Agent skill

Select Variant

by romeerez in romeerez/orchid-orm

A skill your agent uses when the user prompts "select variant".

MITAuto-check passedDatabases

Install Select Variant

skills CLI
$ npx skills add romeerez/orchid-orm --skill select-variant -a claude-code

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

GitHub CLI
$ gh skill install romeerez/orchid-orm select-variant --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/romeerez/orchid-orm.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/select-variant .claude/skills/select-variant && 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
select-variant
GitHub stars
543
Token cost
~2.5k tokens
SKILL.md length
1,217 words
Files
2
Skills in repo
13
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when the user prompts "select variant".

  • Works in 10 steps: Identify the target change folder → Resolve the target idea → Verify required input files → …
  • The user prompts select variant
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Tasks that involve ORMs and data access

What it does

Select Variant is an agent skill from romeerez/orchid-orm. Use when the user prompts "select variant".

Its SKILL.md is about 2.5k 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 Databases, covering ORMs and data access. The licence is MIT.

When your agent uses it

  • The user prompts select variant
  • Tasks that involve ORMs and data access

Example prompts

  • “select variant”
  • “/select-variant”

Workflow steps

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

  1. Identify the target change folder
  2. Resolve the target idea
  3. Verify required input files
  4. Read variants.md and identify the available variants
  5. Select exactly one variant
  6. Check whether selected-variant.md can be replaced
  7. Write a fresh selected-variant.md
  8. Determine whether refinement is required
  9. Refine the saved selected-variant.md when requested
  10. Quality check

What it can do on your machine

Read from SKILL.md and the folder at commit f819fb5. 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 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

Select Variant loads about 2.5k tokens when it runs. Until then it costs about 15 tokens; SKILL.md has 1,217 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~15
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k

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

The full file from romeerez/orchid-orm at commit f819fb5, republished under its MIT licence (© romeerez). 1,217 words, ~2,485 tokens.

Download SKILL.mdSave it as .claude/skills/select-variant/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
select-variant
description
Use when the user prompts "select variant".

Read a specific idea's variants.md, choose exactly one variant, write changes/<feature-name>/<NUMBER-idea-name>/selected-variant.md, and optionally refine that saved file in place.

Input: The argument after /select-variant should include:

  • A feature or change folder name
  • An idea number or idea title
  • Optionally, a variant number or a variant title
  • Optionally, an explicit instruction such as refine or don't refine
  • Optionally, an explicit instruction such as replace or overwrite

Examples:

  • /select-variant 611-row-level-security-integration 2
  • /select-variant 611-row-level-security-integration 2 1
  • /select-variant row-level-security-integration "Run work inside an explicit RLS context" "ALS-backed query-time RLS state in $withOptions"
  • /select-variant row-level-security-integration 2 refine
  • /select-variant row-level-security-integration 2 1 don't refine
  • /select-variant row-level-security-integration 2 1 replace

Goal

Produce a final selection document for one idea variant.

This command is a selection workflow, not a design-generation workflow. It should:

  • Resolve the intended feature and idea without guessing through ambiguity
  • Read the idea's existing variants.md
  • Select exactly one variant
  • Check whether replacing an existing selected-variant.md is allowed
  • Write a fresh selected-variant.md from the selected variant
  • Ask whether to refine it unless the user already decided that
  • Optionally follow the refine workflow against the saved selected-variant.md

The command must save the selected variant document first. If refinement is requested, .agents/commands/refine.md then updates that saved file in place.

Steps

  1. Identify the target change folder

    Search changes/ for the folder that best matches the user's feature input.

    Prefer:

    • An exact folder-name match
    • A folder whose name clearly matches the described feature
    • A folder that already contains ideas.md

    If multiple folders are plausible, stop and ask the user which one to use. Do not guess when the match is ambiguous.

    If no relevant change folder exists, tell the user that no matching change folder was found. Do not create a new change folder here.

  2. Resolve the target idea

    Find an idea folder inside changes/<feature-name>/ that matches the user's idea input.

    Match by:

    • Exact idea number from folders such as 2-run-work-inside-an-explicit-rls-context
    • Or exact / clearly intended idea name from the folder suffix
    • If needed, read changes/<feature-name>/ideas.md to confirm the exact numbered idea title

    If multiple idea folders are plausible, stop and ask one focused clarifying question. Do not guess between similarly named ideas.

    The resolved idea path must be:

    changes/<feature-name>/<NUMBER-idea-name>

  3. Verify required input files

    Confirm that changes/<feature-name>/<NUMBER-idea-name>/variants.md exists.

    If variants.md is missing, stop and tell the user that the idea does not have variants yet. Do not create variants.md in this command.

  4. Read variants.md and identify the available variants

    Read the full changes/<feature-name>/<NUMBER-idea-name>/variants.md.

    Identify variants from headings in this form:

    ## Solution <number>: <solution name>

    For each variant, capture:

    • Its exact solution number
    • Its exact solution name
    • Its full section content

    Treat the variant body as the content from that ## Solution ... heading until the next ## Solution ... heading, or until the next top-level section that is not part of that solution.

