From dev-workflow
Use when performing common development tasks like committing code, reviewing changes, running tests, fixing bugs, creating PRs, or checking repo status. Provides structured workflows for everyday git and development operations.
npx claudepluginhub sagargupta16/claude-skills --plugin dev-workflowThis skill uses the workspace's default tool permissions.
| Task | Command | What It Does |
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Checks Next.js compilation errors using a running Turbopack dev server after code edits. Fixes actionable issues before reporting complete. Replaces `next build`.
| Task | Command | What It Does |
|---|---|---|
| Commit | /commit | Stage changes, write conventional commit message |
| Review | /review | Analyze branch changes for bugs, security, quality |
| Test | /test | Detect test framework, run tests, diagnose failures |
| Fix | /fix | Trace root cause, implement minimal fix, verify |
| PR | /pr | Create pull request with summary and test plan |
| Status | /status | Full repo overview: branches, PRs, CI, sync state |
| Check PR | /check-pr | CI status, reviews, comments, merge readiness |
git status and git diff to understand changesgit log --oneline -5 to match the repo's commit styletype: short descriptionfeat, fix, refactor, docs, test, chore, style, perfWhen reviewing branch changes (git diff main...HEAD):
| Category | Check For |
|---|---|
| Logic | Bugs, off-by-one errors, null handling |
| Security | Injection, XSS, secrets exposure, CORS |
| Performance | N+1 queries, unnecessary loops, missing indexes |
| Error handling | Unhandled exceptions, missing edge cases |
| Style | Consistency with surrounding code |
| Tests | New code covered? Edge cases tested? |
| API | Breaking changes to public interfaces? |
Provide: overall assessment (ship it / needs changes / major issues), specific issues with file:line references, suggested fixes.
Detect the framework and run tests:
| Config File | Framework | Command |
|---|---|---|
package.json (scripts.test) | npm/yarn/pnpm | npm test / pnpm test |
pytest.ini / pyproject.toml | pytest | pytest |
Cargo.toml | cargo | cargo test |
go.mod | go | go test ./... |
Makefile (test target) | make | make test |
On failure: parse output, identify the failing test, show the assertion, suggest a fix (don't auto-fix unless asked).
git log --oneline -10 for recent changesgit log and git diff against base branchgh pr view) - if so, show URL instead## Summary - 2-3 bullet points## Test plan - checklist of what was testedGather and present:
git status - working tree stategit log --oneline -5 - recent commitsgit branch -a - all branchesgit stash list - stashed changesgh pr list --state open - open PRsFor a given PR number: