Close out a change to Open Data Capture before committing, opening a PR, or reporting it done.

Apache-2.0Auto-check passedDevelopment

Install Odc Done

skills CLI
$ npx skills add DouglasNeuroInformatics/OpenDataCapture --skill odc-done -a claude-code

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

GitHub CLI
$ gh skill install DouglasNeuroInformatics/OpenDataCapture odc-done --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/DouglasNeuroInformatics/OpenDataCapture.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/odc-done .claude/skills/odc-done && 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
odc-done
GitHub stars
119
Token cost
~1.6k tokens
SKILL.md length
704 words
Files
2
Skills in repo
16
Repo updated
First seen
Licence
Apache-2.0

At a glance

Close out a change to Open Data Capture before committing, opening a PR, or reporting it done.

  • Works in 8 steps: Lint, then read what it rewrote → Test, and make the run name your file → Run the end-to-end suite, or raise the… → …
  • Tasks that involve Pull requests
  • SKILL.md covers 1. Lint, then read what it…, 2. Test, and make the run name…, 3. Run the end-to-end suite,… and 4. Account for both tests, plus 4 more sections
  • Calls pnpm, git and eslint

What it does

Odc Done is an agent skill from DouglasNeuroInformatics/OpenDataCapture. Close out a change to Open Data Capture before committing, opening a PR, or reporting it done. Use also when another skill hands off its close-out, or when asked whether the current uncommitted change is ready to merge — an already-opened PR is review-pr's job.

Its SKILL.md is about 1.6k 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 Pull requests. 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 Pull requests

Example prompts

  • “/odc-done”

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. Lint, then read what it rewrote
  2. Test, and make the run name your file
  3. Run the end-to-end suite, or raise the exception
  4. Account for both tests
  5. Follow the change through its second file
  6. If the diff touched apps/api, sweep every query
  7. Reconcile the AGENTS.md you contradicted
  8. Say what you did not verify

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:

    • pnpm
    • git
    • eslint

    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 Done loads about 1.6k tokens when it runs. Until then it costs about 68 tokens; SKILL.md has 704 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~68
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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 DouglasNeuroInformatics/OpenDataCapture at commit 432dec8, republished under its Apache-2.0 licence (© DouglasNeuroInformatics). 704 words, ~1,560 tokens.

Download SKILL.mdSave it as .claude/skills/odc-done/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
odc-done
description
Close out a change to Open Data Capture before committing, opening a PR, or reporting it done. Use also when another skill hands off its close-out, or when asked whether the current uncommitted change is ready to merge — an already-opened PR is review-pr's job.

If you are still writing code, keep writing — this is the sweep for the moment the change is finished.

Green is not done. Nothing downstream catches what you skip here: .husky/pre-commit only formats the staged files, and CI runs on a pull request to main, which is after this moment (.agents/docs/architecture/testing-strategy.md).

A check you cannot meet is an exception: one line in your reply naming the check and why. Step 8 collects them.

1. Lint, then read what it rewrote

sh
pnpm lint
git status --porcelain

eslint --fix writes to disk, so a green run can hand back a tree it edited. A tree that already conforms comes back untouched; a rewrite appears when your new code disagrees with perfectionist/sort-objects or import/exports-last. Those rewrites are correct — read them and keep them.

A cold run builds every dependency, generates both Prisma clients and pushes the gateway schema (.agents/docs/architecture/testing-strategy.md). Slow is the expected state, not a hang.

Done when pnpm lint exits green and every path git status reports is one whose diff you have read and intend to commit. TS2345 on a route literal you added is the one failure that is correct as it stands — it clears when the user regenerates route-tree.ts, but only if the literal matches its file path character-for-character (.agents/skills/odc-web-route/SKILL.md). Raise it as an exception rather than editing the tree yourself.

2. Test, and make the run name your file

sh
pnpm test:coverage                  # fails below 100% on any metric — see testing-strategy.md §Coverage
pnpm exec vitest list --filesOnly   # a green run prints counts only; this prints the collected files

A test file the listing never names was collected by nothing — .agents/skills/odc-testing/SKILL.md opens on that failure and owns both the diagnosis and the fix.

