Copybook中文Search

Recently added

  1. Rules

    Pixel art rendering rules for CLAUDE.md

    Pixels crisp in your sprites but blurry on screen: textures on Nearest, whole-number scaling, camera and sprites rounded alike.

Older dates
  1. Skill

    Coordinator skill for Claude Code and Codex

    For work that takes several agent sessions, a coordinator runs Claude and Codex in Herdr and checks changes before release.

    4 more tips from this day

    Prompt

    Screenshot-first UI rebuild prompt

    UI hierarchy and density problems: every page screenshotted, then rebuilt on only a spacing scale, type scale and up to 5 colors.

    Prompt

    Open-Source Scout and Closer prompts

    Unfamiliar features written from scratch, offers to continue: GitHub searched first, then the whole job done and a plain recap.

  2. Skill

    /learn-taste: design corrections as rules

    You keep fixing the same design mistakes: each correction in a session turned into a strict rule with reasoning.

  3. 1 more tip from this day

    Prompt

    Happy-path debt, found and fixed

    Screens that only work when data loads fast and nothing fails: missing states and layout breaks fixed per component, design kept.

  4. Prompt

    Vibe-coding cleanup: 5 Codex /goal prompts

    Half your quota left at reset: dead code, duplicates and unneeded dependencies cut; scheduled tasks and old worktrees sorted.

    3 more tips from this day

    Rules

    Old-rules review for Fable 5.2

    Rules hard-coded for older models work against Fable 5.2: delegation, think-less, style-limit and ‘never’ lines quoted with a fix.

  5. Prompt

    Market read before you build

    Advice with no research behind it: 25-40 competitors indexed, recurring complaints ranked, then where your direction will die.

    2 more tips from this day

    Subagents

    /advisor: Sonnet 5.5 works, Opus on call

    $20 plan on Opus 5.5 by default: Haiku reads code, looks up docs; Opus advises before plans, on repeat errors, before ‘done’.

    Prompt

    Untangle /goal for spaghetti code

    Months of vibe coding left the code in knots: an HTML wiring diagram, the worst numbered in red, then fixes tested one by one.

  6. 1 more tip from this day
  7. Prompt

    Clickable repo map with words vs names

    What you call a module isn’t what the code calls it: every mismatch marked in red, those likeliest to cause a wrong edit first.

  8. Rules

    Decision page rule for long tasks

    A summary saying all went well hides the agent’s choices: one screen of the ones that change the result, those to confirm in red.

    1 more tip from this day

    Rules

    Situation routing rules for skills

    Your agent often forgets to use what you install, so you call each by name: the best fit per task, with one line on which and why.

  9. Prompt

    Perf review: the 5 slowest spots

    Ask for faster code and you probably get a cache: timings from a profile, one matching fix each, its lines and expected speedup.

  10. Prompt

    CI time audit: 150 runs, 9 checks

    Code takes minutes, then each PR waits on CI: the 5 slowest jobs split into queue, setup and run, and the line to change per fix.

    3 more tips from this day
  11. 63 more tips from this day

    Plugin

    Mod request for Claude Code itself

    Something in Claude Code’s interface you want changed: a prompt that finds an existing Mod or proposes the smallest one.

    Skill

    Hallmark: audit and redesign AI-looking pages

    A tiny label above every heading gives AI away: one command lists what’s wrong with a page, another rebuilds it, content kept.

    Rules

    Bug-score rule for Astra’s code reviews

    Astra flags bugs that almost never happen and Opus fixes each one: bugs scored, low scores filed as issues, code left alone.

    Prompt

    Camera moves to name in video prompts

    Opus 5.5 videos that look like a slideshow: six camera moves by name with what each one does, plus seconds and speed to add.

    Subagents

    Pre-launch check: 6 legal traps

    Zero sales and you can still be sued: under-13s, Google fonts, session replay, marketing email, renewal terms, DMCA, all fixed.

    Skill

    TasteSkill v2 AI-look check

    Pages that look AI-made at a glance: every tell at desktop, tablet and phone widths, FAIL before WARN, code untouched.

