Claude Skills by bengous

github.com/bengous

42 skillsA× 41B× 11 installs38 views

Adversarial ReviewAAdversarial review by Codex (OpenAI) of local git changes, either the uncommitted work or the current branch against a base ref, with optional focus text. Codex runs read-only; each finding names a file, a line range and a concrete fix, and the review ends with a SHIP or NO-SHIP verdict. Use when the user asks Codex to review, challenge or attack their uncommitted changes, their diff or their branch before shipping.toolsgoshellVotes: 0GitHub stars: 4
Codex OrchestrateAClaude Code only. Use when the user explicitly invokes /agents-bridge:codex-orchestrate (or /codex-orchestrate) in Claude Code or asks Claude to orchestrate a large multi-slice plan by delegating implementation to the Codex CLI through agents-bridge. In native Codex, use $slice-runner instead.toolsgoshellVotes: 0GitHub stars: 4
CodexAInvoke the OpenAI Codex CLI for cross-model collaboration, a second opinion, or delegated work. Use when the user asks Codex to review, debug, explain, plan or implement something, or names a Codex model.toolsgoshellVotes: 0GitHub stars: 4
CritiqueACritical second opinion from Codex (OpenAI) on a proposal Claude just made — confirms what is sound, challenges what is genuinely weak, and suggests a better path with clear reasoning when one exists. Constructive, not contrarian. Use to cross-check a Claude design, refactor, API, or fix with a non-Claude model before acting on it.toolsgoshellVotes: 0GitHub stars: 4
ImagegenAGenerate or edit images with the Codex CLI's built-in image_gen tool. Use when the user asks to create, generate or draw an image, icon, logo, favicon, illustration or mockup, or to edit an existing image file — restyle, retouch, upscale, add or remove elements.toolsgoshellVotes: 0GitHub stars: 4
Pair PlanningBStart a session in pair-planning mode where Claude and Codex (read-only) each draft an independent implementation plan for a task, then cross-review through an open-point ledger until consensus, escalating remaining disagreements to the user. Produces one agreed plan; does not write code. Use at the start of a task to align two frontier models on the approach before implementation.toolsgoshellVotes: 0GitHub stars: 4
Skills DirectorySkills Directory Look up any of 103,619 scanned skills — grade, score, and every finding. Free.Check a skill
Greenfield AuditARead-only architecture audit that grants the existing code no authority: derive the requirements, design the minimal from-scratch architecture, then classify every important component KEEP / SIMPLIFY / REPLACE / DELETE. Diagnostic in the chat, no file edited.toolsgobashVotes: 0GitHub stars: 4
Null As Error CcAAudit an Effect codebase for silent error swallowing -- catchAll patterns that collapse errors into sentinel values (null, [], false, void) in the success channel. Runs a scanner script, spawns a read-only auditor, and produces a classified report. NOT for: non-Effect projects, React/frontend code, plain TypeScript without Effect.toolstypescriptbashVotes: 0GitHub stars: 4
Refactorlib CcAAudit a codebase for handcrafted code that duplicates functionality already available in the project's dependencies. Reads package.json, launches parallel exploration agents, verifies replacement feasibility, and produces a structured refactor plan. Audit only -- does not execute changes.toolsbashnodeVotes: 0GitHub stars: 4
Structured PlanARigorous planning workflow with research validation, task breakdown, dependency mapping, and post-implementation verification. Use when: (1) planning complex features touching 5+ files, (2) architectural changes or major refactors, (3) unfamiliar tech requiring doc research, (4) user says "thorough plan", "rigorous plan", or "structured plan". Invoke with /structured-plan before or during plan mode.toolsgodocumentationVotes: 0GitHub stars: 4
ShipAShip a feature branch: prepare a clean PR (strip working files with intelligent suggestions), create/update the GitHub PR, then merge to main with GPG signing when ready. Detects lifecycle stage automatically. Use when: "ship", "prep pr", "create pr", "open pr", "merge to main", "submit for review", "push for review", "ship this branch".toolsbashgitVotes: 0GitHub stars: 4
