Stats
Actions
Available In
Tags
Plugin
skill-set
Comprehensive productivity skills and development tools for Claude Code, including git workflow automation, code context understanding, peer LLM consulting, and PR review feedback processing.
What's Inside
Slash Commands10
Zoom Out
/zoom-out
Draw a higher-level system map of unfamiliar code in the project's domain vocabulary. Describes the module's responsibility, callers, dependencies, and sibling modules without diving into implementation details.
Execution
/review
Execute peer LLM reviews using the consulting-peer-llms skill
Commit
/commit
Create a git commit using the managing-git-workflow skill
Pr
/pr
Create a pull request using the managing-git-workflow skill
Push
/push
Push changes to remote using the managing-git-workflow skill
Agents4
resolving-pr-blockers
/resolving-pr-blockers
Resolves all PR blockers — CI failures, merge conflicts, and review feedback. Scans the current branch's PR, detects blockers, dispatches specialized sub-agents, and pushes once all are resolved. Use when user says "fix my PR", "CI failed", "resolve conflicts", "fix the build", "handle review comments", "PR won't merge".
merge-conflict-resolver
/merge-conflict-resolver
Resolves merge conflicts by fetching the target branch, identifying conflicting files, and applying the autofixing-and-escalating skill to classify each conflict as obvious or ambiguous. Called as a sub-agent from resolving-pr-blockers orchestrator.
ci-failure-resolver
/ci-failure-resolver
Analyzes and fixes CI workflow failures by extracting logs from failed GitHub Actions runs, parsing error patterns, and applying the autofixing-and-escalating skill. Called as a sub-agent from resolving-pr-blockers orchestrator.
pr-review-feedback
/pr-review-feedback
Processes PR review comments — classifies feedback as obvious or ambiguous using the autofixing-and-escalating skill, auto-fixes obvious items, discusses ambiguous items with rationale and recommendation. Called as a sub-agent from resolving-pr-blockers orchestrator.
Skills18
applying-coding-baseline
/applying-coding-baseline
Applies a curated, pre-vetted set of baseline behavioral discipline rules (Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution, Fail Fast vs Graceful Handling, Documentation Priority) to coding agent directive files such as CLAUDE.md, AGENTS.md, and their referenced documents. Replaces semantically similar existing content with the standard canonical wording so coverage stays complete and consistent. Use whenever the user wants to seed a new project's directive files, supplement an existing CLAUDE.md/AGENTS.md with baseline coding discipline, normalize ad-hoc rules to canonical wording, or audit a repo against the standard set. Trigger phrases include "apply baseline rules", "install coding baseline", "supplement CLAUDE.md with standard rules", "seed AGENTS.md with discipline directives", "add baseline coding rules", "normalize agent directives". Skips guarding-agent-directives verification because the rule set is already pre-vetted.
autofixing-and-escalating
/autofixing-and-escalating
Classifies issues from external sources by clarity of correctness, auto-fixes obvious ones, and escalates ambiguous ones with rationale and recommendations. Activates automatically whenever 2+ actionable items from an external source appear — linter output, review comments, security scan results, test failures, audit findings, or any batch of issues that were not generated by the current conversation. The user should never have to manually sort through obvious vs ambiguous items from tools or reviewers.
building-shared-vocabulary
/building-shared-vocabulary
Maintains a project's domain glossary in CONTEXT.md and architecture decisions in docs/adr/ as living artifacts — files are created lazily, updated inline as terms resolve and decisions crystallize, and conflicts with existing entries are surfaced immediately. Use this skill whenever a domain term is being pinned down, a decision sounds ADR-worthy, or vocabulary is about to drift — phrases like "domain glossary", "context.md", "we should write this down", "let's name this", "what do we call this", "is this worth an ADR", "pin down this term" — and as a side-effect of grilling-plans when terms or decisions surface.
bumping-version
/bumping-version
Bump a project's version with changelog update — auto-detects version files (plugin.json, package.json, pyproject.toml, Cargo.toml, gemspec, VERSION, ...). Use when user says "bump", "version up", or "release". Per-repo policy (base branch, extra files, commit message) read from CLAUDE.md / AGENTS.md.
consulting-peer-llms
/consulting-peer-llms
Execute peer reviews from other LLM CLI tools (Gemini, Codex, Claude) in parallel and synthesize actionable insights. Use when user requests feedback from other LLMs, peer review, or external validation — e.g., "get feedback from gemini", "ask codex to review", "ask claude to review", "peer review this", "what do other LLMs think", "get a second opinion", "validate with codex".
MCP Servers2
Stats
Version1.13.2
LanguageShell
Stars0
MaintenanceExcellent
LicenseMIT
Last Commit
Added
Available In
Safety Signals
Caution
Uses power tools
Uses Bash, Write, or Edit tools
Tags
Categories
