Agent skill

Vertical Creator

by FairladyZ625 in FairladyZ625/harness-anything

Create, review, or update Harness Anything verticals. An agent skill from FairladyZ625/harness-anything.

AGPL-3.0Auto-check passedDevelopment

Install Vertical Creator

skills CLI
$ npx skills add FairladyZ625/harness-anything --skill vertical-creator -a claude-code

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

GitHub CLI
$ gh skill install FairladyZ625/harness-anything vertical-creator --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/FairladyZ625/harness-anything.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/vertical-creator .claude/skills/vertical-creator && 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
vertical-creator
GitHub stars
226
Token cost
~1.7k tokens
SKILL.md length
528 words
Files
2
Skills in repo
12
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Create, review, or update Harness Anything verticals. An agent skill from FairladyZ625/harness-anything.

  • Works in 11 steps: Name the domain and list its entity… → Decide which entities are lifecycle… → Define package scaffolds and repository… → …
  • Designing vertical-definition JSON
  • SKILL.md covers Core Rule, Workflow, Entity Declaration Tuple and Vertical Definition Pattern, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Vertical Creator is an agent skill from FairladyZ625/harness-anything. Create, review, or update Harness Anything verticals. Use when designing vertical-definition JSON, vertical template catalogs, entity kinds, package scaffolds, checker profiles, projection schemas, and preset layering for a new Harness Anything domain such as coding, QA, docs, design, or operations.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Development, covering Project scaffolding. The repository describes itself as: Clean-room Harness rewrite monorepo. The licence is AGPL-3.0.

When your agent uses it

  • Designing vertical-definition JSON
  • Vertical template catalogs
  • Package scaffolds
  • Checker profiles

Example prompts

  • “/vertical-creator”

Workflow steps

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

  1. Name the domain and list its entity kinds using the entity declaration tuple.
  2. Decide which entities are lifecycle package entities and which are schema-only metadata entities.
  3. Define package scaffolds and repository roots for every lifecycle entity.
  4. Put template bodies in Markdown assets under assets//templates//.md.
  5. Register those assets in template-catalog/v2 with bodyPath; do not use inline body.
  6. Define required documents as templateSelections that point at catalog refs.
  7. Choose the checker profile and projection schemas.
  8. Define applicable presets separately as preset-manifest/v3; do not bury preset behavior in the vertical.
  9. Run ha vertical validate --source before publishing the vertical.
  10. Add validation tests for schema shape, materialized paths, catalog body paths, and default preset/profile behavior.
  11. Add integration tests only for real CLI/filesystem behavior.

What it can do on your machine

Read from SKILL.md and the folder at commit c805ddf. 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 (its code samples are json, bash and markdown).

    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

Vertical Creator loads about 1.7k tokens when it runs. Until then it costs about 79 tokens; SKILL.md has 528 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~79
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

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

The full file from FairladyZ625/harness-anything at commit c805ddf, republished under its AGPL-3.0 licence (© FairladyZ625). 528 words, ~1,744 tokens.

Download SKILL.mdSave it as .claude/skills/vertical-creator/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
vertical-creator
description
Create, review, or update Harness Anything verticals. Use when designing vertical-definition JSON, vertical template catalogs, entity kinds, package scaffolds, checker profiles, projection schemas, and preset layering for a new Harness Anything domain such as coding, QA, docs, design, or operations.

Vertical Creator

Core Rule

Keep verticals declarative. A vertical defines entity shape, template catalogs, scaffolds, defaults, and applicable presets. It must not require CLI core branches for a specific domain.

The CLI may provide only generic vertical infrastructure:

  • Schema validation.
  • Template catalog loading.
  • Template materialization.
  • Settings/dev-mode gating.
  • Generic preset and profile selection.

Vertical-specific behavior belongs in vertical assets, template catalogs, preset manifests, and process scripts.