Meta PromptATurn a rough request or the preceding conversation into a clean prompt for another agent, carrying the user's intention at the user's level of certainty. Use when the user asks to write a prompt, meta-prompt, briefing, or handoff for a separate agent session, or wants to delegate a task just discussed to a fresh instance.toolsgoexpressVotes: 0GitHub stars: 4
Clean CommentsAAudit and clean code comments with four actions: REFACTOR (comment compensates for unclear code), KEEP (why / external constraint / trap), REMOVE (paraphrase, decorative banners), FIX-VERIFY (factual claim checked against the code). Protects why and constraint comments; hunts comments that lie — stale cited paths, wrong hard-coded numbers, guarantees the code refutes. Use when the user wants to clean, audit, review or deslop comments, remove comment slop, or suspects stale or misleading comme...toolsgobashVotes: 0GitHub stars: 4
Verify No RegressionsAVerify no behavioral regressions after implementation. Spawns parallel subagents for semantic diff review while the test suite runs. Use when: user says "verify no regressions", "check for regressions", "make sure nothing broke".toolsbashgitVotes: 0GitHub stars: 4
Agent Docs DriftAAudit agent instruction files (CLAUDE.md, AGENTS.md, .claude/rules/) against the commits since any of them last changed, then propose updates each motivated by a committoolsbashVotes: 0GitHub stars: 4
Context AuditAAudit and improve CLAUDE.md, AGENTS.md and .claude/rules/ for instruction budget, anti-patterns and stale references, then apply approved REMOVE/MOVE/REWRITE/ADD fixestoolsgobashVotes: 0GitHub stars: 4
Revise Claude MdACapture this session's learnings (commands, gotchas, patterns) into CLAUDE.md or .claude/rules/toolsgobashVotes: 0GitHub stars: 4
Git SweepAClean stale git branches and worktrees interactively. Audits local/remote branches, proves which ones the base already contains (including after a squash or rebase), frees finished worktrees, and confirms before deleting. Use when: "git sweep", "sweep branches", "branch cleanup", "prune stale branches", "clean up agent worktrees".toolsbashgitVotes: 0GitHub stars: 4
CommitACommit the current work with a message that follows the repo's convention, closing the branch's issue when its name carries a number. Use when the user asks to commit, to record the work, or to save a change to history.toolsbashgitVotes: 0GitHub stars: 4
RebaseAInteractive rebase of the current branch with a visual plan and reworked commit messages, no editor. Use when the user asks to rebase, rewrite, reorder, reword, or clean up commits, or to continue, skip, or abort a paused rebase.toolsgobashVotes: 0GitHub stars: 4
SquashASquash git commits by pattern, hash list, or the last N, without opening an editor. Use when the user asks to squash, fold, or combine commits, or to collapse fixup and WIP commits.toolsbashgitVotes: 0GitHub stars: 4
Await MergeAWait for a PR's checks, merge it with linear history, update the local base branch.toolsbashgitVotes: 0GitHub stars: 4
Commit Push PrACommit the current work, push the branch, then open or update its pull request.toolsgitVotes: 0GitHub stars: 4
DispatchAHand ready GitHub issues to issue-worker subagents that implement, verify and open their own pull request, one worker per issue. Use when the user asks to dispatch, assign, or hand issues to agents, or to turn issues into PRs.toolsbashgitVotes: 0GitHub stars: 4
IssueAWrite or rewrite a GitHub issue as a context-rich prompt for another agent. Proves the problem with evidence from the code, gives hints instead of a plan, ends with observable acceptance criteria. Use when the user asks to file, write, draft, open, or rewrite an issue.toolsgobashVotes: 0GitHub stars: 4
PrAOpen or update the pull request of the current branch with a body sized to the change and images attached through gh. Use when the user asks to open, create, submit, update, or rewrite a PR, or to push and open one.toolsgobashVotes: 0GitHub stars: 4
ShiftARun one pass of the issue-to-PR loop: triage the open issues, dispatch the ready ones to agents, keep the loop's pull requests green, and return a digest. Use when the user asks to run a shift, to work the backlog on its own, or to run the issue loop.toolsgobashVotes: 0GitHub stars: 4
Stacked PrsARun a stack of pull requests on GitHub with `gh stack`: create, grow, submit, sync, land, repair, and cut a per-layer worktree with its handoff. Use when the user talks about stacked PRs, a stack or pile of PRs, `gh stack`, wants to split a large change into reviewable PRs that land together, or debugs a stack (empty PR "No commits between X and Y", "Needs rebase", local/GitHub divergence, a commit stuck under someone else's).toolsgoshellVotes: 0GitHub stars: 4
