Adk Setup
google/adk-python
Sets up a local ADK Python development environment in a git clone of the open-source adk-python repository: a uv virtual environment, all dependency extras, pre-commit hooks, and a first unit-test…
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…
Install Odc Debugging
$ npx skills add DouglasNeuroInformatics/OpenDataCapture --skill odc-debugging -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install DouglasNeuroInformatics/OpenDataCapture odc-debugging --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-debugging .claude/skills/odc-debugging && 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-debugging" agent skill from https://github.com/DouglasNeuroInformatics/OpenDataCapture/tree/main/.agents/skills/odc-debugging into .claude/skills/odc-debugging/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "odc-debugging", 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-debuggingType 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-debugging -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install DouglasNeuroInformatics/OpenDataCapture odc-debugging --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-debugging .agents/skills/odc-debugging && 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-debugging" agent skill from https://github.com/DouglasNeuroInformatics/OpenDataCapture/tree/main/.agents/skills/odc-debugging into .agents/skills/odc-debugging/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "odc-debugging", 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-debugging -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install DouglasNeuroInformatics/OpenDataCapture odc-debugging --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-debugging .cursor/skills/odc-debugging && 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-debugging" agent skill from https://github.com/DouglasNeuroInformatics/OpenDataCapture/tree/main/.agents/skills/odc-debugging into .cursor/skills/odc-debugging/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "odc-debugging", 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-debugging--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-debugging -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install DouglasNeuroInformatics/OpenDataCapture odc-debugging --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-debugging .gemini/skills/odc-debugging && 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-debugging" agent skill from https://github.com/DouglasNeuroInformatics/OpenDataCapture/tree/main/.agents/skills/odc-debugging into .gemini/skills/odc-debugging/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "odc-debugging", 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-debuggingInstalls 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-debugging -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-debugging .github/skills/odc-debugging && 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-debugging" agent skill from https://github.com/DouglasNeuroInformatics/OpenDataCapture/tree/main/.agents/skills/odc-debugging into .github/skills/odc-debugging/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "odc-debugging", 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-debugging -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-debugging --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-debugging .opencode/skills/odc-debugging && 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-debugging" agent skill from https://github.com/DouglasNeuroInformatics/OpenDataCapture/tree/main/.agents/skills/odc-debugging into .opencode/skills/odc-debugging/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "odc-debugging", 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-debugging- GitHub stars
- 119
- Token cost
- ~2.8k tokens
- SKILL.md length
- 1,162 words
- Files
- 2
- Skills in repo
- 16
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
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…
- Tasks that involve Debugging
- SKILL.md covers Loud and correct, Quiet and wrong, Which database is under the… and When no row matches
- Calls pnpm, git and eslint
- Tasks that involve Linting and formatting
What it does
Odc Debugging is an agent skill from 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 naming runtime/v1, btoa or turbo. Read before diagnosing; systematic-debugging and diagnosing-bugs supply the method, this supplies what is wrong here.
Its SKILL.md is about 2.8k 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 Development, covering Debugging, Linting and formatting and Unit testing. It works with Vite. 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 Debugging
- Tasks that involve Linting and formatting
- Tasks that involve Unit testing
Example prompts
- “/odc-debugging”
What it can do on your machine
Read from SKILL.md and the folder at commit c7a6364. 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:
pnpmgiteslint
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 git, 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
Odc Debugging loads about 2.8k tokens when it runs. Until then it costs about 90 tokens; SKILL.md has 1,162 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:38
reports unresolved modules instead. `.env` is gitignored too and every root script is `env-cmd`-wrapped, so a clone - NoteMentions a .env fileSKILL.md:39
ails earlier still, with `Failed to find .env file at default paths`. Both are - NoteMentions a .env fileSKILL.md:65
| A variable that is present in `.env` is undefined inside a task | Turbo runs strict env mode: a task sees `g
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 c7a6364, republished under its Apache-2.0 licence (© DouglasNeuroInformatics). 1,162 words, ~2,780 tokens.