Workflow

  1. Name the domain and list its entity kinds using the entity declaration tuple.
  2. Decide which entities are lifecycle package entities and which are schema-only metadata entities.
  3. Define package scaffolds and repository roots for every lifecycle entity.
  4. Put template bodies in Markdown assets under assets/<vertical>/templates/<slot>/<locale>.md.
  5. Register those assets in template-catalog/v2 with bodyPath; do not use inline body.
  6. Define required documents as templateSelections that point at catalog refs.
  7. Choose the checker profile and projection schemas.
  8. Define applicable presets separately as preset-manifest/v3; do not bury preset behavior in the vertical.
  9. Run ha vertical validate --source <package-directory> before publishing the vertical.
  10. Add validation tests for schema shape, materialized paths, catalog body paths, and default preset/profile behavior.
  11. Add integration tests only for real CLI/filesystem behavior.

Entity Declaration Tuple

Declare each entity with the v2 five-part contract:

  • id
  • entityType
  • packageKind for lifecycle entities or schemaRef for schema entities
  • contractEntity
  • matching scaffold/root membership where required

Lifecycle entities must have both a packageScaffolds entry and a repositoryScaffold.entityRoots entry. Schema entities must not have package scaffolds or repository roots.

Vertical Definition Pattern

A vertical package contains vertical.json and its catalog/assets. Validate the package directory with ha vertical validate --source <package-directory>; this fragment illustrates the declaration shape.

json
{
  "schema": "vertical-definition/v1",
  "id": "example/work",
  "title": "Example Work",
  "version": "1.0.0",
  "entityFieldExtensions": [],
  "entityKinds": [
    {
      "id": "task",
      "entityType": "lifecycle",
      "packageKind": "task-package/v2",
      "contractEntity": true
    },
    {
      "id": "fact",
      "entityType": "schema",
      "schemaRef": "schema://fact-record",
      "contractEntity": true
    }
  ],
  "contractEntityKinds": ["task", "fact"],
  "packageScaffolds": [
    {
      "entityKind": "task",
      "templateSelections": []
    }
  ],
  "repositoryScaffold": {
    "entityRoots": [
      {
        "entityKind": "task",
        "path": "{{paths.tasksRoot}}",
        "create": "init"
      }
    ],
    "dirs": [],
    "seededDocs": []
  },
  "scripts": [],
  "templateSelections": [],
  "checkerProfile": "standard",
  "projectionSchemas": []
}

Validate it:

sh
ha vertical validate --source <package-directory>

Template Catalog v2

A vertical package should keep bodies as Markdown assets and register them by bodyPath:

text
assets/software-coding/
  vertical.json
  template-catalog.json
  templates/
    task.plan/
      en-US.md
      zh-CN.md
  presets/
    standard-task/
      preset.json

Catalog root:

json
{
  "schema": "template-catalog/v2",
  "package": {
    "id": "software-coding-core",
    "title": "Software Coding Core Templates",
    "version": "1.0.0",
    "owner": "harness-anything",
    "locales": ["zh-CN", "en-US"]
  },
  "documents": [
    {
      "id": "planning/task-plan",
      "version": "1",
      "documentKind": "task-plan",
      "slot": "task.plan",
      "materializeAs": "task_plan.md",
      "frontmatterSchema": "task-package/v2",
      "requiredAnchors": ["## Goal", "## Verification"],
      "fallbackLocale": "en-US",
      "locales": [
        {
          "locale": "en-US",
          "anchors": ["## Goal", "## Verification"],
          "bodyPath": "templates/task.plan/en-US.md"
        },
        {
          "locale": "zh-CN",
          "anchors": ["## Goal", "## Verification"],
          "bodyPath": "templates/task.plan/zh-CN.md"
        }
      ]
    }
  ]
}

templates/task.plan/en-US.md must contain all required anchors:

md
## Goal

Describe the target outcome.

## Verification

List the validation steps.

