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.
npx skills add ArabelaTso/Skills-4-SE --skill refinement-step-generatorgit clone --depth 1 https://github.com/ArabelaTso/Skills-4-SEWrote 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.
[](https://agentmods.dev/skills/arabelatso/skills-4-se/refinement-step-generator)<a href="https://agentmods.dev/skills/arabelatso/skills-4-se/refinement-step-generator"><img src="https://agentmods.dev/badge/skills/arabelatso/skills-4-se/refinement-step-generator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/arabelatso/skills-4-se/refinement-step-generator"><img src="https://agentmods.dev/badge/skills/arabelatso/skills-4-se/refinement-step-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00084 | $0.02246 |
| Opus 5 | $0.00042 | $0.01123 |
| Sonnet 5 | $0.00017 | $0.00449 |
| Haiku 4.5 | $0.00008 | $0.00225 |
Grade A, and why
refinement-step-generator 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refinement Step Generator
Generate systematic refinement steps that transform high-level specifications into concrete, executable implementations while preserving correctness through formal proofs.
Overview
Refinement is the process of transforming abstract specifications into concrete implementations through a series of correctness-preserving steps. Each refinement step:
- Makes the specification more concrete (closer to executable code)
- Preserves correctness through formal proof obligations
- Maintains a clear abstraction relation between levels
- Can be verified independently
This skill provides guidance for generating refinement steps in Isabelle/HOL and Coq.
Refinement Workflow
Abstract Specification
↓ [Data Refinement]
Refined Data Structures
↓ [Algorithmic Refinement]
Concrete Algorithm
↓ [Implementation Refinement]
Executable Code
Each arrow represents a refinement step with proof obligations.
Core Refinement Types
1. Data Refinement
Transform abstract data types into concrete data structures.
Example: Set → List
Abstract (Isabelle):
definition insert_set :: "'a ⇒ 'a set ⇒ 'a set" where
"insert_set x S = S ∪ {x}"
definition member_set :: "'a ⇒ 'a set ⇒ bool" where
"member_set x S = (x ∈ S)"
Concrete (Isabelle):
definition insert_list :: "'a ⇒ 'a list ⇒ 'a list" where
"insert_list x xs = (if x ∈ set xs then xs else x # xs)"
definition member_list :: "'a ⇒ 'a list ⇒ bool" where
"member_list x xs = (x ∈ set xs)"
Abstraction Relation:
definition abs_list :: "'a list ⇒ 'a set" where
"abs_list xs = set xs"
Proof Obligations:
lemma insert_refines:
"abs_list (insert_list x xs) = insert_set x (abs_list xs)"
by (simp add: insert_list_def insert_set_def abs_list_def)
lemma member_refines:
"member_list x xs = member_set x (abs_list xs)"
by (simp add: member_list_def member_set_def abs_list_def)
2. Algorithmic Refinement
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 325 lines · 84 tokens per session scan A 1f0c70749721
refinement-step-generator is a skill published in the GitHub repository ArabelaTso/Skills-4-SE (252 stars, last pushed 22d ago), licensed Apache-2.0. It adds 84 tokens to every session and 2,246 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
datalad
Retrieve, version, and publish scientific datasets with DataLad and git-annex, and capture computational provenance with datalad run, rerun, and containers-run. Use when cloning or fetching data from OpenNeuro, DANDI, datasets.datalad.org, or any DataLad dataset; when a file in a dataset reads as a broken symlink or a…
depmap
Query the Cancer Dependency Map (DepMap) for cancer cell line gene dependency scores (CRISPR Chronos), drug sensitivity data, and gene effect profiles. Use for identifying cancer-specific vulnerabilities, synthetic lethal interactions, and validating oncology drug targets.
latchbio-integration
Build, register, debug, and operate bioinformatics workflows on Latch using the Python SDK, CLI, Latch Data and Registry, Nextflow, Snakemake, programmatic execution, and Latch MCP. Use when authoring or deploying Latch workflows, configuring resources or interfaces, moving data, integrating Registry, or launching and…
ginkgo-cloud-lab
Submit and manage protocols on Ginkgo Bioworks Cloud Lab (cloud.ginkgo.bio), a web-based interface for autonomous lab execution on Reconfigurable Automation Carts (RACs). Use when the user wants to run protein expression and purification (cell-free, E. coli, or Pichia), HiBiT or A280 or LabChip quantification, IVT…
write-paper
Full-pipeline medical/scientific paper writing. 8-phase IMRAD workflow from outline to submission-ready manuscript. Supports original articles, case reports, case series, meta-analyses, AI validation studies, animal studies, and technical notes. Do NOT trigger for self-checking (use self-review instead).
sync-submission
Audit SSOT-to-submission drift and create journal submission manifests from canonical manuscript artifacts.