Agent skill

Hai Razor

by hylarucoder in hylarucoder/hai-stack

Tests whether each requirement, step, role, field, state, module, layer, abstraction, or rule deserves independent existence, then classifies it as Keep, Merge, Defer, Delete, Replace, or Prove first.

Custom licenceAuto-check passedProduct & Project Management

Install Hai Razor

skills CLI
$ npx skills add hylarucoder/hai-stack --skill hai-razor -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install hylarucoder/hai-stack hai-razor --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/hylarucoder/hai-stack.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/hai-razor .claude/skills/hai-razor && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
hai-razor
GitHub stars
382
Token cost
~1.9k tokens
SKILL.md length
979 words
Files
5 (incl. references)
Skills in repo
18
Repo updated
First seen
Licence
Custom licence

At a glance

Tests whether each requirement, step, role, field, state, module, layer, abstraction, or rule deserves independent existence, then classifies it as Keep, Merge, Defer, Delete, Replace, or Prove first.

  • Works in 9 steps: Name the chain being cut. State the… → Gather evidence before judgment. Review… → Map the current chain when the cut is… → …
  • The explicit decision is what can be removed
  • SKILL.md covers Overview, Core Principle, Razor Targets and Classify Each Concept, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Hai Razor is an agent skill from hylarucoder/hai-stack. Tests whether each requirement, step, role, field, state, module, layer, abstraction, or rule deserves independent existence, then classifies it as Keep, Merge, Defer, Delete, Replace, or Prove first. Use when the explicit decision is what can be removed or collapsed(奥卡姆剃刀、砍需求、这个字段/状态/层有必要吗、是否过度设计). Use hai-prd to shape product requirements and hai-architecture to redesign module boundaries after the cuts are known.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `SKILL.zh_CN.md`, `agents/openai.yaml` and `references/llm-complexity-tells.md`).

It sits in Product & Project Management, covering PRD writing.

When your agent uses it

  • The explicit decision is what can be removed
  • Collapsed(奥卡姆剃刀、砍需求、这个字段/状态/层有必要吗、是否过度设计)

Example prompts

  • “Use the hai-razor skill to test whether each requirement, step, role, field, state, module, layer, abstraction, or rule deserves independent…”
  • “/hai-razor”

Workflow steps

9 steps, taken from the first numbered list in SKILL.md.

  1. Name the chain being cut. State the scope (PRD section, feature flow, data model, module
  2. Gather evidence before judgment. Review the PRDs, docs, code, schemas, traces, tests,
  3. Map the current chain when the cut is structural. Show before/after responsibility when a
  4. Run the deletion test. For each concept ask: if this disappears, what concretely breaks?
  5. Find the hidden owner. If the concept is removed, who must absorb its responsibility? If it
  6. Classify each concept using the decision table above. Give every concept exactly one verdict
  7. Protect necessary complexity. Explicitly name what should not be cut: complexity that prevents
  8. Attack the remaining design. Ask how future builders would reintroduce the deleted concept,
  9. Render only when requested. The default deliverable is Markdown. If the user explicitly asks

What it can do on your machine

Read from SKILL.md and the folder at commit a6c7ed2. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Hai Razor loads about 1.9k tokens when it runs, and up to ~5k if it reads all its reference files. Until then it costs about 107 tokens; SKILL.md has 979 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~107
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 979 words (~1,878 tokens).

“For Chinese readers, see SKILL.zh_CN.md. The English SKILL.md is the execution source of truth.”

— opening of SKILL.md by hylarucoder, Custom licence
name
hai-razor

Read the full SKILL.md on GitHub

Files

SKILL.md and 4 other files (references) in skills/hai-razor of hylarucoder/hai-stack.

  • SKILL.md
  • SKILL.zh_CN.md
  • agents/openai.yaml
  • references/llm-complexity-tells.md
  • references/output-template.md

Open the folder on GitHubat commit a6c7ed2

Compare with similar skills

Hai Razor next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Hai Razor compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Hai Razor this skillhylarucoder/hai-stack382—~1.9kAutomated safety check: PassCustom licence
CCPM Project Managementautomazeio/ccpm8.4k—~1.1kAutomated safety check: PassMIT
Ralph Tui Create Beadssubsy/ralph-tui2.5k1 repos~2.6kAutomated safety check: PassMIT
Trellis Brainstormanjiemo/SunnyBeach1787 repos~4kAutomated safety check: PassApache-2.0
Adversarial Speczscole/adversarial-spec5561 repos~8.3kAutomated safety check: NotesMIT
Ralph Tui Create Beads Rustsubsy/ralph-tui2.5k1 repos~2.8kAutomated safety check: PassMIT

Similar skills

  • Runs a spec-driven workflow from PRD to epic to GitHub issues to parallel agents, with status, standup and blocked-work reports from bundled scripts.

    8.4k GitHub stars~1.1k tokensUpdated 6 mo ago
    Product & Project ManagementAuto-check passed
  • Ralph Tui Create Beads

    subsy/ralph-tui

    Convert PRDs to beads for ralph-tui execution. An agent skill from subsy/ralph-tui.

