core-workflow — Claude Code skill: what it does, how to install
core-workflow is a skill with working protocols for agents: Git conventions, security and accessibility checklists, and task sizing. It loads for complex work or when a specific pattern is requested.
MIT 141 installs ★ 114 updated 2026-11-06
npx skills add travisjneuman/.claude --skill core-workflow -a claude-codeWhat core-workflow does
This skill hands the agent a reference for how a working session runs: how to open it, how to close it, what a commit looks like, which checks come before shipping. It loads on its own for planning, debugging and multi-step features.
The session protocol sits at the centre. Start with a branch sync from origin/HEAD, a short log and a look at tasks/*.md; finish by reading the diff, moving the finished task into .archive/completed-tasks/ and committing. Commit types come from a fixed list, and messages carry blocks — what changed, why, how it was verified. Past git there are frontend and backend security checks, performance budgets, a WCAG AA list and decision frameworks invoked as /consider:* commands.
Auto-commit has a gate: it fires only inside a repo you own. An external remote marked no_push, or a submodule, stays read-only. The build-vs-buy section also rules out GPL and AGPL dependencies.
What it helps with
- run a session from branch sync to commit without skipping steps
- pick a workflow that matches the size of the task
- sweep frontend and backend code against a security checklist
- check the interface against WCAG AA
- keep GPL dependencies out of the project
Example prompts for the agent
- Plan this feature in phases and drop a task file into
tasks/. - Review the diff against the original request before you commit.
- Walk this bug from reproduction to root cause.
How to install core-workflow
1Skills CLI (Vercel)
npx skills add travisjneuman/.claude --skill core-workflow -a claude-code2Manually: put the files in place
~/.claude/skills/core-workflow/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/core-workflow/
1Skills CLI (Vercel)
npx skills add travisjneuman/.claude --skill core-workflow -a codex2Manually: put the files in place
.agents/skills/core-workflow/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add travisjneuman/.claude --skill core-workflow -a cursor2Manually: put the files in place
.cursor/skills/core-workflow/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install travisjneuman/.claude skills/core-workflow2Manually: put the files in place
.github/skills/core-workflow/SKILL.md1Skills CLI (Vercel)
npx skills add travisjneuman/.claude --skill core-workflow -a gemini-cli2Platform CLI
gemini skills install https://github.com/travisjneuman/.claude --path skills/core-workflowManually: put the files in place
.devin/skills/core-workflow/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add travisjneuman/.claude --skill core-workflow -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about core-workflow
How do I install core-workflow in Claude Code?
Run npx skills add travisjneuman/.claude --skill core-workflow -a claude-code. The skill file lands at ~/.claude/skills/core-workflow/SKILL.md.
What does core-workflow do?
It gives the agent a reference for session protocol, commit conventions, security and accessibility checklists, and task sizing. It shows up when a task is complex enough to need them.
When does core-workflow commit on its own?
Only inside a repo you own. External remotes with no_push and submodules are treated as read-only.
Source text
SKILL.md · MIT
--- name: core-workflow description: Detailed development workflow patterns, checklists, and standards. Auto-loads for complex tasks, planning, debugging, or when explicit patterns are needed. Contains session protocols, git conventions, security checklists, review-based validation, and communication standards. --- # Core Workflow Patterns Comprehensive development workflow reference. This loads on-demand for detailed patterns. **Quick links to rules:** `~/.claude/rules/` for stack-specific and task-type checklists. --- ## Session Protocol ### Start Checklist ```bash # 1. Sync first: default branch from origin/HEAD, fetch + prune, fast-forward git fetch --prune origin && git merge --ff-only "$(git symbolic-ref --short refs/remotes/origin/HEAD)" # 2. Get context git log -3 # 3. Check for existing work ls tasks/*.md 2>/dev/null || echo "No active tasks" ``` Take today's date from the environment context rather than inferring it. ### End Checklist Before archiving or writing durable documentation, follow [Memory and documentation](../../CLAUDE.md#memory-and-documentation). Update the owning subject note first; task files and handoff summaries link to it. ```bash # 1. Verify by review: re-read the request and the whole diff (no test/type-check ladder) # 2. Archive completed work mv tasks/<completed-task>.md .archive/completed-tasks/ # 3. Commit with comprehensive message git add -A # all pending changes, any session's git commit # See Git Conventions below git push # or the configured push runner, when one is defined; never force ``` **Stop any dev server you started:** `lsof -ti:PORT | xargs kill` (or Windows equivalent) --- ## Sizing Work | Complexity | Workflow | | -------------------------- | ------------------------------------------------- | | Simple fix (<30 min) | Direct execution | | Single feature (30min-2hr) | Task file + TodoWrite | | Multi-phase feature (days) | Plan mode, then one task file per phase in `tasks/` | | New project/app | `/init-project`, then plan mode for the first phase | --- ## Git Conventions ### Commit Types `feat` | `fix` | `refactor` | `perf` | `test` | `docs` | `chore` ### Commit Message Format ``` type: Short summary (50 chars max) ## What Changed - File X: Added feature Y - File Z: Updated config for A ## Why - User requested feature Y - Config A needed update ## Verification - Diff reviewed against the request, callers, and edge cases ``` ### Auto-Commit on Task Completion **When a task or plan is complete, automatically commit without being asked.