    Ignore non-variant sections such as:

    • # <Idea Title>
    • ## Goal
    • ## Context from existing research
    • ## Comparison
    • ## References
  5. Select exactly one variant

    If the user provided a variant number or name:

    • Match by exact solution number
    • Or exact / clearly intended solution name

    If the title match is ambiguous, stop and ask one focused clarifying question. Do not guess between similarly named variants.

    If the user did not provide a variant:

    • If there is exactly one variant in variants.md, select it automatically
    • If there is more than one variant, stop and ask the user which variant to choose

    Record:

    • The exact idea title
    • The selected solution number
    • The selected solution name
    • The selected solution body
  6. Check whether selected-variant.md can be replaced

    Check whether changes/<feature-name>/<NUMBER-idea-name>/selected-variant.md already exists.

    If it does not exist, continue.

    If it exists, inspect the user input for an explicit replacement decision.

    Explicit yes:

    • replace
    • overwrite
    • recreate
    • clearly equivalent wording

    If selected-variant.md exists and the user did not explicitly choose replacement, stop and ask a short direct question about whether the existing file should be replaced.

    If the user says no, stop without changing the file.

  7. Write a fresh selected-variant.md

    The output path must be:

    changes/<feature-name>/<NUMBER-idea-name>/selected-variant.md

    Create this file only after:

    • the selection is complete
    • replacement was explicitly allowed when needed

    Build the file from variants.md by preserving only:

    • ## Goal
    • ## Context from existing research
    • the selected ## Solution <number>: <solution name> section content
    • ## References

    Omit:

    • all non-selected ## Solution ... sections
    • ## Comparison
    • any other sections that only exist to compare or discuss unselected variants

    Use this structure:

    md
    # <Selected solution name>
    
    ## Goal
    
    <Copied from `variants.md`.>
    
    ## Context from existing research
    
    <Copied from `variants.md`.>
    
    ## Solution
    
    <Write the original selected solution section content here, including any example subsection(s), but without the original `## Solution ...` heading.>
    
    ## References
    
    <Copied from `variants.md`.>

    Output guidance:

    • Use the exact selected solution name in the # heading
    • Preserve ## Goal, ## Context from existing research, and ## References from variants.md
    • Do not include the selected solution number anywhere in the final file unless it naturally appears inside copied prose
    • The ## Solution section should contain the original selected solution content, including any example subsection(s), but without the original ## Solution ... heading
    • Do not invent extra detail at this step
    • Do not include process notes, unresolved questions, comparison material, or metadata about the selection itself
  8. Determine whether refinement is required

    Inspect the user input for an explicit refinement decision.

    Explicit yes:

    • refine
    • refined
    • clearly equivalent wording

    Explicit no:

    • don't refine
    • do not refine
    • skip refine
    • clearly equivalent wording

    If the user explicitly chose refinement, proceed to the refinement step using the saved selected-variant.md.

    If the user explicitly chose not to refine, finish without refinement.

    If the user did not make the decision explicit, ask a short direct question about whether the saved selected-variant.md should be refined.

  9. Refine the saved selected-variant.md when requested

    If refinement is required, follow the workflow in .agents/commands/refine.md using:

    changes/<feature-name>/<NUMBER-idea-name>/selected-variant.md

    as the input file.

    The refine step must update that same file in place.

    If refinement is skipped, leave the just-written selected-variant.md unchanged.

  10. Quality check

Show full SKILL.md (292 more words)Show less

Before finishing, verify:

  • The change folder is the best match for the user's feature input
  • The idea folder is the best match for the user's idea input
  • variants.md was read from the correct idea folder
  • Exactly one variant was selected
  • If selected-variant.md already existed, replacement was explicitly provided by the user or explicitly asked and confirmed
  • selected-variant.md was written only after the selection / replacement flow was complete
  • The saved file initially used the selected solution name as the top title
  • The saved file initially preserved the goal, context, selected solution content, and references from variants.md
  • The saved file initially used ## Solution as the selected solution section title
  • The saved file did not include the solution number as output metadata
  • The saved file omitted non-selected variants and comparison-only material
  • The refine decision was either explicitly provided by the user or explicitly asked
  • Refinement was only performed when requested
  • If refinement was performed, it happened only after selected-variant.md was written and it updated that same file in place
  • If refinement was skipped, the just-written selected-variant.md remained unchanged

Guardrails

  • Do not create or update variants.md in this command
  • Do not guess when feature, idea, or variant matching is ambiguous
  • Do not auto-select among multiple variants when the user did not specify one
  • Do not replace an existing selected-variant.md unless the user explicitly said to replace it or confirmed replacement when asked
  • Do not write selected-variant.md before the selection and replacement checks are complete
  • Do not wait on the refine decision before writing selected-variant.md
  • Do not refine unless the user explicitly chose it or answered yes when asked
  • Do not write a second output file for refinement
  • Do not regenerate or reconcile selected-variant.md from variants.md after refinement begins
  • Do not turn this command into implementation planning

© romeerez, MIT. 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 .agents/skills/select-variant of romeerez/orchid-orm.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit f819fb5

Compare with similar skills

Select Variant 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.