    Prompt

    Logging plan and daily fix list

    Broken features, stuck users, slow steps: ranked by users affected, with log lines; the worst one already has a test.

    Prompt

    Plan review: 5 methods in one message

    Plan written, no code yet: one message for first principles, adversarial review, ablation, Occam’s razor and loose coupling.

    Prompt

    4 starting points for a code-only animation

    An animation you love, a one-line idea, a character image or an art style: a prompt for each, one HTML file rendered, plus sound.

    Skill

    Herdr app: Opus 5.5 coordinating workers

    Running more agents without leaving Claude Code: Opus 5.5 coordinates up to 10 workers through Herdr, and a Codex worker reviews.

    Plugin

    Ponytail 5: reuse what exists before writing

    Your agent hand-builds what’s already there: the repo, standard library, browser and installed dependencies checked first.

    Config

    Fable main, Opus subagents: 3 settings

    Fable quota going fast: 3 settings send reading and lookups to half-price Opus subagents; Fable keeps the judgment.

    Prompt

    Disk map of dev leftovers

    Disk almost full: a read-only scan, a treemap of what development left behind, and a cleanup script only for what you tick.

    Prompt

    Mod ideas from your last 20 sessions

    Requests you repeat, commands you stop or undo, how you check changes: ranked by how much each would help, your words quoted.

    Prompt

    README rewrite prompt and Impeccable polish

    Codex and Claude Code slowly turn your README into a changelog: what it is and who it’s for first, history in CHANGELOG.md.

    Prompt

    Code and direction review prompts

    Code too complicated, or busy a long time with no clear direction: one finds what needn’t exist, one rechecks the direction.

    Prompt

    One line against AI prose

    ‘It’s not X, it’s Y’ is gone and it still reads like AI: Anthropic’s Fable 5.1 guide has a more direct one-line prompt.

    Rules

    3 checks before installing a skill

    Someone put 314 malicious skills on ClawHub: check the source, scan the code, question the permissions, in under five minutes.

    Plugin

    Claude’s official security plugin

    Three lines before something goes wrong: agents sweep the repo, three more try to knock each finding down, two must agree.

    Prompt

    Skill score with yes/no questions

    Did the skill edit help: 10 real tasks, 8 yes/no questions, a blind judge subagent; keep only a fix that raises the score.

    Prompt

    Awwwards scoring loop

    A quality bar for the site it builds: each round screenshotted, scored on the Awwwards sheet, until every category hits 7.5.

    Prompt

    7 role prompts from idea to done

    Still walking a senior AI through every step: tech lead, requirements, debugging, performance, frontend, backend, reviewer.

    Prompt

    6 ChatGPT photo prompts

    A finish you’d pay a photographer for: headshot, cinematic still, travel, magazine shoot, old-photo repair, golden hour.

    Prompt

    Goal wrapper and 5 prompts built on it

    One preference typed in three places: a goal wrapper, plus prompts for components, parallel runs, review, states and corrections.

    Config

    Grok Bot team of 6 roles

    Which work deserves its own Bot: six roles with ownership, handoffs and limits, and what stays a Skill or a routine.

    Rules

    Two AGENTS.md lines: less text, UX/DX/AX

    Taglines, helper text and labels on every screen: one line cuts them so the layout speaks for itself; one weighs UX, DX and AX.

    Prompt

    Unslop prompt for pages that look AI-made

    Pages that scream AI at first glance: every slop sign listed, a five-line direction for your OK, then fixes pass by pass.

  12. 25 more tips from this day

    Prompt

    Pre-launch site check: 20 page items

    A vibe-coded site about to go live: design, mobile, every state, real-user flows and launch details, fixed in one pass.

    Plugin

    OpenAI’s Game Studio plugin for Codex

    Browser games with Codex: 9 skills for 2D and 3D, animation, models, menus and health bars; it plays the result to find bugs.

    Subagents

    4-person motion video team

    A motion video in Claude Code: breakdown, storyboard and review subagents around a main session on HyperFrames; you direct.

    Subagents

    /advisor: Opus 5.5 works, Fable on call

    Fable quota idle while Opus 5.5 does the work: Fable called in before a plan, when an error repeats and before ‘done’.

