cursor-review
Run a Cursor Composer review as an advisory second opinion while keeping the primary review verdict on the host brain. Use when user invokes cursor:review, asks Cursor to review, or wants composer to sanity-check a diff. Cursor never owns APPROVE/REQUEST_CHANGES.
- License 许可
- MIT
- 最近更新
- 2026-11-11
- Stars
- ★ 3.2k
- Forks
- 306
01 前言 Front Matter
- name
- cursor-review
- description
- Run a Cursor Composer review as an advisory second opinion while keeping the primary review verdict on the host brain. Use when user invokes cursor:review, asks Cursor to review, or wants composer to sanity-check a diff. Cursor never owns APPROVE/REQUEST_CHANGES.
- allowed-tools
- [ "Read", "Bash", "Grep" ]
- argument-hint
- [--base <ref>] [review-scope]
- description-en
- Run a Cursor Composer review as an advisory second opinion while keeping the primary review verdict on the host brain. Use when user invokes cursor:review, asks Cursor to review, or wants composer to sanity-check a diff. Cursor never owns APPROVE/REQUEST_CHANGES.
- description-ja
- Cursor Composer に advisory second opinion としてレビューさせるスキル。cursor:review、Cursor にレビューして、composer で差分を sanity check して、という時に使う。primary verdict は常に host brain が持ち、Cursor は APPROVE/REQUEST_CHANGES を所有しない。
- user-invocable
- true
03 SKILL.md 正文
cursor:review - Advisory Cursor Review
Cursor Composer (composer-2.5-fast) を read-only second opinion として使う review skill。primary verdict は host brain (Opus / Claude role) が出す。
Quick Reference
cursor:review --base origin/main
cursor:review "Phase 88.5 command namespace diff"
Rules
-
Cursor review is advisory. The final verdict must come from the host reviewer.
-
Do not pass
--writetocursor-companion.sh. -
Use resolver/model routing, not direct env checks:
bash scripts/resolve-impl-backend.sh --backend cursor --role reviewer bash scripts/model-routing.sh --host cursor --role worker --field model -
Prefer the existing
harness-reviewcontract when a full review is requested. This command exists for users who explicitly ask for the Cursor lane.
Flow
-
Resolve the Harness helper root:
HARNESS_PLUGIN_ROOT="${HARNESS_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-}}" if [ -z "$HARNESS_PLUGIN_ROOT" ] && [ -n "${CLAUDE_SKILL_DIR:-}" ]; then probe="$(cd "${CLAUDE_SKILL_DIR}" && pwd)" while [ "$probe" != "/" ] && [ ! -d "$probe/scripts" ]; do probe="$(cd "$probe/.." && pwd)" done [ -d "$probe/scripts" ] && HARNESS_PLUGIN_ROOT="$probe" fi if [ -z "$HARNESS_PLUGIN_ROOT" ]; then echo "ERROR: HARNESS_PLUGIN_ROOT is not set and could not be derived from CLAUDE_PLUGIN_ROOT or CLAUDE_SKILL_DIR" >&2 exit 2 fi -
Determine review scope:
BASE_REF="${TASK_BASE_REF:-origin/main}" REVIEW_SCOPE="${ARGUMENTS:-}" if [ -n "${REVIEW_SCOPE}" ]; then set -- ${REVIEW_SCOPE} while [ "$#" -gt 0 ]; do case "$1" in --base) BASE_REF="${2:?--base requires a ref}" shift 2 ;; --base=*) BASE_REF="${1#--base=}" shift ;; *) shift ;; esac done fi DIFF_STAT="$(git diff --stat "${BASE_REF}..HEAD")" DIFF_TEXT="$(git diff "${BASE_REF}..HEAD")" -
Ask Cursor in read-only mode:
PROMPT="$(cat <<EOF
Review this diff as an advisory second opinion. Base ref: ${BASE_REF} Requested scope: ${ARGUMENTS:-full diff} Requirement, purpose and DoD: <original request and completion criteria> Spec and validation evidence: <relevant paths and observed results>
Focus on bugs, regressions, missing tests, and unsafe assumptions. Do not propose broad refactors. Use the supplied requirement, DoD, spec and validation evidence to assess the requested scope; inspect missing context read-only. For each finding, state its location, trigger, impact and checkable evidence. Separate hypotheses from observed defects; do not invent findings to fill a quota. Return an assessment only. Do not implement changes or treat the implementation worker's self-report as verification.
Diff stat: ${DIFF_STAT}
Diff: ${DIFF_TEXT} EOF )" bash "${HARNESS_PLUGIN_ROOT}/scripts/cursor-companion.sh" task "${PROMPT}"
4. Host reads Cursor's output and performs the primary review:
- Findings first, ordered by severity.
- Mark Cursor-originated points as advisory when used.
- `APPROVE` / `REQUEST_CHANGES` must be the host decision, not a copied Cursor verdict.
## Output
Use the standard review shape:
- findings
- open questions
- validation run
- final host verdict
04 同仓库更多 Skills
escape-skill
暂无简介
zz-review-empty
暂无简介
session-send
This skill should be used when the user asks to notify other session, requests a session handoff, says tell other agent, or needs a cross-session message.
memory
Manage SSOT, memory, and cross-tool memory search. Guardian of decisions.md and patterns.md. Use when user mentions memory, SSOT, decisions.md, patterns.md, merging, migration, SSOT promotion, sync memory, save learnings, memory search, harness-mem, past decisions, or record this. Do NOT load for: implementation work, reviews, ad-hoc notes, or in-session logging.
maintenance
File cleanup and archiving. Tidies up bloated Plans.md, session-log.md, old logs, and state files. Trigger: /maintenance, cleanup, archive, organize, split session-log. Do NOT load for: implementation, review, release, new feature development.
japanese-writing-drafter
Detect when the operator corrects the agent's Japanese phrasing mid-conversation (rewrites a sentence, calls out a style problem, says 'this wording is bad, say it like X instead') and draft a pending writing-rule proposal into ~/.claude/writing-lint/proposals.jsonl for later human review. This skill is the ONLY writer of proposals.jsonl — it never edits rules.jsonl and never sets status to anything but pending. Promotion to rules.jsonl only happens via the human-run scripts/writing-rule-approve.sh. Use when user mentions writing-rule proposal, 表現を直して, 文体を直して, その言い方はNG, writing lint 提案, 指摘をルール化して. Do NOT load for: approving or rejecting proposals (use scripts/writing-rule-approve.sh), listing pending proposals (use scripts/writing-rule-list.sh), or scanning text against the existing dictionary (the writinglint engine / PostToolUse hook does that).