Select Variant compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Select Variant this skillromeerez/orchid-orm543—~2.5kAutomated safety check: PassMIT
Content Create Hero Imageprisma/web1.1k—~6.9kAutomated safety check: PassNone
Sea Orm 2FlyinPancake/yoink112—~2.9kAutomated safety check: PassApache-2.0
Prisma Client APIcurvenote/curvenote1702 repos~1.6kAutomated safety check: PassMIT
DB Migratesimstudioai/sim30k—~2kAutomated safety check: PassApache-2.0
DB Migrationskurealnum/dotfiles290—~820Automated safety check: PassNone

Similar skills

  • Official

    A skill your agent uses when the operator wants a hero or meta image for a Prisma blog post; asks to create or generate a blog hero, cover, social card, Open Graph, or YouTube image; mentions cover…

    1.1k GitHub stars~6.9k tokensUpdated today
    DatabasesAuto-check passed
  • Sea Orm 2

    FlyinPancake/yoink

    Expert guidance for SeaORM 2.0, Rust's async ORM with strongly-typed columns, nested ActiveModels, Entity Loader API, and entity-first workflow.

    112 GitHub stars~2.9k tokensUpdated 4 days ago
    DatabasesAuto-check passed
  • Prisma Client API

    curvenote/curvenote

    Prisma Client API reference covering model queries, filters, operators, and client methods.

    170 GitHub starsUsed in 2 repos~1.6k tokens
    DatabasesAuto-check passed
  • DB Migrate

    simstudioai/sim

    Author or review a Drizzle DB migration for zero-downtime safety — expand/contract phasing, backward-compatibility with the deployed app version, and writing the -- migration-safe acknowledgment the…

    30k GitHub stars~2k tokensUpdated today
    DatabasesAuto-check passed
  • DB Migrations

    kurealnum/dotfiles

    A skill your agent uses when generating or regenerating Drizzle migration files, changing database schema tables or columns, resolving migration sequence conflicts after rebase, reviewing migration…

    290 GitHub stars~820 tokensUpdated 5 mo ago
    DatabasesAuto-check passed
  • Change Database Schema

    martin-ueding/geo-activity-playground

    How to change the SQLAlchemy data model and generate the matching Alembic migration.

    100 GitHub stars~225 tokensUpdated 11 days ago
    DatabasesAuto-check passed

More from romeerez/orchid-orm

All 13 skills in this repo
  • Spec

    romeerez/orchid-orm

    A skill your agent uses when the user prompts "write spec" or "make spec".

    543 GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Task List

    romeerez/orchid-orm

    A skill your agent uses when user asks to write a task list, not to do a task

    543 GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • Type Optimizer

    romeerez/orchid-orm

    A skill your agent uses when need to optimize TypeScript types.

    543 GitHub stars~798 tokensUpdated today
    Auto-check passed
  • Code Doc

    romeerez/orchid-orm

    A skill your agent uses when the user prompts "code doc" to create or update internal Orchid ORM code documentation from changes/ specs, short-code feature folders, or existing implementation code.

    543 GitHub stars~2.2k tokensUpdated today
    Auto-check passed
  • Ideas

    romeerez/orchid-orm

    A skill your agent uses when the user prompts "write ideas" or "make ideas".

    543 GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • Implemenation Note

    romeerez/orchid-orm

    A skill your agent uses when the user prompts "implementation note" for an existing change idea.

    543 GitHub stars~1.3k tokensUpdated today
    Auto-check passed

Categories

Questions about Select Variant

What does Select Variant do?

A skill your agent uses when the user prompts "select variant". Select Variant is an agent skill from romeerez/orchid-orm. Use when the user prompts "select variant".

When should I use Select Variant?

Select Variant fits situations like: the user prompts select variant; tasks that involve ORMs and data access.

How do I install Select Variant in Claude Code?

Run `npx skills add romeerez/orchid-orm --skill select-variant -a claude-code`. Or copy the skill folder (.agents/skills/select-variant in romeerez/orchid-orm) into .claude/skills/select-variant in your project. Claude Code loads it when a task matches its description.

How do I install Select Variant in Codex?

Run `npx skills add romeerez/orchid-orm --skill select-variant -a codex`. Or copy the skill folder (.agents/skills/select-variant in romeerez/orchid-orm) into .agents/skills/select-variant in your project. Codex loads it when a task matches its description.

Can I use Select Variant 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 romeerez/orchid-orm --skill select-variant -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/select-variant, .gemini/skills/select-variant, .github/skills/select-variant and .opencode/skills/select-variant in your project.

What does Select Variant need to run?

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

Does Select Variant 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 Select Variant 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 Select Variant use?

Select Variant is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Select Variant use?

About 2.5k tokens (SKILL.md is roughly 9.9k 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 Select Variant?

Skills that share tags, products or a category with Select Variant: Content Create Hero Image (prisma/web, 1.1k stars), Sea Orm 2 (FlyinPancake/yoink, 112 stars), Prisma Client API (curvenote/curvenote, 170 stars) and DB Migrate (simstudioai/sim, 30k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Select Variant?

romeerez (a GitHub user) maintains it in romeerez/orchid-orm, which has 543 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on October 8, 2026.

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