Preset overlays should reference the same catalog documents from preset-manifest/v3 profiles:

json
{
  "id": "baseline",
  "title": "Baseline",
  "checkerProfile": "standard",
  "completionGates": [],
  "templateSelections": [
    {
      "slot": "task.plan",
      "templateRef": "template://planning/task-plan@1",
      "materializeAs": "task_plan.md",
      "localePolicy": { "prefer": "project", "fallback": "en-US" }
    }
  ]
}
Show full SKILL.md (216 more words)Show less

Design Rules

  • Use templates for document structure, not ad hoc file writes.
  • Use presets for optional process or content overlays.
  • Use preset-manifest/v3 for all new preset examples.
  • Use template-catalog/v2 with bodyPath; never teach inline template body.
  • Keep project/user overrides additive and fail closed on invalid active overrides.
  • Do not promise unattended conversion when the system supports Legacy Intake plus explicit rebuild only.
  • Keep private harness operating state out of public docs unless explicitly designing public product documentation.

Review Checklist

  • ha vertical validate --source <package-directory> passes.
  • Entity kinds declare entityType and exactly one of packageKind or schemaRef.
  • Every lifecycle entity has a package scaffold and repository root.
  • Schema entities do not declare package scaffolds or repository roots.
  • Template refs exist in template-catalog/v2 and use asset-backed bodyPath.
  • Required anchors match locale anchors and appear in each body asset.
  • Presets shipped with the vertical use preset-manifest/v3, profiles, and defaultProfile; every v3 profile explicitly declares completionGates, even when empty (ADR-0027 D7).
  • Preset manifests pass ha preset validate --source <package-directory>.
  • The vertical works without CLI branches keyed by vertical id.
  • Template refs exist in the catalog and materialize to stable paths.
  • Default preset/profile behavior is explicit.
  • Custom verticals remain gated by user dev mode and project settings.
  • Tests are placed in the proper tier manifest when new test files are added.

© FairladyZ625, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/vertical-creator of FairladyZ625/harness-anything.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit c805ddf

Compare with similar skills

Vertical Creator 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.

Vertical Creator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Vertical Creator this skillFairladyZ625/harness-anything226—~1.7kAutomated safety check: PassAGPL-3.0
Nx Generatenomcopter/react-mosaic4.8k7 repos~1.9kAutomated safety check: PassCustom licence
PonytailDavidObando/gsharp5657 repos~1.7kAutomated safety check: PassMIT
Run Nx Generatornrwl/nx29k2 repos~592Automated safety check: NotesMIT
Conductor Setupgemini-cli-extensions/conductor3.8k—~4.2kAutomated safety check: PassApache-2.0
Mirage VFS Adapter Authoringstrukto-ai/mirage3.7k—~2.5kAutomated safety check: PassApache-2.0

Similar skills

  • Nx Generate

    nomcopter/react-mosaic

    Generate code using nx generators. An agent skill from nomcopter/react-mosaic.

    4.8k GitHub starsUsed in 7 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Ponytail

    DavidObando/gsharp

    Forces the laziest solution that actually works, simplest, shortest, most minimal.

    565 GitHub starsUsed in 7 repos~1.7k tokens
    DevelopmentAuto-check passed
  • Run Nx generators with prioritization for workspace-plugin generators.

    29k GitHub starsUsed in 2 repos~592 tokens
    DevelopmentAuto-check: notes
  • Conductor Setup

    gemini-cli-extensions/conductor

    Scaffolds the project and sets up the Conductor environment.

    3.8k GitHub stars~4.2k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Builds or extends a custom Mirage virtual filesystem adapter for an API, database, object store or app data, with a working mount configuration and filesystem tests.

    3.7k GitHub stars~2.5k tokensUpdated today
    DevelopmentAuto-check passed
  • Enforces this repository's TypeScript backend module architecture under server/: feature folders, barrel exports, and where shared types and utilities belong.

