J Rig

What it does

When your agent uses it

• Improving an existing skill
• Refining a SKILL.md against measured behavior
• Bootstrapping an eval set for a skill
• Gating skill edits before they ship

Example prompts

• “/j-rig”
• “refine this skill”
• “bootstrap an eval set”
• “/j-rig”

Requirements

• Node.js
• A credential in ANTHROPIC_API_KEY
• Compatibility (from SKILL.md): Designed for Claude Code; the refine subcommands wrap the published @intentsolutions/jrig-cli binary and run anywhere that CLI installs
• Pre-approved tools (allowed-tools): Read, Write, Edit, Glob, Bash(j-rig:*), Bash(git:*), Bash(python:*)

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Write
  • Edit
  • Glob
  • Bash(j-rig:*)
  • Bash(git:*)
  • Bash(python:*)

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • git
  • npm
  • pnpm

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

• Network

  Links to these hosts (documentation or services it may open):

  • npmjs.com

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

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • ANTHROPIC_API_KEY

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

• Compatibility

  Designed for Claude Code; the refine subcommands wrap the published @intentsolutions/jrig-cli binary and run anywhere that CLI installs

  From compatibility in the SKILL.md frontmatter.

Context cost

J Rig loads about 2.7k tokens when it runs. Until then it costs about 201 tokens; SKILL.md has 1,139 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~201

When it runs · the whole SKILL.md, loaded when a task matches

~2.7k

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

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 jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its Apache-2.0 licence (© jeremylongshore). 1,139 words, ~2,712 tokens.

name

j-rig

description

Skill Refiner, the eval-guided improvement loop for SKILL.md files. Runs the bootstrap, score, propose, apply, and status cycle as a thin wrapper over the published @intentsolutions/refiner CLI, proposing safe, minimal, bounded SKILL.md edits and accepting an edit only when a held-out eval score strictly improves with no regression on any other case. Ships a 3-layer cost-tiered hook architecture (sinker, line, hook) that gates skill quality at edit time, end of turn, and commit time. Use when improving an existing skill, refining a SKILL.md against measured behavior, bootstrapping an eval set for a skill, or gating skill edits before they ship. Trigger with "/j-rig", "refine this skill", "bootstrap an eval set", "propose a skill edit", "promote the candidate", or "skill refiner status".

allowed-tools

Read, Write, Edit, Glob, Bash(j-rig:*), Bash(git:*), Bash(python:*)

compatibility

Designed for Claude Code; the refine subcommands wrap the published @intentsolutions/jrig-cli binary and run anywhere that CLI installs

version

0.1.0

author

Jeremy Longshore <jeremy@intentsolutions.io>

license

Apache-2.0

argument-hint

[refine bootstrap|score|propose|promote|status] <skill-dir>

tags

skill-refiner, eval-guided, skill-md, meta-tooling, hooks

J-Rig Skill Binary Eval   ->   Skill Refiner   ->   Rollout Gate
      (test)                     (improve)             (ship)

# Global — gives you the `j-rig` command everywhere
npm install -g @intentsolutions/jrig-cli

# Or per-repo (recommended for CI version-pinning)
pnpm add -D @intentsolutions/jrig-cli   # then: pnpm exec j-rig --help

# 1. Create a held-out eval set for the skill (deterministic, offline).
j-rig refine bootstrap skills/my-skill

# 2. Establish the baseline score (Sonnet tier).
j-rig refine score skills/my-skill --model sonnet

# 3. Propose one bounded edit; the acceptance gate shadow-validates it.
ANTHROPIC_API_KEY=... j-rig refine propose skills/my-skill --strategy skill-opt-style

# 4. If accepted, apply it, producing a new candidate version (human-gated promote).
j-rig refine apply skills/my-skill --proposal "<hash>"

# 5. Inspect the trajectory, best pointer, and event log any time.
j-rig refine status my-skill

j-rig refine render-report .j-rig/refiner/report.md --output report.html

© jeremylongshore, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/.curated/j-rig of jeremylongshore/tons-of-skills-marketplace.

Open the folder on GitHubat commit cfae287