Download SKILL.mdSave it as
.claude/skills/odc-debugging/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- odc-debugging
- description
- 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 naming runtime/v1, btoa or turbo. Read before diagnosing; systematic-debugging and diagnosing-bugs supply the method, this supplies what is wrong here.
Failures in this repo sort into two piles that want opposite reactions.
Loud and correct — a command failed, and the failure is the repo working as designed. Name it as designed behaviour, leave it standing, and carry on with the change it interrupted. The whole answer here is the explanation plus, at most, a change to your own uncommitted work — the configs, CI and docs stay as they are.
Quiet and wrong — nothing failed, and that is the symptom: the test never ran, the query returned every group's rows, the story is not in Storybook, the instrument was never loaded. These are the expensive ones, because the signal that would have caught them is the signal you are trusting.
Done when the symptom has been read against both piles, and you have either opened the owner named by the matching row or can say that no row matches.
Loud and correct
TS2345 on a route file you just wrote.
error TS2345: Argument of type '"/_app/your-route"' is not assignable to parameter of type 'keyof FileRoutesByPath | undefined'.The expected state of a correct new route until the user regenerates route-tree.ts —
.agents/skills/odc-web-route/SKILL.md. There is no generator command to avoid: every Vite run in apps/web
(pnpm dev, dev:test, the Playwright webServer, vite build) rewrites that tracked file from configResolved, so
when git status shows route-tree.ts after a debugging run, revert it and leave the regeneration to the user.
pnpm lint came back green and the working tree moved. Lint is eslint --fix, so it rewrites while it checks, and
a tree that already conforms comes back untouched — the rewrites in front of you are your own new code being sorted.
Read that diff as your work and keep it.
A fresh checkout fails in places that never name the cause. runtime/v1/dist is gitignored and unbuilt, so a dev
server dies with ENOENT while a Vite config is still resolving, and every consumer whose tsconfig maps /runtime/v1/*
reports unresolved modules instead. .env is gitignored too and every root script is env-cmd-wrapped, so a clone
that has never been set up fails earlier still, with Failed to find .env file at default paths. Both are
prerequisites rather than bugs: .agents/skills/odc-run-locally/SKILL.md. Turbo repairs the build for you; anything
run outside turbo — a bare tsc, vitest, storybook — does not.
Some breakage is known, documented, and deliberately left alone. Before calling anything a new bug, read the
AGENTS.md of the package that owns it — that is where these are recorded (the always-skipped development block in
packages/release-info), with the build- and test-infrastructure ones in the Known warts section of
.agents/docs/architecture/testing-strategy.md. Name any you hit in your reply and leave it as it is.
Quiet and wrong
Read the owner before changing anything: the row tells you where you are, not what to type.
| Symptom | Cause | Owner |
|---|---|---|
A new unit test passes; pnpm test output never names its file | The package has no vitest.config.ts, and the root config globs only apps/*, packages/* and runtime/* | .agents/skills/odc-testing/SKILL.md |
A type error survives pnpm lint and CI | Lint is the only type-check, and runtime/v1 has no lint script while instrument-stubs and instrument-guidelines run eslint with no tsc | .agents/docs/architecture/testing-strategy.md |
| An endpoint returns rows belonging to every group | accessibleQuery(undefined, …) returns {}; an omitted ability is caught by neither tsc, nor eslint, nor a green suite | .agents/skills/odc-api/SKILL.md |
| A new route is reachable by any authenticated user | @RouteAccess([]) passes because [].every(...) is true — a handler with no decorator 500s instead of opening | .agents/skills/odc-api/SKILL.md |
| A route 500s inside the validation pipe the first time it is called | The $Schema used as the @Body() parameter type arrived through import type, which erases the runtime binding | .agents/skills/odc-api/SKILL.md |