    14k GitHub stars~1.2k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from FairladyZ625/harness-anything

All 12 skills in this repo
  • Harness Contributing

    FairladyZ625/harness-anything

    Contribute a public change to Harness Anything from a GitHub issue through an isolated worktree, scoped tests, manifest-selected gates, a complete bilingual PR body, review triage, and maintainer…

    226 GitHub stars~4.4k tokensUpdated today
    Auto-check passed
  • Gate Customization

    FairladyZ625/harness-anything

    在目标仓库 harness.yaml 的 settings.gates 里声明与定制任务完成门:local-command 本地命令见证、manual-attest 人工签字、github-actions CI 见证、none 显式免除,治理字段 mandatorySignoff(双控签注)与 allowOverride(owner 特批),以及…

    226 GitHub stars~3.5k tokensUpdated today
    Auto-check passed
  • Preset Creator

    FairladyZ625/harness-anything

    Create, review, or update Harness Anything preset-manifest/v3 packages, including profiles, completion gates, template selections, output shapes, script entrypoints, capability declarations, package…

    226 GitHub stars~1.9k tokensUpdated today
    Auto-check passed
  • Preset Trigger

    FairladyZ625/harness-anything

    Start Harness Anything task creation by choosing a software/coding preset first.

    226 GitHub stars~928 tokensUpdated today
    Auto-check passed
  • Task Explainer HTML

    FairladyZ625/harness-anything

    产出与增量维护任务包中的活解释页 artifacts/explainer.html;按物化模板中的唯一权威注释编写,并消费派工注入的 task-context 因果上下文。Use when a task-bound dispatch requires creating, updating, or freezing the task's living explainer page, or…

    226 GitHub stars~689 tokensUpdated today
    Auto-check passed
  • Harness Reckoning

    FairladyZ625/harness-anything

    Run and interpret a read-only retrospective over Harness ledger projections, then prepare evidence-backed mechanism fixes, deletion candidates, or time-bounded rule proposals for human adjudication.

    226 GitHub stars~768 tokensUpdated today
    Auto-check passed

Categories

Questions about Vertical Creator

What does Vertical Creator do?

Create, review, or update Harness Anything verticals. An agent skill from FairladyZ625/harness-anything. Vertical Creator is an agent skill from FairladyZ625/harness-anything. Create, review, or update Harness Anything verticals.

When should I use Vertical Creator?

Vertical Creator fits situations like: designing vertical-definition JSON; vertical template catalogs; package scaffolds; checker profiles.

How do I install Vertical Creator in Claude Code?

Run `npx skills add FairladyZ625/harness-anything --skill vertical-creator -a claude-code`. Or copy the skill folder (skills/vertical-creator in FairladyZ625/harness-anything) into .claude/skills/vertical-creator in your project. Claude Code loads it when a task matches its description.

How do I install Vertical Creator in Codex?

Run `npx skills add FairladyZ625/harness-anything --skill vertical-creator -a codex`. Or copy the skill folder (skills/vertical-creator in FairladyZ625/harness-anything) into .agents/skills/vertical-creator in your project. Codex loads it when a task matches its description.

Can I use Vertical Creator 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 FairladyZ625/harness-anything --skill vertical-creator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/vertical-creator, .gemini/skills/vertical-creator, .github/skills/vertical-creator and .opencode/skills/vertical-creator in your project.

What does Vertical Creator need to run?

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

Does Vertical Creator 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 Vertical Creator 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 Vertical Creator use?

Vertical Creator is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Vertical Creator use?

About 1.7k tokens (SKILL.md is roughly 7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Vertical Creator?

Skills that share tags, products or a category with Vertical Creator: Nx Generate (nomcopter/react-mosaic, 4.8k stars), Ponytail (DavidObando/gsharp, 565 stars), Run Nx Generator (nrwl/nx, 29k stars) and Conductor Setup (gemini-cli-extensions/conductor, 3.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Vertical Creator?

FairladyZ625 (a GitHub user) maintains it in FairladyZ625/harness-anything, which has 226 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 10, 2026.

Source: FairladyZ625/harness-anything on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.