Skip to content
Skills Library
Programming · Building & coding

refactor

/refactor

Restructure the aws-blog-skills skill files (SKILL.md, references/, scripts/) or the bash harness without changing behavior, verifying with tests/run-all.sh after each step. Use when asked to reorganize, deduplicate, shorten, or split the skill, its scripts, or the harness.

Licence
MIT
Last repository change
03.11.2026

Assessment and security

90/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content25 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 03.11.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Restructure the aws-blog-skills skill files (SKILL.md, references/, scripts/) or the bash harness without changing behavior, verifying with tests/run-all.sh after each step. Use when asked to reorganize, deduplicate, shorten, or split the skill, its scripts, or the harness.

Original author description

Restructure the aws-blog-skills skill files (SKILL.md, references/, scripts/) or the bash harness without changing behavior, verifying with tests/run-all.sh after each step. Use when asked to reorganize, deduplicate, shorten, or split the skill, its scripts, or the harness.

How it works

  1. What "behavior" means here
  2. Process
Original SKILL.md headings · 40 lines, 261 words
SKILL.md preview
---
name: refactor
description: Restructure the aws-blog-skills skill files (SKILL.md, references/, scripts/) or the bash harness without changing behavior, verifying with tests/run-all.sh after each step. Use when asked to reorganize, deduplicate, shorten, or split the skill, its scripts, or the harness.
---

# Refactor Skill

Improve structure without changing what the skill does or what the harness checks.

## What "behavior" means here
- **Skill**: the workflow steps 0-7, the deliverable set (md + PNG + SVG + zip), the work-folder layout,
  the confirmed rules in `references/` and their dates, and the author bio text.
  Moving text between SKILL.md and a reference file is a refactor; changing any of the above is not.
- **Scripts**: which inputs each script accepts or rejects and its exit codes
  (`lint_prose.py` and `check_structure.py` exit 1 on findings, `check_urls.py` exit 1 on FAIL/REDIRECT,
  `package_blog.sh` writes no zip on failure).
- **Harness**: which inputs each hook and test accepts or rejects.

## Process

### 1. Analysis
- Read root `CLAUDE.md` and `skills/CLAUDE.md`
- Identify the target and the tests covering it (`tests/structure/test-plugin-structure.sh`,
  `tests/structure/test-skill-scripts.sh`, `tests/hooks/*.sh`)
- Record the baseline: `bash tests/run-all.sh` and `claude plugin details aws-blog-skills@aws-blog-skills`
  (always-on and on-invoke token cost)

### 2. Plan
Present the plan to the user:
- What will change
- What will NOT change (workflow steps, deliverables, confirmed rules, script exit codes)
- Expected effect on always-on cost (the SKILL.md `description` is loaded every session)
- Risk assessment (low/medium/high)

### 3. Execute
- Small steps; after each one run `bash tests/run-all.sh` and `claude plugin validate .`
- Keep rule dates `(YYYY-MM-DD 확정)` and the `lint_prose.py` term lists in sync
- Keep commits atomic

### 4. Verify
- All tests pass
- `git diff --stat` touches only the intended files
- A skill-text refactor still ships to users, so bump the PATCH version (see `release` skill)

Versions

RepositoryScoreLicence
This page · whchoi98/aws-blog-skills90MIT
froglet-studio/cosmic-shore100MIT
mgiovani/cc-arsenal100MIT
jongio/skills100MIT
boshu2/agentops100Apache-2.0
y-miyazaki/terraform-aws-base100Apache-2.0
mickeyyaya/evolve-loop100Apache-2.0
j0hanz/j0hanz-marketplace100MIT
kriscard/kriscard-claude-plugins100MIT

Database snapshot: 13.11.2026 · package version e9acdbbe0633 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100plugin-review
    Review changes to the aws-blog-skills plugin (skills/aws-blog-skills SKILL.md, references, scripts, .claude-plugin manifests, README) with confidence-based scoring, reporting only issues >= 75. Use when asked to review a diff or changes before commit or release. Named…
  • 90code-review
    Review criteria and confidence scoring for changes in the harness-eval monorepo (Bash scripts, hooks, SKILL/agent prompts, manifests). Use when reviewing a diff, PR, or file set in this repo.
  • 100refactor-safely
    Restructure, rename, split or move code without changing behaviour, and prove that nothing changed. Use this for any refactor, cleanup, file move, module split or dead code removal, including when it is only one step inside a larger task.
  • 92write-script-bash
    MUST use when writing Bash scripts.
  • 100dev-refactor
    Use when changing structure without changing behavior: restructure, extract, rename, dedupe or split code.
  • 95refactoring
    Reshape code while preserving behavior, using a passing behavior pin before and after each structural step. Use for renaming, extracting, inlining, moving, deduplicating, architecture improvement reports, module deepening, internal caller migration and deletion, external…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.