence (© DouglasNeuroInformatics). 474 words, ~1,020 tokens.
Download SKILL.mdSave it as
.claude/skills/odc-run-locally/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- odc-run-locally
- description
- Bring the Open Data Capture stack up on this machine — `pnpm dev` (api, gateway, web), a fresh clone from zero, the standalone playground, storybook or outreach dev servers, or a local instance with data in it. Use also when a dev server dies at startup, or the browser gets ECONNREFUSED from the api.
Four things have to be true before a dev server serves anything, and each one fails as a decoy — the thing you are looking at is not the thing that is wrong. Check all four before debugging a startup crash.
The four prerequisites, in dependency order
1. .env exists — and pnpm generate:env is a first-clone command only. It rewrites .env
wholesale with fresh secrets, so on a clone that already works, hand-add the one line you need
instead (playbook step 3; a genuinely new variable is .agents/docs/playbooks/add-env-var.md). The
decoy is the logout you notice — the fresh SECRET_KEY also orphans every stored instrument-repo
credential, and those fail silently, later.
2. STORAGE_ENABLED=false, unless an S3-compatible service really is listening. A freshly
generated .env points it at http://localhost:9000, where nothing listens, and
StorageService.onModuleInit kills the api during boot (playbook step 4). The decoy is what turbo
prints: the api takes its two sibling dev servers down with it, so the run ends in
ERROR run failed over a nested connect ECONNREFUSED ::1:9000 that never says the word storage.
3. pnpm build has run at least once. A dev server started before that build dies while its
Vite config is still resolving (playbook step 7). The crash does name the path — ENOENT: no such file or directory, scandir '<repo>/runtime/v1/dist', from generateManifest in
packages/runtime-meta/src/index.js — but it is raised inside a plugin factory, so the decoy is a
Vite configuration error. Confirm runtime/v1/dist exists before chasing one. Turbo repairs this
for you; anything started outside turbo does not.
4. Development talks to a real Mongo replica set. Only NODE_ENV=test gets an in-memory one
(apps/api/src/core/prisma.ts; playbook step 5 starts the real one and initiates it). The decoy is
a green pnpm test:e2e: it passes on a machine with no MongoDB installed at all, and proves nothing
about whether pnpm dev can connect.
Show full SKILL.md (169 more words)Show less
Then follow the playbook
.agents/docs/playbooks/run-locally.md is the ordered procedure — open it and work it end to end.
playground, storybook and outreach are each started on their own; its closing table carries the
command and port for each.
| Branch | Done when |
|---|---|
pnpm dev, a fresh clone | every command in the playbook's ## Verify block has run and returned the documented result — reading rs.status().ok through a host mongosh if Mongo is not in Docker |
| a standalone app | the port it logged answers, and its first page renders |
| an instance with data | curl -s http://localhost:5500/v1/setup reports "isSetup":true |
Getting data into a local instance
There is no seed script. The setup screen (POST /v1/setup) is the only way to get a populated
instance in one shot, and it drops the database first — so reaching for it to clear a stuck login on
a development instance takes every record with it. Everything else arrives one record at a time
through the api's ordinary create endpoints. Playbook step 9 has the mechanism and the
deliberate-reset commands.
© DouglasNeuroInformatics, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in .agents/skills/odc-run-locally of DouglasNeuroInformatics/OpenDataCapture.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit 432dec8
Compare with similar skills
Odc Run Locally 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Odc Run Locally this skillDouglasNeuroInformatics/OpenDataCapture | 119 | — | ~1k | Automated safety check: Notes | Apache-2.0 | |
| Ds Figma Handovermqtt-viewer/mqtt-viewer | 134 | — | ~990 | Automated safety check: Pass | GPL-3.0 | |
| Ds Implement Handovermqtt-viewer/mqtt-viewer | 134 | — | ~853 | Automated safety check: Pass | GPL-3.0 | |
| Stories Componentinkline/inkline | 1.5k | — | ~1.1k | Automated safety check: Notes | None | |
| System Designopenxlings/xlings | 615 | 1 repos | ~328 | Automated safety check: Pass | Apache-2.0 | |
| Verifytheopenco/llmgateway | 1.7k | — | ~1k | Automated safety check: Pass | Custom licence |
Similar skills
Ds Implement Handover
mqtt-viewer/mqtt-viewer
Implement a Figma→code handover doc — apply the listed changes to Svelte components, update their colocated .spec.json and stories, and get pnpm ds:validate green.
Stories Component
inkline/inkline
Phase 3 of building an Inkline component — author single-source Storybook stories.