    Skill

    awesome-design-md and the shadcn skill

    Pages still look like default shadcn: a Stripe or Linear style DESIGN.md, every component restyled, a design system page too.

    Command

    REA: take apart another app’s feature

    A feature you like and can’t see how it’s built: taken down layer by layer, each finding with evidence, then a plan for your own.

    Prompt

    Pre-launch check: 4 test subagents

    Try to break it yourself first: 16 questions on security, data, flows and environment, issues ranked by severity, then fixed.

    Rules

    DESIGN.md from sites you like

    Pages look AI-made since Opus hasn’t seen what you like: 3-5 screenshots become a DESIGN.md; add taste-skill and Impeccable.

  13. 29 more tips from this day

    Prompt

    Slow-computer audit when agents run

    Many agents open and the Mac bogs down: a dry-run map of processes and startup items, cleaned only where you approve.

    Prompt

    Agent workspace audit

    Your agent feels dumber over time: every instruction, skill, MCP and memory marked KEEP or REMOVE, cleared on your OK.

    Subagents

    Luna Max as a Codex subagent

    Bounded delegated work at max reasoning: a luna_worker custom agent, checked against your Codex version, diff shown first.

    Skill

    Archify: system diagrams from code

    A system you have to explain: an HTML diagram you can search, trace up and downstream, compare across versions, export as PNG.

    Skill

    5 /goal prompts for leftover Codex quota

    Quota unused before it resets: a UI/UX audit, a clickable code map, measurable speedups, a workspace and a Codex cleanup.

    Prompt

    Blast radius, red team and 3 more prompts

    ‘Fix this bug’ hands you defaults: what your diff touches, an end-to-end goal, a red-teamed plan, a user walk, a thinking budget.

    Rules

    Clickable repo map

    Before you change a repo: click any module for its callers, dependencies, tests and source evidence; a rule keeps it current.

    Rules

    Think-carefully cleanup for Opus 5.5

    Opus 5.5 already thinks before it answers: rules that push extra thinking, dole out steps or stop to confirm, quoted with a fix.

    Connector

    codebase-memory MCP: an index of your repo

    Dozens of grep and read turns per question: the repo as one graph of functions, files and dependencies; dead code found too.

    Prompt

    HANDOFF.md for the next agent

    A task longer than one session: progress, decisions, files, checks and next steps kept current for the next agent.

    Prompt

    Fable 5 plans, Codex builds the backend

    Fable 5 burns tokens fast: planning and frontend stay with it, the backend goes to Codex by /goal; a redesign prompt too.

    Skill

    Herdr: Astra coordinating Claude Code workers

    Your Claude Code subscription, used from Codex: Astra runs up to 10 Opus workers through Herdr and hands them the heavy work.

    Prompt

    One question before it answers

    Ten questions at once get ignored: assumptions, missing info, the usual mistake, then the one question that changes its approach.

    Rules

    One AGENTS.md for Claude Code and Codex

    Two agents, one rules file: plan first, smallest change, subagent roles, own the bug, verify before done, Lessons per correction.

    Rules

    Orwell’s 6 writing rules for CLAUDE.md and AGENTS.md

    Banning AI words one by one never ends: 6 rules from 1946 for your global rules file, plus prompts for docs, PRs and reports.

    Skill

    Dashboard redesign: 2 skills, 2 prompts

    Dashboards that look AI-made on sight: ui-ux-pro-max and frontend-design in one redesign prompt, then a four-angle review.

    Prompt

    Component stress test in every state

    Sample data proves little: the real component rendered in every state that matters, fixed only where a failure reproduces.

    Config

    Opus 5.5 main model, medium subagents

    Usage that lasts longer: Opus 5.5 as main model, Opus 5.5 on medium as default subagent; hard-coded model IDs found first.

    Skill

    3 design skills for Codex

    Tired of ‘make it look better’: Impeccable, 21st Design and UX Audit turn it into specific changes, or one line with no skills.

    Prompt

    UI/UX audit as a senior designer

    A review with a designer’s authority: taste baseline, correctness fixed, cheap-looking parts found, big changes proposed.