| Two apparently identical schemas reject each other; error maps miss | A bare zod import resolves to the vendored v3, a separate registry from zod/v4 | packages/schemas/AGENTS.md |
| An instrument builds and is listed, but no instance has it | apps/api/src/demo/demo.service.ts holds one hand-written import per instrument | .agents/skills/odc-instruments/SKILL.md |
| The runtime build logged an error and the command still succeeded | runtime-bundler's CLI catches a bundle failure, prints it, and exits 0 | packages/runtime-bundler/AGENTS.md |
| A route literal a Playwright spec uses does not type-check | testing/src/generated/route.d.ts is git-ignored and rewritten by gen:routes from route-tree.ts | .agents/skills/odc-web-route/SKILL.md |
| A spec has no authentication and every fixture is undefined | It imported test from @playwright/test rather than ../support/fixtures | .agents/skills/odc-testing/SKILL.md |
| An e2e test passes alone and fails inside the suite | One database, shared by every worker, with fullyParallel on — fixed names collide | .agents/skills/odc-testing/SKILL.md |
A variable that is present in .env is undefined inside a task | Turbo runs strict env mode: a task sees globalEnv (NODE_ENV, NODE_OPTIONS) plus its own env array and nothing else | .agents/docs/playbooks/add-env-var.md |
| A gateway change does nothing, and hydration disagrees with the SSR | pnpm dev disposes the esbuild watcher immediately and SSR loads from its output; only Vite-middleware assets refresh | apps/gateway/AGENTS.md |
A gateway page 500s from rootLoader; the same content renders elsewhere | RootProps is serialized with btoa, which throws above U+00FF — one curly quote anywhere in the bundle is enough | apps/gateway/AGENTS.md |
| A playground instrument you added is missing, or an edit vanished | The store persists to IndexedDB via idb-keyval, and its merge keeps only instruments whose category is Saved | apps/playground/AGENTS.md |
| A story never appears in Storybook | storybook/config/main.ts enumerates its story directories explicitly; anything outside them is invisible | .agents/skills/odc-frontend/SKILL.md |
| Keyed translations fail to type-check, or render as nothing | A namespace takes three separate edits in apps/web/src/services/i18n.ts; apps/gateway has no resource files at all | .agents/skills/odc-frontend/SKILL.md |
| A route file resolves to a URL nobody asked for | A . in a filename under src/routes/ is a path separator, not part of the name | .agents/skills/odc-web-route/SKILL.md |
toBeInTheDocument is not a function | @testing-library/jest-dom is not installed anywhere in the repo | .agents/docs/architecture/testing-strategy.md |
odc-cli rejects a value the API accepts | cli/odc-cli has no generated client and no compile-time link to packages/schemas, so API drift reaches it silently | cli/AGENTS.md |
| A token keeps working after its permissions changed, and never expires | Permissions are frozen into the JWT at login with no refresh endpoint, and JwtStrategy ignores expiry in development | .agents/docs/architecture/auth-and-permissions.md |
Show full SKILL.md (187 more words)Show less
Which database is under the failure
A bug that reproduces in one environment and not the other is usually about the database rather than the code. What
each environment is — an in-memory replica set under NODE_ENV=test, a real Mongo otherwise — and what POST /v1/setup
destroys are in .agents/skills/odc-run-locally/SKILL.md; why no unit test can see a row is in
.agents/skills/odc-testing/SKILL.md. Two consequences those two do not draw:
- Contents. The e2e database is seeded once through the UI by
testing/src/global/setup.spec.tsand dropped byteardown.spec.ts. Nothing resets a development database automatically, so it holds whatever was last put there. NODE_ENVitself changes behaviour, which makes an environment-dependent bug a candidate before the code is — JWT expiry is ignored in development only (.agents/docs/architecture/auth-and-permissions.md).
When no row matches
Fall back to the method: .agents/skills/systematic-debugging/SKILL.md. Reproduce it, find the root cause, then fix
that — a symptom fix in this codebase usually just moves the silence somewhere else.
Done when the fact you needed and could not find has landed in a repo document — .agents/skills/odc-agent-docs/SKILL.md
decides which one, and this file is a candidate — or you can name the document that already carries it.
