claude code skill

Teach your agent
to ship for review.
Once.

The Draftmark skill wraps the dm CLI so your coding agent knows the whole loop — publish a plan, share the link, read the feedback, iterate, close the review — without you spelling out a single API call. Install it once; it activates on the right prompts.

# install the skill
$ git clone github.com/draftmark-app/skill
$ cp -r skill/draftmark ~/.claude/skills/draftmark

# then, in your agent
share this migration plan for review
✓ Published to draftmark.app/share/a1b2c3d4
  (ran: dm create plan.md --agent)

# next session
any feedback on the plan yet?
✓ 3 comments — incorporating now
  (ran: dm comments --json)
// how it works
00

Install once

Clone the repo and drop the draftmark/ folder into ~/.claude/skills/ (or a project's .claude/skills/). Restart your agent — the skill is discovered automatically. No per-project setup.

$ git clone github.com/draftmark-app/skill.git
$ cp -r skill/draftmark ~/.claude/skills/draftmark
01

The agent publishes

Ask your agent to "share this plan for review." The skill fires, checks auth with dm whoami, writes the markdown to a file, and runs dm create --agent — then hands you the share link.

share the plan for review
# agent runs:
$ dm create plan.md --agent --json
02

Humans review

Reviewers open the link and leave comments — general or anchored to specific lines — in the browser. Nothing to install on their end. The agent just waits; review is asynchronous.

# draftmark.app/share/a1b2c3d4
alice: section 3 needs a rollback plan
bob: 👍 on the phased cutover
03

The agent reads back

Next session, ask "any feedback yet?" The skill resolves the doc from .draftmark.json, pulls comments as JSON, incorporates them with dm update, and closes the review when it's done.

any feedback on the plan?
# agent runs:
$ dm comments --json | ...
$ dm update revised.md && dm close
// what the skill knows
[›]

Trigger-aware

Activates on the prompts that matter — "share this for review," "get feedback on this draft," "any comments yet?" — and stays out of the way otherwise.

[dm]

Built on the CLI

No new runtime — the skill drives the same dm CLI you can run by hand. Auth, JSON, and exit codes are already solved.

[json]

JSON-first

Reads results with --json and parses structured output — slugs, line-anchored comments, review status — instead of scraping tables.

[0-4]

Gate-aware

Knows the exit codes: 2 auth, 3 not found, 4 conflict (review closed or past deadline). It reports gates instead of retrying blindly.

[↻]

Cross-session

.draftmark.json is the memory between sessions. A fresh session picks up the pending doc and its feedback without you re-pasting a link.

[⚡]

Reviewer mode

When your agent reviews someone else's doc, it comments with --author-type agent and line anchors, so its feedback carries a visible [agent] badge.

[?]

Auth-first

Checks dm whoami before acting and asks for an account key when one is missing — no silent failures, no leaked keys in tracked files.

[url]

Self-host aware

Honors --base-url, so the same skill works against a self-hosted Draftmark instance without any changes.

// prerequisites
the CLI
$ npm install -g draftmark
# the skill drives this binary — see the CLI page
and an account key for private docs
auth
$ dm login --api-key acct_xxxx
# or export DM_API_KEY (public docs work without a key)

One skill.
The whole review loop.

get the skill on GitHubexplore the CLI →