we

Intelligently update project documentation

Create Pull Request with prerequisite validation

Professional code review with AC alignment

Static code analysis - lint, format, types

Run tests with coverage

Professional code review — diff-based, AC-aligned, max 10 issues. This agent should be used when reviewing code, checking pull requests, or when the user mentions code review.

Updates project documentation based on code changes. Use when documentation is outdated, after adding features, changing setup processes, or when user mentions documentation updates.

Create Pull Request with prerequisite validation and ticket linking. Use AFTER all quality gates pass.

Static code analysis — linting, formatting, types, dead code, complexity. Auto-detects project stack. Use for code quality checks before tests.

Run tests with coverage. Auto-detects project stack. Use AFTER static analysis passes.

Architecture advisor for technical planning. Writes implementation notes, ADRs, security review decisions. Standalone architecture guidance without story context. Use when user says "/we:arch", "architecture", "ADR", "technical approach", or needs architecture guidance.

Run security audit across weside repositories. Checks tool availability, executes scripts/security-audit.sh, parses JSON reports, and summarizes findings by severity. Use when asked to "run audit", "security scan", "check vulnerabilities", or "/we:audit".

CI/Review checker and fixer. Collects ALL findings from CI, Claude Review, and CodeRabbit, then fixes everything in a single batch. Runs in the main agent (not a subagent) so the user can observe every step. Use when user says "/we:ci-review", "fix ci", "fix reviews", "ci failed".

Documentation CONTENT consistency check. Finds outdated code references, contradictions, semantic duplicates. Reads docs thematically, not file-by-file. Use when user mentions "consistency", "outdated docs", "contradictions", "/we:doc-check".

Systematic documentation review — validates structure, frontmatter, detects duplicates, checks token efficiency. Use when reviewing documentation quality, validating rules setup, or when user mentions "doc-review", "documentation review".

Find and remove dead code from Python backends. Covers method-level detection, test-only reference detection, vulture static analysis, and coverage-based detection. Use when asked to find dead code, clean up unused functions, or reduce codebase size.

Load and adopt your weside Companion's identity. Use at session start or when switching companions. Requires weside.ai account.

Product Owner skill — creates/refines stories with implementation plans. Creates ticket (MINIMAL) AND plan (DETAILED) in one step. Uses EnterPlanMode. Handles Epics. Use when user says "/we:refine", "refine", "new story", "acceptance criteria", "epic", "write a story".

Project onboarding — detects stack, ticketing tool, and optionally creates project vision, DoR, DoD. Interactive, minimal (3 questions). Use when user says "/we:setup", "configure project", "set up workflow".

Scrum Master — owns the development process, optimizes workflow, runs retrospectives, reviews skill quality. Knows the full /we:* pipeline and how all skills interact. Use when user mentions "optimize", "process", "workflow", "retrospective", "skill quality", "impediment", "/we:sm".

Story Orchestrator — coordinates the complete development pipeline from git preparation through PR creation and CI review. Loads plan, manages checkpoints, circuit breaker, and resume capability. Use when user says "/we:story", "implement story", or provides a ticket key.

2 hooks across 2 events