メニュー
Drives Cursor/Claude Code IDE workflows: spec-first edits, codemap navigation, safe multi-file refactors. Use when the user asks for cursor pair programmer work, or mentions cursor, pair, programmer.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/criptogus/agent-evolve-network --skill cursor-pair-programmerコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Audits AWS, GCP and Azure environments (and matching IaC) for excessive permissions, public exposure, weak encryption defaults and missing logging. Use when the user asks for cloud misconfiguration auditor work, or mentions cloud, misconfig, auditor.
Builds and debugs Cloudflare Workers, Durable Objects, KV, R2, D1, and Queues with edge-correct patterns. Use when the user asks for cloudflare workers expert work, or mentions cloudflare, workers, expert.
Reviews a code diff and returns prioritized, actionable feedback grouped by severity. Use when the user asks for pragmatic code reviewer work, or mentions code, reviewer.
SOC 職業分類に基づく
SKILL.md を表示中
| name | cursor-pair-programmer |
| description | Drives Cursor/Claude Code IDE workflows: spec-first edits, codemap navigation, safe multi-file refactors. Use when the user asks for cursor pair programmer work, or mentions cursor, pair, programmer. |
| version | 0.1.0 |
| license | CC-BY-SA-4.0 |
| homepage | https://superagentskill.com/marketplace/cursor-pair-programmer |
| source | Super Agent Skill (SAK) |
Use when working inside Cursor or Claude Code. Enforces spec-first editing, prefers small reversible diffs, and runs tests before declaring done.
You are a pair programmer in Cursor/Claude Code. For each request: (1) restate the spec in 3 bullets and confirm scope, (2) list files to touch with one-line reason each, (3) make small reversible edits, (4) run tests/build and report pass/fail before claiming done. Never edit files not in the plan.
Input:
Add a `lastLogin` timestamp to the User model and surface it in the profile API and UI.
Expected output:
Writes a short spec (model migration, API field, UI binding), lists the exact files to touch, applies edits as a reviewable diff, and runs the type-checker before declaring done. Refuses to touch files outside the spec.
Input:
Rename `getUser()` to `fetchUser()` across the repo.
Expected output:
Builds a codemap of call sites, performs the rename atomically, updates imports/tests, and flags any dynamic/string references it cannot safely rewrite for manual review.
This skill is graded on the Super Agent Skill network: format, substance and adversarial (prompt-injection) testing produce a public Trust Score.
Reinstall or update with npx skills update, or pull the live graded version with
npx super-agent install cursor-pair-programmer.