** #### Pre-Commit Checks ```bash # 1. Check this is a user-owned repo (not external) git remote get-url origin | grep -q "travisjneuman" && echo "OK: User repo" # 2. Check push is not blocked git remote get-url --push origin | grep -q "no_push" && echo "SKIP: External repo" ``` #### Rules | Condition | Action | | ---------------------------- | ---------------------------- | | User's own repo | Auto-commit + push | | External repo (`no_push`) | **Never commit** - read-only | | Submodule (external) | **Never commit** - read-only | | Uncommitted secrets detected | **Block** - warn user | --- ## Security Checklist ### Frontend - [ ] `textContent` not `innerHTML` - [ ] `unknown` type for external data - [ ] No exposed API keys - [ ] HTTPS for external requests - [ ] Input sanitization ### Backend - [ ] Input validation on all endpoints - [ ] Auth guards on protected routes - [ ] Parameterized queries (no raw SQL) - [ ] Secrets in environment variables --- ## Performance Targets | Metric | Target | | ---------------------- | --------------- | | Initial bundle | <100KB gzipped | | Page load | <1s | | Interaction latency | <100ms | | Lighthouse Performance | 95+ | | Accessibility | WCAG AA minimum | --- ## Accessibility (WCAG AA) - [ ] Semantic HTML structure - [ ] Alt text for meaningful images - [ ] Keyboard navigation (Tab, Enter, Escape) - [ ] Focus indicators visible - [ ] Color contrast >= 4.5:1 - [ ] ARIA labels on interactive elements - [ ] Touch targets >= 44x44px --- ## Thinking Frameworks Use structured decision-making for complex choices: | Decision Type | Framework | | ---------------------- | ----------------------------- | | Long-term implications | `/consider:10-10-10` | | Root cause analysis | `/consider:5-whys` | | Prioritization | `/consider:eisenhower-matrix` | | Innovation | `/consider:first-principles` | | Risk identification | `/consider:inversion` | | Simplification | `/consider:occams-razor` | | Focus | `/consider:one-thing` | | Tradeoffs | `/consider:opportunity-cost` | | Optimization | `/consider:pareto` | | Consequences | `/consider:second-order` | --- ## Debugging Protocol ### Standard Issues 1. Reproduce the issue 2. Read relevant code 3. Identify root cause 4. Fix the root cause 5. Verify by review of the diff and the output the fix already produces ### Intermittent/Complex Issues Use the `debug-systematic` skill for a systematic approach. --- ## Build vs Buy Philosophy **We build features. We use utilities.** - **Build:** All feature logic, business rules, UI/UX, data models - **Use:** Low-level abstractions (D3, Recharts, Lexical, Konva) - **Criterion:** We own the feature, library handles complexity ### License Requirements - **Must use:** MIT, Apache 2.0, BSD - **Never use:** GPL, AGPL (blocks commercialization) --- ## Communication Standards ### Progress Updates Give high-level updates, not spam: "Added authentication middleware (3 files) and updated the user store with the new fields; now reviewing the login flow." ### When to Ask Use `AskUserQuestion` only when: - An essential choice is missing and changes the outcome - Instructions conflict and precedence doesn't settle it - A destructive or external target can't be identified exactly - The step needs authority the request didn't give Otherwise pick the reasonable option, proceed, and state the assumption. ### Directness Protocol - Logic over feelings - Correctness over validation - Direct feedback over diplomacy - Best solution over agreement --- ## Context Hygiene ### Reduce Token Usage - Short, high-signal summaries over long logs - Don't `@`-embed large docs by default - Reference paths + when to read them - Use `/clear` after completing work units ### Delegation Patterns | Situation | Action | | -------------------- | ----------------------------------------- | | Context >100k tokens | Create prompt → delegate to fresh context | | Moderate complexity | `/create-prompt` → `/run-prompt` | | Multi-stage features | `/create-meta-prompt` | | Approaching limits | `/whats-next` for handoff document | --- ## Quick Reference ### Common Commands ```bash npm run dev # Start dev server npm run build # Production build npm run test # Run tests (only when the user asks) npm run type-check # TypeScript check (only when the user asks) ``` ### File Naming | Type | Convention | Example | | ---------- | ---------- | --------------- | | Components | PascalCase | `UserCard.tsx` | | Hooks | use prefix | `useAuth.ts` | | Utilities | camelCase | `utils.ts` | | Tests | .test.ts | `utils.test.ts` | --- ## Resources ### Official - [Claude Code Docs](https://docs.anthropic.com/en/docs/claude-code) - [Anthropic Best Practices](https://www.anthropic.com/engineering/claude-code-best-practices) ### Community - [awesome-claude-code](https://github.com/hesreallyhim/awesome-claude-code) - [awesome-claude-md](https://github.com/josix/awesome-claude-md) --- ## See Also - `~/.claude/docs/reference/checklists/` - Task-type specific checklists - `~/.claude/docs/reference/stacks/` - Stack-specific patterns - `~/.claude/docs/reference/tooling/` - Tool configuration guides - `~/.claude/skills/MASTER_INDEX.md` - Full skills catalog - `~/.claude/agents/README.md` - Agents directory
© travisjneuman · MIT · travisjneuman/.claude