review
Get a person's review of an artifact you produced or were handed: a plan, spec, report or other Markdown file.
Skill by spacedock-dev
Chalk Labs
Need help deploying review?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/spacedock-dev-review
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, frontend, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/review
What's inside
- Skill name
review- Description
- Get a person's review of an artifact you produced or were handed: a plan, spec, report or other Markdown file. Use when you have a file that someone should read and react to before work continues, or when the user asks to send something for review. Picks the Terminal (TUI) or the Web from this project's recorded choice and never uploads without it. With no argument it shows or changes that choice; tui or web records it; a file path is reviewed; any other text is a prompt to carry out first.
- License
- Apache-2.0
- Instructions
- 138 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Review an artifact Hand one artifact to a person for review. The project's recorded choice decides the view and where the file goes. Never upload anything that the project has not agreed to upload. The two choices, worded as the view first, then where the file goes. Use these words whenever you show or ask for the choice: ```text Terminal (TUI): the file stays on this machine Web: uploads to review.spacedock.md; anyone with the link can open it ``` The commands record Terminal (TUI) as `local` and Web as `remote`. If `spacedock review-mode` is an unknown command, spacedock is too old for this skill and has no `update` command. Tell the user to update it: `brew upgrade spacedock` on Homebrew, or run the install line again. Stop. ## Asking the user Each question below is asked through the harness's question tool when it has one (Claude Code: AskUserQuestion; if its schema is not loaded, load it with ToolSearch first), as one menu with the options named. Where there is no such tool, ask in plain text with the same options. Wait for the answer; record only what the user chose, never your guess. ## Pick the branch from the argument For every natural-language review request, first run `spacedock review-mode get --json`, including same-conversation follow-ups; a previous turn's read does not satisfy this step. "Spacedock Review" names the product, never Web. Saved Terminal uses Terminal, saved Web uses Web, and nothing saved runs **Ask for the choice**. Only explicit Web words (`web`, `browser`, `upload`, `share link`, `review.spacedock.md`) select Web for one review. Review the named existing file with the requested modifier, such as `decision`; do not generate a replacement artifact. This does not change the argument branches below or the four file review keyword forms. Take the first branch that fits. Compare the reserved words as the whole argument, ignoring case. 1. No argument: do **Show or change the choice** and nothing else. 2. `tui`, `terminal` or `local`: run `spacedock review-mode set local`, say that Terminal (TUI) is recorded for this project, and end with the sentence about changing it (**Ask for the choice**, step 4). Open and upload nothing. 3. `web`, `webui` or `remote`: do **Ask for the choice** from step 3. Open and upload nothing. 4. An argument that names an existing file (`test -f`), removing enclosing quotes if present: do **Review the file**. Test the whole path before parsing keywords. 5. An existing file followed by review keywords: do **File review keywords**. 6. Any other text is a prompt: do **Carry out the prompt, then review**. ## File review keywords Recognize these four forms before treating text as a prompt. Read trailing keywords from the right; the remainder is the existing file path. Keywords ignore case; preserve the path exactly. Quoted paths such as `"plans/launch plan.md"` are one locator: quote the path when testing it and handing it on, never evaluate it as code. | Argument | Hand-off | |---|---| | `<file> terminal decision` | Terminal once, `subspace:r` with `--mode binding` | | `<file> web decision` | Web once, `subspace:remote-review`, wait for the owner's decision | | `<file> decision` | Saved choice or the existing ask-and-save flow; binding on Terminal, owner's decision on Web | | `<file> terminal questions` | Terminal once, `subspace:r` with `--allow-question` | Refuse `decision` together with `questions`, in either order: the installed Subspace supports questions only for feedback, not binding decisions. Refuse Web with `questions`, with or without `decision`: Web questions are unsupported. Retain both requested intents in the explanation; do not drop one or substitute another location. Refuse any other suffix only when the first word after the file is a location or modifier word (`tui`, `terminal`, `local`, `web`, `webui`, `remote`, `decision`, `questions`) and the whole request is not one of the four forms. The four suffixes in the table are exact: a location alone after the file (`terminal`, `tui`, `local`, `web`, `webui` or `remote`) is refused. Do not reinterpret it as a bare-file review or infer an omitted modifier. Give corrected requests only from the table, one per retained intent (so `decision` with `questions` may offer both halves), each on its own line; use the actual path, quoting it if needed, for example `/spacedock:review plan.md terminal decision`. Explain the refused words without repeating the refused command. Refusals open, upload and generate nothing. Every other text keeps the prompt branch, including `plan.md summarize this file into summary.md`. For a valid form, **Review the file** with its location and modifier. An explicit location applies only to this review: never set, clear, or temporarily change the saved choice. An omitted location keeps the existing ask-and-save flow. ## Ask for the choice Used whenever a choice is needed. 1. Ask "Terminal (TUI) or Web?" with two options, Terminal (TUI) and Web, each described by its line above. Say the answer is remembered for this project only. 2. Terminal (TUI): `spacedock review-mode set local`. 3. Web: do not record yet. Ask a second question on its own, with two options, "Yes, upload it" and "No": ```text Web uploads the file to review.spacedock.md. Anyone with the link can open it, and it expires automatically after seven days. Agree? ``` Yes: `spacedock review-mode set remote`. No: record nothing, say so, and end the turn. Offer the Terminal (TUI) in a sentence of your reply, not as another question: the user records it by running `/spacedock:review tui`. 4. In your reply to the final answer, whichever it is (a Terminal (TUI) choice, a Yes, or a No while you still offer the Terminal (TUI)), tell the user they can change the setting at any time by running `/spacedock:review` with no argument. ## Show or change the choice Publish nothing and open nothing. 1. Run `spacedock review-mode get --json`. If it exits 1, the recorded choice is
From spacedock-dev/spacedock, Apache-2.0.