    2.5k GitHub starsUsed in 1 repo~2.6k tokens
    Product & Project ManagementAuto-check passed
  • Trellis Brainstorm

    anjiemo/SunnyBeach

    Guides collaborative requirements discovery before implementation.

    178 GitHub starsUsed in 7 repos~4k tokens
    Product & Project ManagementAuto-check passed
  • Adversarial Spec

    zscole/adversarial-spec

    Iteratively refine a product spec by debating with multiple LLMs (GPT, Gemini, Grok, etc.) until all models agree.

    556 GitHub starsUsed in 1 repo~8.3k tokens
    Product & Project ManagementAuto-check: notes
  • Convert PRDs to beads for ralph-tui execution using beads-rust (br CLI).

    2.5k GitHub starsUsed in 1 repo~2.8k tokens
    Product & Project ManagementAuto-check passed
  • Runs a guided product-manager interview that classifies each question automatically and produces a Product Requirements Document.

    6.2k GitHub starsUsed in 1 repo~5.7k tokens
    Product & Project ManagementAuto-check passed

More from hylarucoder/hai-stack

All 18 skills in this repo
  • Verify a defined software change against requirements and produce a proportional, evidence-backed acceptance report with specification precedence, scope boundaries, requirement-to-evidence…

    382 GitHub stars~2.1k tokensUpdated 3 days ago
    Auto-check passed
  • Hai Ast Grep

    hylarucoder/hai-stack

    Produces a ready-to-run ast-grep command or reusable YAML lint/codemod rule, validated against positive and negative fixtures.

    382 GitHub stars~1.5k tokensUpdated 3 days ago
    Auto-check passed
  • Readme Beautifier

    hylarucoder/hai-stack

    Reformats and restructures a README or similar Markdown project document without changing its factual content, voice, or scope, then summarizes formatting-only edits.

    382 GitHub stars~1.8k tokensUpdated 3 days ago
    Auto-check passed
  • Hai Visual Explainer

    hylarucoder/hai-stack

    Turns supplied content into self-contained HTML and PNG in two modes: card for one shareable frame(知识卡、信息卡、金句卡、封面、把要点做成一张图), report for multi-section documents(可视化报告、HTML 汇报页、PRD/计划/评审做成网页).

    382 GitHub stars~2k tokensUpdated 3 days ago
    Auto-check passed
  • Code Review And Quality

    hylarucoder/hai-stack

    Reviews a code change for correctness, security, maintainability, architecture, performance, and verification gaps, or performs a local code-smell review.

    382 GitHub stars~934 tokensUpdated 3 days ago
    Auto-check passed
  • Entity Model Auditor

    hylarucoder/hai-stack

    Audits an entity model field by field: what should exist, what exists now, where each value belongs (column, config, computed runtime value, or removal), and what must migrate.

    382 GitHub stars~1.5k tokensUpdated 3 days ago
    Auto-check passed

Questions about Hai Razor

What does Hai Razor do?

Tests whether each requirement, step, role, field, state, module, layer, abstraction, or rule deserves independent existence, then classifies it as Keep, Merge, Defer, Delete, Replace, or Prove first. Hai Razor is an agent skill from hylarucoder/hai-stack. Tests whether each requirement, step, role, field, state, module, layer, abstraction, or rule deserves independent existence, then classifies it as Keep, Merge, Defer, Delete, Replace, or Prove first.

When should I use Hai Razor?

Hai Razor fits situations like: the explicit decision is what can be removed; collapsed(奥卡姆剃刀、砍需求、这个字段/状态/层有必要吗、是否过度设计).

How do I install Hai Razor in Claude Code?

Run `npx skills add hylarucoder/hai-stack --skill hai-razor -a claude-code`. Or copy the skill folder (skills/hai-razor in hylarucoder/hai-stack) into .claude/skills/hai-razor in your project. Claude Code loads it when a task matches its description.

How do I install Hai Razor in Codex?

Run `npx skills add hylarucoder/hai-stack --skill hai-razor -a codex`. Or copy the skill folder (skills/hai-razor in hylarucoder/hai-stack) into .agents/skills/hai-razor in your project. Codex loads it when a task matches its description.

Can I use Hai Razor in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add hylarucoder/hai-stack --skill hai-razor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hai-razor, .gemini/skills/hai-razor, .github/skills/hai-razor and .opencode/skills/hai-razor in your project.

What does Hai Razor need to run?

SKILL.md names no scripts, command-line tools or credentials: Hai Razor is instructions for the agent only.

Does Hai Razor access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Hai Razor safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Hai Razor use?

Hai Razor has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Hai Razor use?

About 1.9k tokens (SKILL.md is roughly 7.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.1k tokens, read only when the agent opens those files.

What are the alternatives to Hai Razor?

Skills that share tags, products or a category with Hai Razor: CCPM Project Management (automazeio/ccpm, 8.4k stars), Ralph Tui Create Beads (subsy/ralph-tui, 2.5k stars), Trellis Brainstorm (anjiemo/SunnyBeach, 178 stars) and Adversarial Spec (zscole/adversarial-spec, 556 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Hai Razor?

hylarucoder (a GitHub user) maintains it in hylarucoder/hai-stack, which has 382 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on October 5, 2026.

Source: hylarucoder/hai-stack on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.