© 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-debugging of DouglasNeuroInformatics/OpenDataCapture.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit c7a6364
Compare with similar skills
Odc Debugging 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 Debugging this skillDouglasNeuroInformatics/OpenDataCapture | 119 | — | ~2.8k | Automated safety check: Notes | Apache-2.0 | |
| Adk Setupgoogle/adk-python | 22k | — | ~993 | Automated safety check: Notes | Apache-2.0 | |
| Vite Plus ConventionsGoldziher/ai-rulez | 153 | — | ~567 | Automated safety check: Pass | MIT | |
| Chrome Devtools MCPmanagedcode/dotnet-skills | 486 | — | ~2.2k | Automated safety check: Pass | MIT | |
| Code Completionfacioquo/stock-indicators-dotnet | 1.2k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| Pierre Testing and Verification Guidepierrecomputer/pierre | 6.2k | — | ~608 | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Vite Plus Conventions
Goldziher/ai-rulez
vite+ unified TypeScript toolchain conventions: the vp CLI for package/node management, oxlint/oxfmt, type-aware linting, vitest, rolldown/tsdown bundling, task caching, and migration.
Chrome Devtools MCP
managedcode/dotnet-skills
Use Chrome DevTools MCP from .NET agents and .NET-focused repos to inspect, debug, and automate Chrome through an MCP client.
Code Completion
facioquo/stock-indicators-dotnet
Quality gates for finishing work in this repository — dead-code cleanup, Roslynator and dotnet format fixes, markdownlint, build, unit tests, documentation, and Obsolete migration shims — with the…
Pierre Testing and Verification Guide
pierrecomputer/pierre
Chooses the right verification step after a code change in Pierre's monorepo: format and lint, a typecheck, Bun unit tests, snapshots, or Playwright E2E.
Ha Frontend Testing
home-assistant/frontend
Home Assistant frontend testing and validation workflow. An agent skill from home-assistant/frontend.
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 Done
DouglasNeuroInformatics/OpenDataCapture
Close out a change to Open Data Capture before committing, opening a PR, or reporting it done.
Related
Works with
Categories
Questions about Odc Debugging
What does Odc Debugging do?
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…. Odc Debugging is an agent skill from 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 naming runtime/v1, btoa or turbo.
When should I use Odc Debugging?
Odc Debugging fits situations like: tasks that involve Debugging; tasks that involve Linting and formatting; tasks that involve Unit testing.
How do I install Odc Debugging in Claude Code?
Run `npx skills add DouglasNeuroInformatics/OpenDataCapture --skill odc-debugging -a claude-code`. Or copy the skill folder (.agents/skills/odc-debugging in DouglasNeuroInformatics/OpenDataCapture) into .claude/skills/odc-debugging in your project. Claude Code loads it when a task matches its description.
How do I install Odc Debugging in Codex?
Run `npx skills add DouglasNeuroInformatics/OpenDataCapture --skill odc-debugging -a codex`. Or copy the skill folder (.agents/skills/odc-debugging in DouglasNeuroInformatics/OpenDataCapture) into .agents/skills/odc-debugging in your project. Codex loads it when a task matches its description.
Can I use Odc Debugging 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-debugging -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-debugging, .gemini/skills/odc-debugging, .github/skills/odc-debugging and .opencode/skills/odc-debugging in your project.
What does Odc Debugging need to run?
Going by SKILL.md and its folder, Odc Debugging needs the command-line tools its instructions call (pnpm, git and eslint).
Does Odc Debugging access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Odc Debugging 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 Debugging use?
Odc Debugging 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 Debugging use?
About 2.8k tokens (SKILL.md is roughly 11k 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 Debugging?
Skills that share tags, products or a category with Odc Debugging: Adk Setup (google/adk-python, 22k stars), Vite Plus Conventions (Goldziher/ai-rulez, 153 stars), Chrome Devtools MCP (managedcode/dotnet-skills, 486 stars) and Code Completion (facioquo/stock-indicators-dotnet, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Odc Debugging?
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.