System Design
openxlings/xlings
Design systems, services, and architectures. An agent skill from openxlings/xlings.
Verify
theopenco/llmgateway
Build, launch, and drive the LLM Gateway stack in an isolated worktree environment to verify API, gateway, dashboard, playground, or screenshot changes.
Aholo Viewer Example Content
manycoretech/aholo-viewer
Owns the paired JSON metadata and TypeScript runner files that define the Aholo Viewer's example and Playground content.
More from DouglasNeuroInformatics/OpenDataCapture
All 16 skills in this repoOdc Agent Docs
DouglasNeuroInformatics/OpenDataCapture
Write or correct this repo's agent documentation — a workspace AGENTS.md (or its CLAUDE.md symlink), a playbook under .agents/docs/playbooks, an architecture doc, or the workspace map.
Odc Testing
DouglasNeuroInformatics/OpenDataCapture
Test a change in Open Data Capture. An agent skill from DouglasNeuroInformatics/OpenDataCapture.
Review PR
DouglasNeuroInformatics/OpenDataCapture
Triage pull requests against upstream main — one verdict, action items, and whether it needs the user's eyes.
Odc Open PR
DouglasNeuroInformatics/OpenDataCapture
Open a pull request against main for the current branch. An agent skill from DouglasNeuroInformatics/OpenDataCapture.
Opening Issues
DouglasNeuroInformatics/OpenDataCapture
File a GitHub issue for Open Data Capture with its labels. An agent skill from DouglasNeuroInformatics/OpenDataCapture.
Odc Debugging
DouglasNeuroInformatics/OpenDataCapture
What actually breaks in Open Data Capture — a failing build, lint, unit test or e2e run; a change with no visible effect; a suite that stays green after you broke the code on purpose; an error…
Related
Categories
Questions about Odc Run Locally
What does Odc Run Locally do?
Bring the Open Data Capture stack up on this machine — pnpm dev (api, gateway, web), a fresh clone from zero, the standalone playground, storybook or outreach dev servers, or a local instance with…. Odc Run Locally is an agent skill from DouglasNeuroInformatics/OpenDataCapture. Bring the Open Data Capture stack up on this machine — pnpm dev (api, gateway, web), a fresh clone from zero, the standalone playground, storybook or outreach dev servers, or a local instance with data in it.
When should I use Odc Run Locally?
Odc Run Locally fits situations like: tasks that involve Microservices.
How do I install Odc Run Locally in Claude Code?
Run `npx skills add DouglasNeuroInformatics/OpenDataCapture --skill odc-run-locally -a claude-code`. Or copy the skill folder (.agents/skills/odc-run-locally in DouglasNeuroInformatics/OpenDataCapture) into .claude/skills/odc-run-locally in your project. Claude Code loads it when a task matches its description.
How do I install Odc Run Locally in Codex?
Run `npx skills add DouglasNeuroInformatics/OpenDataCapture --skill odc-run-locally -a codex`. Or copy the skill folder (.agents/skills/odc-run-locally in DouglasNeuroInformatics/OpenDataCapture) into .agents/skills/odc-run-locally in your project. Codex loads it when a task matches its description.
Can I use Odc Run Locally 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 DouglasNeuroInformatics/OpenDataCapture --skill odc-run-locally -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/odc-run-locally, .gemini/skills/odc-run-locally, .github/skills/odc-run-locally and .opencode/skills/odc-run-locally in your project.
What does Odc Run Locally need to run?
Going by SKILL.md and its folder, Odc Run Locally needs the command-line tools its instructions call (pnpm and curl) and credentials named SECRET_KEY. Our summary lists: Docker; A credential in SECRET_KEY.
Does Odc Run Locally 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 Odc Run Locally safe to install?
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Odc Run Locally use?
Odc Run Locally is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Odc Run Locally use?
About 1k tokens (SKILL.md is roughly 4.1k 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 Odc Run Locally?
Skills that share tags, products or a category with Odc Run Locally: Ds Figma Handover (mqtt-viewer/mqtt-viewer, 134 stars), Ds Implement Handover (mqtt-viewer/mqtt-viewer, 134 stars), Stories Component (inkline/inkline, 1.5k stars) and System Design (openxlings/xlings, 615 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Odc Run Locally?
DouglasNeuroInformatics (a GitHub organization) maintains it in DouglasNeuroInformatics/OpenDataCapture, which has 119 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on October 7, 2026.
Source: DouglasNeuroInformatics/OpenDataCapture on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.