skill-refine

skill-refine is a command for coding agents from gobing-ai/superskill. It costs 8 tokens per session (548 once invoked), scanned A, original, Apache-2.0.

A command that evaluates a skill and then applies structural and content improvements to its instruction file.

In plain words
What is it for?
Use it to refine a skill automatically, target a platform such as Claude, save results, or run a dry preview without changing files.
Why use it?
It combines quality checking and repair in one operation, with options to preview changes or save the evaluation results.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/gobing-ai/superskill/skill-refine
Clone the repo
git clone --depth 1 https://github.com/gobing-ai/superskill

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for skill-refine

README.md
[![agentmods](https://agentmods.dev/badge/commands/gobing-ai/superskill/skill-refine.svg)](https://agentmods.dev/commands/gobing-ai/superskill/skill-refine)
Your own site
<a href="https://agentmods.dev/commands/gobing-ai/superskill/skill-refine"><img src="https://agentmods.dev/badge/commands/gobing-ai/superskill/skill-refine.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 548 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00008 $0.00548
Opus 5 $0.00004 $0.00274
Sonnet 5 $0.00002 $0.00110
Haiku 4.5 $0.00001 $0.00055

Measured 3d ago against content hash bd427e09a6d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-refine scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/cc/commands/skill-refine.md · 67 lines

What it actually says

Skill Refine

Wraps cc:cc-skills skill.

Run evaluation, apply deterministic fixes, then perform LLM content improvement — all in one step. Delegates to cc:cc-skills skill.

When to Use

  • Improve skill quality after scaffolding
  • Fix skill issues without running evaluate separately

Arguments

Argument Description Default
<nameOrPath> Skill name or path to its SKILL.md file (required)
--auto Skip interactive prompts (auto-apply fixes) false
--save Save evaluation results to file false
--dry-run Preview classified fixes and projected score delta without writing false
--target Target platform claude

Examples

# Refine a skill
/cc:skill-refine ./skills/my-skill/SKILL.md
# Auto-refine without prompts
/cc:skill-refine ./skills/my-skill/SKILL.md --auto --save
# Preview fixes without writing
/cc:skill-refine ./skills/my-skill/SKILL.md --dry-run

Content Fix Types

Beyond deterministic structural fixes, refine applies two named content fix types: description prune (three description rules: front-loaded identity, one trigger per branch, no body restatement) and the pruning pass (per-sentence no-op hunt — delete the whole failing sentence, never trim it; duplication collapse; sediment removal; disclosure moves; negation flip — rewrite prohibition-steered lines to name the positive target). Single copy: cc:cc-skills workflows reference § "Content fix types" and the six-mode taxonomy in its skill-engineering theory reference.

Implementation

Pass $ARGUMENTS to the underlying skill for processing.

Delegates to cc:cc-skills skill:

Skill(skill="cc:cc-skills", args="refine $ARGUMENTS")

Direct CLI execution (all platforms):

superskill skill refine $ARGUMENTS

Platform Notes

  • Claude Code: Invoke via Skill() delegation
  • Other platforms: Run superskill CLI directly via Bash tool
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 67 lines · 8 tokens per session scan A bd427e09a6d7

Subscribe to this mod's changes

skill-refine is a command published in the GitHub repository gobing-ai/superskill (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 8 tokens to every session and 548 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.