TriageAVerify an open GitHub issue or PR against the current code and act on the verdict: close or comment with a factual proof, or report work that is still valid. Use when the user asks to triage, verify, check, handle, or clean up an issue, a PR, or the tracker.toolsgobashVotes: 0GitHub stars: 4
GoalifyAConvert rough coding, product, architecture, audit, review, migration, cleanup, debugging, or orchestration intent into the smallest useful goal payload to hand to a fresh Claude Code agent (a new session, a subagent, or /loop). Invoke with /goalify, or "/goalify interactive" to be questioned one point at a time before the goal is written. Produces goal text only, never the downstream implementation.toolsgodebuggingVotes: 0GitHub stars: 4
Mermaid DiagramsACreate Mermaid diagrams. ONLY use when user explicitly says "Mermaid". NOT for general diagrams, schemas, ASCII art, or wireframes.toolsgonodeVotes: 0GitHub stars: 4
Layer TestingAGenerate comprehensive tests for architectural layers with coverage-first analysis. Use when testing specific layers (core, domain, application, infrastructure, boundary). Reads testing strategy from playbook or uses interactive template selection.toolstypescriptgoVotes: 0GitHub stars: 4
UsageAShow plugin-cache-sync status and explain sync workflowtoolsbashVotes: 0GitHub stars: 4
Linear FlowAMigrate a repo to the dev-trunk/main-release fast-forward model (no merge commits) and load its doctrine. One-shot setup; day-to-day rules live in each repo's CLAUDE.md afterwards.toolsgitVotes: 0GitHub stars: 4
Submodule SetupAThis skill should be used when the user asks to "set up submodules", "migrate branches to submodules", "automate submodule sync", "create submodule architecture", "convert branches to repos", or mentions setting up git submodules with GitHub Actions automation for multi-repo synchronization.toolsbashgitVotes: 0GitHub stars: 4
Search Claude DocsASearch the official Claude Code docs through the claude-code-docs MCP server with progressive disclosure, and date a behavior with the changelog.toolsshellgitVotes: 0GitHub stars: 4
Cli DesignACreate distinctive, user-respecting command-line interfaces with exceptional UX. Use this skill when the user asks to build CLI tools, scripts, or terminal applications. Generates well-crafted CLIs that follow platform conventions and treat users as humans, not machines.toolsgoshellVotes: 0GitHub stars: 4
Excellence Skill CreatorACreate opinionated, anti-slop skills that encode taste. Use when the user wants a skill that makes Claude less generic in a domain, in the style of frontend-design, cli-design or system-architecture. NOT for: general skill structure, reference guides, procedural docs (use skill-creator instead).toolsgosqlVotes: 0GitHub stars: 4
IaqiAIteratively improve artifacts via parallel reviewers with anchor-based drift prevention. NOT for: one-shot edits, simple fixes, tasks without measurable quality. USE for: skills, prompts, commands, agents needing iterative refinement with score targets. Triggers: "iterate to 9.0", "quality loop", "IAQI", "reviewer loop", "improve until threshold", "iterative quality".toolsgoexpressVotes: 0GitHub stars: 4
System ArchitectureADesign systems with appropriate complexity—no more, no less. Use this skill when the user asks to architect applications, design system boundaries, or make structural decisions. Generates pragmatic architectures that solve real problems without premature abstraction.toolsgosqlVotes: 0GitHub stars: 4
StartAWrite a plan the way its reviewer reads it: open choices settled first, the plan ordered by what the reviewer is most likely to change, interfaces and files before mechanics, vertical slices each closed by a check, then a fresh session to implement. Use when a design choice is open, the change crosses several modules or interfaces, a refactor reshapes a contract, or the user asks for a thorough plan or a frontier plan. Not for a change you can describe in one sentence.toolsgoshellVotes: 0GitHub stars: 4
StopALeave the vellum planning mode without a plan. The working directory is kept, the review server stops, and file writes outside that directory are unlocked. Only the reviewer runs it.toolsVotes: 0GitHub stars: 4