Done when the run is green at 100% coverage and list --filesOnly names every test file this change added.

3. Run the end-to-end suite, or raise the exception

sh
pnpm test:e2e

Playwright boots apps/api, apps/gateway and apps/web itself. The browsers must be installed once per machine — pnpm --filter @opendatacapture/testing exec playwright install chromium firefox (.agents/docs/playbooks/add-e2e-test.md, which also carries the single-spec and UI-mode invocations for when you are iterating on one failure).

Done when the suite is green, or its exception is in your reply.

4. Account for both tests

Every change needs a unit test and an end-to-end test in testing/ (root AGENTS.md).

Done when you can name the unit test file and the testing/src/specs/ file this change added, or each missing one carries its exception.

Show full SKILL.md (330 more words)Show less

5. Follow the change through its second file

Each row is a pair of files that must agree, where the second is easy to leave unfinished.

You touchedWhat must followOwned by
a file under apps/web/src/routes/route-tree.ts (the user's) and testing/src/generated/route.d.ts.agents/skills/odc-web-route/SKILL.md
a new folder under packages/schemas/srcits subpath in that package's exports — there is no . exportpackages/schemas/AGENTS.md
a new instrument directorythe hand-written import and create call in apps/api/src/demo/demo.service.ts.agents/docs/playbooks/add-instrument.md
a wrapper under vendor/runtime/v1/package.json devDependencies and runtime.config.js.agents/docs/playbooks/add-vendor-package.md
an environment variablethe rest of the chain, in the playbook's order.agents/docs/playbooks/add-env-var.md
a packages/react-core componentsrc/index.ts — the barrel is the public API, there are no deep importspackages/react-core/AGENTS.md
a request or response shape in apps/apicli/odc-cli, which nothing links to the APIcli/AGENTS.md
a new workspace or vitest projectthe tables in workspace-map.md and testing-strategy.md.agents/skills/odc-agent-docs/SKILL.md

Done when every row whose left column matches your diff is either done or carries its exception.

6. If the diff touched apps/api, sweep every query

Open .agents/skills/odc-api/SKILL.md before you sweep — it carries why an omitted ability silently returns an empty where, and how the guard and the where clause divide the work.

Done when every Prisma query in the diff is accounted for — each one either names accessibleQuery in its where, or is unscoped for a reason your reply states — and every handler calling a scoped service forwards @CurrentUser('ability'). Every one, not a sample.

7. Reconcile the AGENTS.md you contradicted

Where the change disagrees with a workspace AGENTS.md, .agents/skills/odc-agent-docs/SKILL.md carries the house format for the edit — open it before you write.

Done when you have opened the AGENTS.md of every workspace in the diff and each one is either consistent with the change or edited in this commit.

8. Say what you did not verify

Some exceptions were never a command: a row in step 5 you took on trust, a behaviour no test exercises.

Done when your reply lists every exception raised above, or states that every check ran green.

© 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-done of DouglasNeuroInformatics/OpenDataCapture.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 432dec8

Compare with similar skills

Odc Done 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.

Odc Done compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Odc Done this skillDouglasNeuroInformatics/OpenDataCapture119—~1.6kAutomated safety check: PassApache-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Iterate PRmeshery/meshery-operator1517 repos~2.2kAutomated safety check: PassApache-2.0
Tabularis Local PR ReviewTabularisDB/tabularis5.1k—~1.4kAutomated safety check: PassApache-2.0
MAUI PR Performance Analysisdotnet/maui23k—~2.4kAutomated safety check: PassMIT
PlotJuggler Ship CheckPlotJuggler/PlotJuggler6.2k—~1.3kAutomated safety check: PassMPL-2.0

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Iterate PR

    meshery/meshery-operator

    Iterate on a PR until CI passes. An agent skill from meshery/meshery-operator.

    151 GitHub starsUsed in 7 repos~2.2k tokens
    DevelopmentAuto-check passed
  • Tabularis Local PR Review

    TabularisDB/tabularis

    Reviews a Tabularis pull request locally, judging the diff against the repo's rule files, verifying every claim in its description against the code, and running its tests on the real branch.

