بنقرة واحدة
prp-framework
يحتوي prp-framework على 56 من skills المجمعة من gobikom، مع تغطية مهنية على مستوى المستودع وصفحات skill داخل الموقع.
Skills في هذا المستودع
Multi-agent PR review — spawns parallel specialized agents for deep code review.
Multi-agent PR review — spawns parallel specialized agents for deep code review.
Execute an implementation plan with rigorous validation loops — typecheck, lint, test, and build after every change. TDD approach with automatic failure recovery.
Create a comprehensive implementation plan by analyzing the codebase, discovering patterns, and producing a step-by-step actionable plan document.
Execute an implementation plan with rigorous validation loops — typecheck, lint, test, and build after every change. TDD approach with automatic failure recovery.
Create a comprehensive implementation plan by analyzing the codebase, discovering patterns, and producing a step-by-step actionable plan document.
Execute the complete PRP lifecycle end-to-end — issue context, smart plan, implement, commit, PR, review-fix loop (until 0 issues), merge, and cleanup. Supports --issue, --merge, --max-review-rounds, --fast, --ralph, --skip-plan, --skip-review, --no-pr, --resume, --no-interact, --dry-run, --fix-severity, --verify, --qa-delegate=<agent>, --done options.
Execute the complete PRP lifecycle end-to-end — issue context, smart plan, implement, commit, PR, review-fix loop (until 0 issues), merge, and cleanup. Supports --issue, --merge, --max-review-rounds, --fast, --ralph, --skip-plan, --skip-review, --no-pr, --resume, --no-interact, --dry-run, --fix-severity, --verify, --qa-delegate=<agent>, --done options.
Create a pull request from current branch with proper title, body, linked issues, and implementation report enrichment. Uses PR templates if available.
Create a pull request from current branch with proper title, body, linked issues, and implementation report enrichment. Uses PR templates if available.
Comprehensive multi-pass PR code review covering quality, security, dependencies, docs, tests, error handling, types, performance, accessibility, and simplification. Posts findings to GitHub.
Comprehensive multi-pass PR code review covering quality, security, dependencies, docs, tests, error handling, types, performance, accessibility, and simplification. Posts findings to GitHub.
Post-merge cleanup — verify PR merged, archive artifacts, delete local/remote branches. Supports --all for batch cleanup, --dry-run for preview.
Stage files with natural language targeting, pre-commit quality scan, plan-aware commit message, and conventional commit format.
Root cause analysis using the 5 Whys methodology — finds the actual fixable code, not symptoms. Produces evidence-backed RCA report with fix specification.
Prepare demo environment for customer presentations — setup, sample data, scripts.
Generate technical design document from PRD as optional reference (not in workflow)
Issue closure gate — verifies PR merged, review artifact exists, verify artifact exists, and Vera QA passed before closing a GitHub issue.
Multi-agent feature review — spawns parallel specialized agents for deep package analysis.
Implement a fix from investigation artifact — code changes, PR, and self-review.
Investigate a GitHub issue or problem - analyze codebase, create plan, post to GitHub
Interactive PRD generator - problem-first, hypothesis-driven product spec
Generate PROJECT.md from code analysis, PRDs, and business context. Creates compact project documentation for AI token efficiency and human readability.
Acceptance criteria verification — Playwright browser testing, API contract testing, E2E flows, responsive viewports, and accessibility checks. Reports pass/fail per criterion with screenshot evidence.
Cancel an active PRP Ralph loop and preserve work done so far.
Start autonomous Ralph loop to execute PRP plan until all validations pass. Self-referential feedback loop with iteration tracking.
Fix all issues from a PR review artifact — applies critical, high, medium, and suggestion fixes to the PR branch with validation loops and automatic failure recovery. Default LOOP mode: auto re-review + fix until 0 issues across all severities, matching run-all Step 6 semantics. Use --single-pass or explicit --severity to opt out of loop.
Safely undo implementation changes on the current branch with stash backup for recovery. Supports --soft (unstage), --hard (revert to origin/main), and --restore (recover from stash).
Requirements verification — for each acceptance criterion, find evidence in the PR diff that it was implemented. Produces verify artifact for safe-merge Gate 2.
Post-merge cleanup — verify PR merged, archive artifacts, delete local/remote branches. Supports --all for batch cleanup, --dry-run for preview.
Acceptance criteria verification — Playwright browser testing, API contract testing, E2E flows, responsive viewports, and accessibility checks. Reports pass/fail per criterion with screenshot evidence.
Issue closure gate — verifies PR merged, review artifact exists, verify artifact exists, and Vera QA passed before closing a GitHub issue.
Requirements verification — for each acceptance criterion, find evidence in the PR diff that it was implemented. Produces verify artifact for safe-merge Gate 2.
Fix all issues from a PR review artifact — applies critical, high, medium, and suggestion fixes to the PR branch with validation loops and automatic failure recovery. Default LOOP mode: auto re-review + fix until 0 issues across all severities, matching run-all Step 6 semantics. Use --single-pass or explicit --severity to opt out of loop.
Cancel an active PRP Ralph loop and preserve work done so far.
Start autonomous Ralph loop to execute PRP plan until all validations pass. Self-referential feedback loop with iteration tracking.
Generate PROJECT.md from code analysis, PRDs, and business context. Creates compact project documentation for AI token efficiency and human readability.
Orchestrate complete PRP workflow from feature request to pull request. Run branch, plan, implement, commit, PR, review with fix loop, and summary in sequence. Use when implementing features using PRP methodology or when user requests full PRP workflow.
Generate technical design document from PRD as optional reference (not in workflow)
Multi-agent feature review — spawns parallel specialized agents for deep package analysis.