More from spacedock-dev/spacedock
- 0.676score
first-officer
spacedock-dev
Use when running or resuming a Spacedock workflow, especially to discover a workflow, dispatch packaged workers, manage approval gates, and advance entity…
SkillAFreshness: A★ 81Claude Code +9 - 0.671score
compass
spacedock-dev
Open Spacedock Compass, the local dashboard of what your coding-agent sessions are doing: sessions, subagents, progress and drift.
SkillAFreshness: A★ 81Claude Code +9 - 0.659score
fo-gate-lifecycle
spacedock-dev
Handle an engaged gate entry.
SkillAFreshness: A★ 81Claude Code +9 - 0.642score
commission
spacedock-dev
This skill should be used when the user asks to "commission a workflow", "create a workflow", "design a workflow", "launch a workflow", or wants to…
SkillAFreshness: A★ 81Claude Code +9 - 0.636score
survey
spacedock-dev
Use when arriving at or returning to a project that already has AI-agent history and you want the lay of the land before doing anything else — "survey this…
SkillBFreshness: B★ 81Claude Code +9 - 0.631score
fo-dispatch-recovery
spacedock-dev
Claude dispatch failure recovery — Break-Glass Manual Dispatch (the manual `Agent()` template) and Context Budget Failure/Dead Ensign Handling (the…
SkillBFreshness: B★ 81Claude Code +9 - 0.631score
fo-status-viewer
spacedock-dev
First-officer status query/mutate/display surface — the `status` command flag docs, `--set` field docs, canonical captain-facing invocations, the…
SkillBFreshness: B★ 81Claude Code +9 - 0.628score
present-gate
spacedock-dev
First-officer gate-presentation rendering — the captain-facing gate-review template and assembly rules, including workflow-owned finding labels.
SkillBFreshness: B★ 81Claude Code +9 - 0.628score
feedback-rejection-flow
spacedock-dev
First-officer feedback-rejection routing — the correction-round record, reuse-or-fresh routing of findings to the `feedback-to` target, the reviewer re-run…
SkillBFreshness: B★ 81Claude Code +9 - 0.622score
ensign
spacedock-dev
Execute workflow stage work as a dispatched worker.
SkillBFreshness: B★ 81Claude Code +9 - 0.606score
debrief
spacedock-dev
This skill should be used when the user asks to "debrief", "record what happened", "session summary", "write a debrief", or wants to capture session activity…
SkillBFreshness: B★ 81Claude Code +9 - 0.606score
refit
spacedock-dev
This skill should be used when the user asks to "refit a workflow", "upgrade a workflow", "update workflow scaffolding", or wants to bring an existing…
SkillBFreshness: B★ 81Claude Code +9
Signals
- Stars
- 81
- Forks
- 9
- Open issues
- 85
- Last commit (this folder)
- Oct 21, 2026 (9 days ago)
- Last release
- Sep 15, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/spacedock-dev/spacedock
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from spacedock-dev
- 0.676score
first-officer
spacedock-dev
Use when running or resuming a Spacedock workflow, especially to discover a workflow, dispatch packaged workers, manage approval gates, and advance entity…
SkillAFreshness: A★ 81Claude Code +9 - 0.671score
compass
spacedock-dev
Open Spacedock Compass, the local dashboard of what your coding-agent sessions are doing: sessions, subagents, progress and drift.
SkillAFreshness: A★ 81Claude Code +9 - 0.659score
fo-gate-lifecycle
spacedock-dev
Handle an engaged gate entry.
SkillAFreshness: A★ 81Claude Code +9 - 0.642score
commission
spacedock-dev
This skill should be used when the user asks to "commission a workflow", "create a workflow", "design a workflow", "launch a workflow", or wants to…
SkillAFreshness: A★ 81Claude Code +9 - 0.636score
survey
spacedock-dev
Use when arriving at or returning to a project that already has AI-agent history and you want the lay of the land before doing anything else — "survey this…
SkillBFreshness: B★ 81Claude Code +9 - 0.631score
fo-dispatch-recovery
spacedock-dev
Claude dispatch failure recovery — Break-Glass Manual Dispatch (the manual `Agent()` template) and Context Budget Failure/Dead Ensign Handling (the…
SkillBFreshness: B★ 81Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get review running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
review skill. Agent Mart. https://agentmart.dev/skills/spacedock-dev-review (last updated 2026-10-24)