    5.1k GitHub stars~1.4k tokensUpdated today
    DevelopmentAuto-check passed
  • Official

    Interprets pinned managed benchmark evidence for a dotnet/maui pull request and writes a narrative for the performance review workflow, without running or publishing anything.

    23k GitHub stars~2.4k tokensUpdated today
    DevelopmentAuto-check passed
  • PlotJuggler Ship Check

    PlotJuggler/PlotJuggler

    Runs a gated finish-line checklist before committing a PlotJuggler PJ4 change: build proof, red-test triage, hooks, docs freshness and a diff self-review.

    6.2k GitHub stars~1.3k tokensUpdated 8 days ago
    DevelopmentAuto-check passed
  • Review Envoy Gateway PR

    envoyproxy/gateway

    Review an Envoy Gateway pull request for essential API, implementation, status, and test coverage requirements.

    3.1k GitHub stars~850 tokensUpdated today
    DevelopmentAuto-check passed

More from DouglasNeuroInformatics/OpenDataCapture

All 16 skills in this repo
  • Odc 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.

    119 GitHub stars~2.7k tokensUpdated 2 days ago
    Auto-check passed
  • Odc Testing

    DouglasNeuroInformatics/OpenDataCapture

    Test a change in Open Data Capture. An agent skill from DouglasNeuroInformatics/OpenDataCapture.

    119 GitHub stars~1.5k tokensUpdated 2 days ago
    Auto-check: notes
  • Review PR

    DouglasNeuroInformatics/OpenDataCapture

    Triage pull requests against upstream main — one verdict, action items, and whether it needs the user's eyes.

    119 GitHub stars~2.8k tokensUpdated 2 days ago
    Auto-check passed
  • Odc Open PR

    DouglasNeuroInformatics/OpenDataCapture

    Open a pull request against main for the current branch. An agent skill from DouglasNeuroInformatics/OpenDataCapture.

    119 GitHub stars~533 tokensUpdated 2 days ago
    Auto-check passed
  • Opening Issues

    DouglasNeuroInformatics/OpenDataCapture

    File a GitHub issue for Open Data Capture with its labels. An agent skill from DouglasNeuroInformatics/OpenDataCapture.

    119 GitHub stars~614 tokensUpdated 2 days ago
    Auto-check passed
  • 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…

    119 GitHub stars~2.8k tokensUpdated 2 days ago
    Auto-check: notes

Questions about Odc Done

What does Odc Done do?

Close out a change to Open Data Capture before committing, opening a PR, or reporting it done. Odc Done is an agent skill from DouglasNeuroInformatics/OpenDataCapture. Close out a change to Open Data Capture before committing, opening a PR, or reporting it done.

When should I use Odc Done?

Odc Done fits situations like: tasks that involve Pull requests.

How do I install Odc Done in Claude Code?

Run `npx skills add DouglasNeuroInformatics/OpenDataCapture --skill odc-done -a claude-code`. Or copy the skill folder (.agents/skills/odc-done in DouglasNeuroInformatics/OpenDataCapture) into .claude/skills/odc-done in your project. Claude Code loads it when a task matches its description.

How do I install Odc Done in Codex?

Run `npx skills add DouglasNeuroInformatics/OpenDataCapture --skill odc-done -a codex`. Or copy the skill folder (.agents/skills/odc-done in DouglasNeuroInformatics/OpenDataCapture) into .agents/skills/odc-done in your project. Codex loads it when a task matches its description.

Can I use Odc Done 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-done -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-done, .gemini/skills/odc-done, .github/skills/odc-done and .opencode/skills/odc-done in your project.

What does Odc Done need to run?

Going by SKILL.md and its folder, Odc Done needs the command-line tools its instructions call (pnpm, git and eslint).

Does Odc Done 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 Done 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 Odc Done use?

Odc Done 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 Done use?

About 1.6k tokens (SKILL.md is roughly 6.2k 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 Done?

Skills that share tags, products or a category with Odc Done: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Iterate PR (meshery/meshery-operator, 151 stars), Tabularis Local PR Review (TabularisDB/tabularis, 5.1k stars) and MAUI PR Performance Analysis (dotnet/maui, 23k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Odc Done?

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.