pro-workflow (Claude Skill) — Use Cases, Install & Live Demo

Why use it

Key features

Capture corrections as durable rules tied to file/feature scope
Surface relevant rules at task start (no re-stating per session)
Parallel git worktree orchestration for concurrent agent threads
Compounds across 50+ sessions — measurable drift reduction
CLAUDE.md auto-edits with version control

Live Demo

What it looks like in practice

ready

Install

Pick your client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "pro-workflow-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/rohitg00/pro-workflow",
        "~/.claude/skills/pro-workflow"
      ],
      "_inferred": true
    }
  }
}

Open Claude Desktop → Settings → Developer → Edit Config. Restart after saving.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "pro-workflow-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/rohitg00/pro-workflow",
        "~/.claude/skills/pro-workflow"
      ],
      "_inferred": true
    }
  }
}

Cursor uses the same mcpServers schema as Claude Desktop. Project config wins over global.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "pro-workflow-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/rohitg00/pro-workflow",
        "~/.claude/skills/pro-workflow"
      ],
      "_inferred": true
    }
  }
}

Click the MCP Servers icon in the Cline sidebar, then "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "pro-workflow-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/rohitg00/pro-workflow",
        "~/.claude/skills/pro-workflow"
      ],
      "_inferred": true
    }
  }
}

Same shape as Claude Desktop. Restart Windsurf to pick up changes.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "pro-workflow-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/rohitg00/pro-workflow",
        "~/.claude/skills/pro-workflow"
      ]
    }
  ]
}

Continue uses an array of server objects rather than a map.

~/.config/zed/settings.json

{
  "context_servers": {
    "pro-workflow-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/rohitg00/pro-workflow",
          "~/.claude/skills/pro-workflow"
        ]
      }
    }
  }
}

Add to context_servers. Zed hot-reloads on save.

claude mcp add pro-workflow-skill -- git clone https://github.com/rohitg00/pro-workflow ~/.claude/skills/pro-workflow

One-liner. Verify with claude mcp list. Remove with claude mcp remove.

Use Cases

Real-world ways to use pro-workflow

Stop correcting Claude Code on the same thing twice

👤 Daily Claude Code users ⏱ ~10 min beginner

When to use: You've told Claude 'use lodash isEmpty, not !arr.length' three times and it keeps reverting.

Prerequisites

Skill installed in repo — git clone https://github.com/rohitg00/pro-workflow ~/.claude/skills/pro-workflow

Flow

Capture the next correction

Use pro-workflow. Capture this rule: 'Use lodash isEmpty for emptiness checks; never !arr.length'. Scope: src/utils/.✓ Copied

→ Rule saved with scope; CLAUDE.md updated
Verify next session

Tomorrow: ask Claude to clean up an empty-check pattern in src/utils/.✓ Copied

→ Claude uses isEmpty without re-prompting
Audit the rule set monthly

List all captured rules. Anything stale or superseded?✓ Copied

→ Rule list with last-applied dates; prune cruft

Outcome: Each correction is paid once, not weekly.

Pitfalls

Over-broad rules ('always use functional style') backfire — Scope rules to directories or feature areas; concrete > general

Combine with: filesystem

Run two Claude Code threads against the same repo without stepping on each other

👤 Devs running long agent tasks ⏱ ~20 min intermediate

When to use: You want to refactor module A while Claude continues a feature on module B.

Flow

Spawn worktrees

Use pro-workflow. Create two worktrees: ../wt-refactor-a and ../wt-feature-b from main.✓ Copied

→ Worktrees created; rules synced into each
Run threads

Start a Claude Code session in each. Worktree-aware rules apply per directory.✓ Copied

→ Both sessions running; no merge conflicts mid-flight
Reintegrate

When both branches are ready, open PRs. The skill notes any rules that triggered and their effects.✓ Copied

→ PRs include rule-effect summaries

Outcome: Real parallelism — agent throughput multiplied without coordination tax.

Pitfalls

Rules drift between worktrees if only updated in one — The skill syncs rule set on worktree creation; for ongoing edits, run sync-rules

Audit how context compounds over 50 sessions

👤 Engineering leaders evaluating AI workflows ⏱ ~30 min advanced

When to use: You want data on whether 'AI gets smarter on this repo over time' is real or vibes.

Flow

Baseline

Use pro-workflow. Show me corrections per session over the last 30 days.✓ Copied

→ Trend chart; expect downward slope
Tag categories

Categorize corrections: style, architecture, dependency choice, test pattern. Show category-wise decay.✓ Copied

→ Per-category trend
Decide

Recommend whether to roll this out team-wide based on data.✓ Copied

→ Concrete recommendation with caveats

Outcome: Data-grounded decision on agent workflow investment.

Pitfalls

Drop in corrections != quality up — could just mean you stopped reviewing — Cross-check against PR review feedback or test failure rate

Combinations

Pair with other MCPs for X10 leverage

pro-workflow-skill + filesystem

Persist rules in repo so the team shares them

Commit .claude/rules/ and CLAUDE.md to git; teammates inherit the same rule set.✓ Copied

pro-workflow-skill + claude-mem-skill

Layered memory — pro-workflow for rules, claude-mem for session continuity

Use pro-workflow to capture corrections; use claude-mem to bridge session context.✓ Copied

Tools

What this MCP exposes

Tool	Inputs	When to call
capture_rule	rule_text, scope_path?, severity?	Right after correcting Claude on something durable
list_rules	scope?	Audit / prune
create_worktree	branch, path	Start a parallel agent thread
sync_rules	—	After updating rules in one worktree, sync to others
correction_stats	since?	Trend audit

Cost & Limits

What this costs to run

API quota: None — local
Tokens per call: Surfaced rules add 100–800 tokens to system prompt; pruning matters
Monetary: Free
Tip: Audit rules monthly; over-broad or stale rules cost tokens forever

Security

Permissions, secrets, blast radius

Minimum scopes: filesystem-read filesystem-write

Credential storage: Rules stored in repo (.claude/rules/) — same trust as the repo itself

Data egress: None

Don't capture secrets as rules — rules go to git

Troubleshooting

Common errors and fixes

Rule not applied in next session

Check scope path; the rule may be scoped narrower than the file you're editing

Verify: list_rules --scope /the/file

CLAUDE.md edits causing merge conflicts

Skill writes rules to a separate file; only the index in CLAUDE.md changes — check rebase strategy

Worktree creation fails

git version >= 2.5 required; ensure no untracked files block the new path

Verify: git worktree list

Stats show no decay over 50 sessions

Probably rules are too narrow to apply; run audit and broaden a few key ones

Alternatives

pro-workflow vs others

Alternative	When to use it instead	Tradeoff
claude-reflect (BayramAnnakov)	You want a more passive reflection-driven capture instead of explicit	Different capture style; less worktree orchestration
Manual CLAUDE.md curation	Your team is small and you don't mind hand-curating rules	No analytics; no parallel-worktree help

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills