All authors
Claude Skills by bendrucker
github.com/bendrucker111 skills1 installs202 views
- Never UsedA personal skill that never fires.Votes: 0GitHub stars: 17
- Prefer HeadersFixture exercising the prefer-headers rule across its boundary cases.Votes: 0GitHub stars: 17
- AuditAudit code comments for AI slop: restatement, narration/decision-log, self-praise, docstring-scope, and section-divider banners. Audits a diff (the comments a change introduced) or a whole repo, ranks by intrinsic complexity, fans out judging agents, and applies the trims to a fresh branch. Use when asked to audit, trim, or clean up code comments, or as the comment pass of a branch-finishing flow. Not a general code review: run it only on a change that introduces comments.Votes: 0GitHub stars: 17
- AttachAttach a local image or video to GitHub content so it renders inline in an issue, pull request, comment, or review. Use when attaching a screenshot, recording, or diagram to GitHub content.Votes: 0GitHub stars: 17
- CopilotGet a cross-model second opinion on a code change from GPT via the Copilot CLI, then triage what it finds. Use when the ask names GPT, Copilot, a second model, or a cross-model check, and as the cross-model pass on a change that clears the review gate.Votes: 0GitHub stars: 17
- StackPublish and merge GitHub native stacked pull requests with the `gh stack` extension. Use when a branch is stacked on another branch rather than the default branch, when linking a chain of branches into a stack on GitHub, or when merging a PR that belongs to a stack. Load before running any `gh stack` command.Votes: 0GitHub stars: 17
- JxaReference for writing JXA (JavaScript for Automation) scripts run through `osascript -l JavaScript`. Covers the JavaScriptCore ES5 constraints, `run(argv)`, and the `Application()` bridge.Votes: 0GitHub stars: 17
- ImageGenerate a meme by overlaying text on an image. Use when asked to make a meme, caption an image, add meme text, or produce classic Impact macros, TV-subtitle stills, white-bar captions, or multi-label formats (Drake, distracted boyfriend, whiteboard).Votes: 0GitHub stars: 17
- CodeReview the current diff for correctness bugs and reuse/simplification/efficiency cleanups at a given effort level. Use for "review my changes", "review the diff", "find bugs in my changes", or as the correctness pass before opening a PR. Low/medium surface fewer, high-confidence findings. High and xhigh broaden coverage and may include uncertain findings. Pass --fix to apply the findings to the working tree after the review.Votes: 0GitHub stars: 17
- Follow UpFollow up as the reviewer on a PR/MR you reviewed: did the author's fixes actually grasp each concern you raised, or just go through the motions? Finds silently resolved or mechanically-fixed threads and returns a graded re-review call. Use when you left review comments and want to verify the author acted on them before re-approving. Triggers: "did they fix my review comments", "re-review this PR", "check whether the author addressed my feedback".Votes: 0GitHub stars: 17
- InboxDispatch inbound pull request reviews as background sessions that collect in `claude agents`. Use when reviewing multiple PRs, checking the review queue, batch reviews, or managing your review inbox across GitHub and GitLab. Pass --queue to dispatch an already-ordered queue.Votes: 0GitHub stars: 17
- CreateWrite a technical specification for a feature or project from product requirements.Votes: 0GitHub stars: 17
- ReviewReview an existing technical specification for gaps, risks, and missing considerations.Votes: 0GitHub stars: 17
- AnalyzeCurate the writing plugin's trope ruleset by auditing wordlist entries against session history and surfacing candidate phrases. Use when refreshing trope detection, reviewing wordlist health, or mining sessions for new AI-writing patterns to add or stale rules to remove.Votes: 0GitHub stars: 17
- No DiaryCut slop, jargon, process narration, past states, session leakage, and provenance from a deliverable (PR or MR body, code comment, doc, skill, review comment, issue, plan) so it states the result rather than how the work happened. Use when asked to de-slop, de-jargon, trim, shorten, or cut down one of those, or when told that one reads as slop or runs too long.Votes: 0GitHub stars: 17
- ReviewReview a document through specialized lenses using parallel agents. Use when reviewing documentation, blog posts, READMEs, proposals, or any prose for quality issues across content, style, and embedded artifacts.Votes: 0GitHub stars: 17
- RewriteRewrite a draft message, explanation, or note to strip AI voice, slop, and filler while preserving meaning. Use to polish functional prose before sending.Votes: 0GitHub stars: 17
- ScanDetect AI writing tropes in repository prose. Use `audit` to scan a directory or glob (READMEs, docs, skill files, proposals) for slop already committed and gate on it, reporting every match with file, line, and column. Use `score` to measure trope density of one input on a per-1000-word basis, compare two drafts, or score code comments separately. Not for rewriting a single input.Votes: 0GitHub stars: 17
- AfkSignal that you are stepping away so the agent keeps working without stalling on prompts. Drives the current task to completion, batches reversible decisions behind safe defaults, raises only irreversible ones via push, and defers bandwidth- or power-heavy work when tethered, on battery, or lid-closed. Use via /afk or /afk <duration>.Votes: 0GitHub stars: 17
- Agent BrowserReal-browser automation via the `agent-browser` CLI. Use when a task needs an actual browser — navigating pages, filling forms, clicking, taking screenshots, scraping or extracting page data — or for exploratory testing, QA, and dogfooding of web apps. Pulls version-matched workflow instructions from the CLI itself.Votes: 0GitHub stars: 17
- AskShorthand to make Claude convert a wall of prose into structured questions via the AskUserQuestion tool. Invoke with /ask.Votes: 0GitHub stars: 17
- Diagnosing BugsFind the cause of a reported failure by first building a command that reproduces it. Use when the user reports something broken, failing, throwing, hanging, or slower than it was, or points at a red CI, pipeline, or lint job.Votes: 0GitHub stars: 17
- FlightsSearch flights from a natural-language request, using Google Flights for market context and united.com for what United will actually sell. Compares cash against miles, explores flexible date and routing shapes, and reports a ranked shortlist with deep links. Reads only. Never books. Use via /flights.Votes: 0GitHub stars: 17
- Github TriageClear Dependabot and bot noise from your GitHub notification inbox: mark settled merged and closed PRs done, merge green dependency PRs in repos you maintain, dismiss low-value ones, and leave only real human threads behind.Votes: 0GitHub stars: 17
- GrillingInterrogate a plan, decision, or idea round by round until every open decision is settled and nothing is silently assumed. Use when the user says grill me, grill this, stress-test this, poke holes in this, or wants their thinking interrogated before committing to it.Votes: 0GitHub stars: 17
- HerdrDrive the herdr terminal workspace manager: inspect workspaces, tabs, and panes, hand work to sibling coding agents in other panes (distinct from in-session `Agent` subagents), split panes for collaborative file viewing or long-running processes, and correlate panes to Claude sessions. Load this when the decision to hand a task to another pane's agent arrives mid-task, and when opening a file alongside the user, starting a dev server or log tail the user should watch, capturing another pane's...Votes: 0GitHub stars: 17
- JobDaily routines for a corporate software engineering job. Start mode triages the inbound review queue, your own open PRs, and the issue tracker's plan for today. End mode clears the outbox, surfaces review debt, sweeps worktrees for unpushed work, and tidies tracker state for tomorrow. Use via /job, /job start, /job end, or /job setup.Votes: 0GitHub stars: 17
- LeadLead a multi-PR project: scope issues into pull requests, dispatch with herdrVotes: 0GitHub stars: 17
- ModernizeSurvey a project for ways to adopt newer language and major-dependency features that did not exist when the code was written, replacing boilerplate with modern idioms. Use when the user wants to modernize a codebase, adopt new language features, retire dependencies the stdlib now subsumes, or catch a project up to current framework APIs.Votes: 0GitHub stars: 17
- ScheduledReconcile repo-local launchd agents for scheduled Claude Code runs, grouped by machine. Use via /scheduled, /scheduled setup, /scheduled sync, /scheduled list, /scheduled status, or /scheduled run <label>.Votes: 0GitHub stars: 17
- ShipFinish a branch: infer which review passes the change warrants, run them, open the PR, babysit CI to green, triage bot comments, and refresh the body from a clean context.Votes: 0GitHub stars: 17
- Show MeExplain the current topic or a proposed design visually with types and signatures, pseudocode, a call tree, a component tree, a file tree, a diff, a whole block, a Mermaid diagram, or a published Artifact.Votes: 0GitHub stars: 17
- TddTest-driven development. Use when building a feature or fixing a bug test-first, when the user asks for red-green-refactor, or when a change needs its tests written before its implementation.Votes: 0GitHub stars: 17
- TwinEntry skill shadowed by a personal skill of the same name.Votes: 0GitHub stars: 17
- A Personal Skill Whose Name Runs All The Way To The Sixty Four CA personal skill whose name occupies the full 64-character budget.Votes: 0GitHub stars: 17
- TwinPersonal skill claiming a bare name a plugin entry skill also wants.Votes: 0GitHub stars: 17
- Typed OnlyA personal skill the model never loads and the user only types.Votes: 0GitHub stars: 17
- PromptingWrite a document a model executes: a product prompt, a system prompt, a skill, a tool or agent description, a CLAUDE.md or AGENTS.md, a reference file behind a pointer. Use when authoring or revising any of those, when deciding what belongs in a prompt versus behind a pointer, when a prompt produces different behavior from run to run, or when a prompt makes the model take the wrong approach.Votes: 0GitHub stars: 17
- ScanReport prompt defects a lexical scan finds in documents a model executes. Use to audit a repository's skills, CLAUDE.md, agent definitions, or a product's prompt files, or to gate them in CI or a pre-commit hook.Votes: 0GitHub stars: 17
- HumanRequest Ben's own review of the working diff or a document before it leaves the machine, for architecture and slop rather than bugs. Runs after the mechanical passes (review:code or simplify, comments:audit). Use for "get my review", "let me look at this first", or as the last pre-PR pass.Votes: 0GitHub stars: 17
- BruhSay the last message again in plain language and shorter, like one person talking to another.Votes: 0GitHub stars: 17
- FlockCoordinate every pane, worktree, and pull request open across the herdr server: close out what has landed, merge what has cleared the bar, and report what needs you. One flock per machine. Use via /flock.Votes: 0GitHub stars: 17
- Grill DocsRun the grilling interview and write each settled term and decision to the repo as it settles, so they survive compaction or an abandoned session.Votes: 0GitHub stars: 17
- Component Change DiffBoth charts are dumb — they just render whatever `data` they're handed. The single choke point is one hook call in the dashboard page. **Component tree:** ``` Dashboard (src/pages/Dashboard.tsx) ├── Header ├── RevenueChart ← props: any, just renders data={revenue} ├── SignupsChart ← props: any, just renders data={signups} └── RecentOrders ``` **Where the 30-day lock-in lives today** — `src/pages/Dashboard.tsx:8`: ```tsx const { revenue, signups } = useMetrics({ days: 30 }); ``` `useMetric...Votes: 0GitHub stars: 17
- Declined Card```mermaid sequenceDiagram participant Route as route.ts participant Checkout as checkout() participant Inv as inventory.holdInventory participant Gateway as gateway.authorize Route->>Checkout: checkout(cart) Checkout->>Inv: holdInventory(items) Inv-->>Checkout: hold Checkout->>Gateway: authorize(customerId, total) Gateway-->>Checkout: throw CardDeclinedError("insufficient_funds") Checkout->>Inv: releaseInventory(hold) Checkout-->>Route: rethrow CardDeclinedError Route-->>Route: catch → 402 {...Votes: 0GitHub stars: 17
- Design OrderSmall CLI, JSON-file store — tags fit as a `string[]` on `Note`, parsed from repeated `--tag` flags. **Type change** ```diff export interface Note { id: number; text: string; createdAt: string; + tags: string[]; } ``` **File tree** ```diff src/ ├── cli.ts ├── commands/ │ ├── add.ts │ ├── list.ts +│ └── tags.ts # new: `notes tags` — count per tag └── store/ └── notes.ts ``` **cli.ts — route the new command, split flags from positional args** ```diff import { add } from "./command...Votes: 0GitHub stars: 17
- File RolesIt's a small Bun/TypeScript CLI with a clean layered structure: **Entry point** - `src/cli.ts` — parses `process.argv` and hands off to `run()`. The whole app in 4 lines. **Commands** (CLI-facing logic) - `src/commands/parse.ts` — turns raw argv into a typed `Command` union: `add`, `balance`, or `export`. - `src/commands/run.ts` — the dispatcher. Loads entries from disk, builds a `Ledger`, executes the matching command (add/print balance/export CSV), persists if needed. **Domain model** - `sr...Votes: 0GitHub stars: 17
- Plugin Loader DesignLooked at the existing structure — it's a minimal `Command` interface (`{ description, run(args) }`) statically registered in `src/commands/index.ts` and dispatched from `src/cli.ts`. Here's the design I'd propose for letting third-party packages register commands via node_modules.Votes: 0GitHub stars: 17
- Pseudocode LogicThis is a per-key token bucket (`src/limits/middleware.ts` + `src/limits/bucket.ts`). ```text rateLimit(req) key = req["x-api-key"] header, else "anonymous" cost = GET → 1, else → 3 allow(key, cost) ? yes → pass request through no → 429 "slow down" allow(key, cost) bucket = buckets[key], or {tokens: 20, updatedAt: now} if new elapsed = now - bucket.updatedAt bucket.tokens = min(20, bucket.tokens + elapsed * 5/sec) # refill bucket.updatedAt = now if bucket.tokens < cost save bucket return ...Votes: 0GitHub stars: 17
- Request FlowThis is a small custom TypeScript dispatcher (no Express/Nest) — `src/server.ts` maps the string key `"POST /orders"` straight to a handler function, no middleware layer. ```text handleCreateOrder(req) src/routes/orders.ts:3 parses { customerId, items } from JSON body createOrder(customerId, items) src/orders/create.ts:7 validateCart(items) src/orders/validate.ts:1 priceOf(sku) src/orders/validate.ts:7 reserveSto...Votes: 0GitHub stars: 17