SKILLS/GENERAL CODING WORKFLOWS/pr-manager/SKILL.md
Review, test, lint, and prepare smart merges for all open and closed PRs, verifying features and documenting technical debt.
npx skillsauth add mattmre/evokore-mcp pr-managerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill manages outstanding PRs, ensuring code quality, feature completeness, and smart merging without losing context or code.
docs folder.Adapted from Agent33's risk trigger framework. When a PR touches certain areas, it must be routed to the appropriate specialist reviewer before merge.
Route to security reviewer (or invoke security-review skill) when the PR includes any of:
Route to database/schema reviewer when the PR includes:
Route to architecture reviewer when the PR includes:
package.json, requirements.txt, or lockfiles| Trigger Category | Specific Triggers | Required Reviewer | Block Merge? | |-----------------|-------------------|-------------------|--------------| | Security/Auth/Crypto | Auth flows, session mgmt, token handling, encryption | Security | Yes | | Input Validation | User input parsing, sanitization, allowlists | Security | Yes | | Secrets Handling | API keys, tokens, vault config, credential rotation | Security | Yes | | Schema/Data Model | Migrations, ORM models, constraints, indexes | DBA | Yes | | Public API/Interface | New endpoints, schema changes, removed routes | Architecture | Yes | | CI/CD/Deployment | Pipelines, Dockerfiles, IaC | Architecture | Yes | | Large Refactor | 10+ files changed, module restructuring | Architecture | Recommended | | Supply Chain | New deps, lockfile changes, build scripts | Security | Recommended | | Prompt Injection | Untrusted content processing, dynamic prompts | Security | Yes | | Sandbox/Permissions | Tool approvals, elevated permissions, network access | Security | Yes |
development
Core orchestration framework for model-agnostic multi-agent workflows with handoff protocol, policy governance, and configuration schemas
testing
Specialized skill for triage issue skill workflows.
development
Complete workflow for building, implementing, and testing goal-driven agents. Orchestrates hive-* skills. Use when starting a new agent project, unsure which skill to use, or need end-to-end guidance.
development
Iterative agent testing with session recovery. Execute, analyze, fix, resume from checkpoints. Use when testing an agent, debugging test failures, or verifying fixes without re-running from scratch.