pr-implement
Fork-based PR implementation with isolation check. Runs isolation check before starting work. Triggers: "implement PR", "implement contribution", "fork implementation", "code the PR".
Best use case
pr-implement is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Fork-based PR implementation with isolation check. Runs isolation check before starting work. Triggers: "implement PR", "implement contribution", "fork implementation", "code the PR".
Teams using pr-implement should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/pr-implement/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How pr-implement Compares
| Feature / Agent | pr-implement | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Fork-based PR implementation with isolation check. Runs isolation check before starting work. Triggers: "implement PR", "implement contribution", "fork implementation", "code the PR".
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# PR Implement Skill Fork-based implementation for open source contributions with mandatory isolation check. ## Overview Execute a contribution plan with fork isolation. Ensures PRs are clean and focused by running isolation checks before and during implementation. **Input**: Plan artifact from `$pr-plan` or repo URL **When to Use**: - Implementing a planned OSS contribution - Need isolation enforcement for clean PRs - After completing `$pr-plan` **When NOT to Use**: - Internal project work (use `$implement`) - Haven't planned yet (run `$pr-plan` first) --- ## Workflow ``` -1. Prior Work Check -> BLOCKING: Check for competing PRs 0. Input Discovery -> Find plan artifact or repo 1. Fork Setup -> Ensure fork exists and is current 2. Worktree Creation -> Create isolated worktree 3. Isolation Pre-Check -> BLOCK if mixed concerns 4. Implementation -> Execute plan 5. Isolation Post-Check -> BLOCK if scope creep 6. Commit Preparation -> Stage with proper commit type 7. Handoff -> Ready for $pr-prep ``` --- ## Phase -1: Prior Work Check (BLOCKING) ```bash # Search for open PRs on this topic gh pr list -R <owner/repo> --state open --search "<topic>" --limit 10 # Check target issue status gh issue view <issue-number> -R <repo> --json state,assignees ``` | Finding | Action | |---------|--------| | Open PR exists | Coordinate or wait | | Issue assigned | Coordinate or find alternative | | No competing work | Proceed | --- ## Phase 3: Isolation Pre-Check (BLOCKING) ```bash # Commit type analysis git log --oneline main..HEAD | sed 's/^[^ ]* //' | grep -oE '^[a-z]+(\([^)]+\))?:' | sort -u # File theme analysis git diff --name-only main..HEAD | cut -d'/' -f1-2 | sort -u ``` | Check | Pass Criteria | |-------|---------------| | Single commit type | 0 or 1 prefix | | Thematic files | All match plan scope | | Branch fresh | Based on recent main | **DO NOT PROCEED IF PRE-CHECK FAILS.** --- ## Phase 4: Implementation ### Guidelines | Guideline | Why | |-----------|-----| | **Single concern** | Each commit = one logical change | | **Match conventions** | Follow project style exactly | | **Test incrementally** | Run tests after each change | ### Commit Convention ```bash git commit -m "type(scope): brief description Longer explanation if needed. Related: #issue-number" ``` --- ## Phase 5: Isolation Post-Check (BLOCKING) ```bash # Commit type analysis git log --oneline main..HEAD | sed 's/^[^ ]* //' | grep -oE '^[a-z]+(\([^)]+\))?:' | sort -u # Summary stats git diff --stat main..HEAD ``` | Check | Pass Criteria | |-------|---------------| | **Single commit type** | All commits share same prefix | | **Thematic files** | All files relate to PR scope | | **Atomic scope** | Can explain in one sentence | --- ## Phase 7: Handoff ``` Implementation complete. Isolation checks passed. Branch: origin/$BRANCH_NAME Commits: N commits, +X/-Y lines Next step: $pr-prep ``` --- ## Anti-Patterns | DON'T | DO INSTEAD | |-------|------------| | Skip isolation pre-check | Run Phase 3 FIRST | | Skip isolation post-check | Run Phase 5 before push | | Mix concerns in commits | One type prefix per PR | | Implement without plan | Run $pr-plan first | ## Examples ### Implement From Contribution Plan **User says:** "Implement this external PR plan with isolation checks." **What happens:** 1. Run pre-checks for branch and scope isolation. 2. Implement only in planned files/areas. 3. Run post-checks and prepare handoff for PR prep. ### Enforce Single-Concern Commit Set **User says:** "Make sure this branch is still single-purpose before I prep the PR." **What happens:** 1. Inspect commit/file patterns against stated scope. 2. Flag mixed concerns and suggest extraction steps. 3. Produce a clean handoff to `$pr-prep`. ## Troubleshooting | Problem | Cause | Solution | |---------|-------|----------| | Isolation check fails | Unrelated changes on branch | Move unrelated edits to separate branch/PR | | Commits mix concerns | Implementation drifted from plan | Re-split commits by concern and revalidate | | Scope keeps expanding | Weak boundaries in plan | Re-anchor to `Out of Scope` and stop additional changes | | Hard to hand off | Missing summary/test context | Add concise change summary and verification notes | ## Local Resources ### scripts/ - `scripts/validate.sh`
Related Skills
implement
Execute a single issue with full lifecycle. Triggers: "implement", "work on task", "build this", "start feature", "pick up next issue", "work on issue".
vibe
Comprehensive code validation. Runs complexity analysis then multi-model council. Answer: Is this code ready to ship? Triggers: "vibe", "validate code", "check code", "review code", "code quality", "is this ready".
validation
Full validation phase orchestrator. Vibe + post-mortem + retro + forge. Reviews implementation quality, extracts learnings, feeds the knowledge flywheel. Triggers: "validation", "validate", "validate work", "review and learn", "validation phase", "post-implementation review".
update
Reinstall all AgentOps skills globally from the latest source. Triggers: "update skills", "reinstall skills", "sync skills".
trace
Trace design decisions and concepts through session history, handoffs, and git. Triggers: "trace decision", "how did we decide", "where did this come from", "design provenance", "decision history".
test
Test generation, coverage analysis, and TDD workflow. Triggers: "test", "generate tests", "test coverage", "write tests", "tdd", "add tests", "test strategy", "missing tests", "coverage gaps".
status
Single-screen dashboard showing current work, recent validations, flywheel health, and suggested next action. Triggers: "status", "dashboard", "what am I working on", "where was I".
standards
Language-specific coding standards and validation rules. Provides Python, Go, Rust, TypeScript, Shell, YAML, JSON, and Markdown standards. Auto-loaded by $vibe, $implement, $doc, $bug-hunt, $complexity based on file types.
shared
Shared reference documents for multi-agent skills (not directly invocable)
security
Continuous repository security scanning and release gating. Triggers: "security scan", "security audit", "pre-release security", "run scanners", "check vulnerabilities".
security-suite
Composable security suite for binary and prompt-surface assurance, static analysis, dynamic tracing, repo-native redteam scans, contract capture, baseline drift, and policy gating. Triggers: "binary security", "reverse engineer binary", "black-box binary test", "behavioral trace", "baseline diff", "prompt redteam", "security suite".
scenario
Author and manage holdout scenarios for behavioral validation. Scenarios are stored in .agents/holdout/ where implementing agents cannot see them. Triggers: "$scenario", "holdout", "behavioral scenario", "create scenario", "list scenarios".