refactor-solo-maintenance SKILL.md skillA

refactor-solo-maintenance from lstr-1/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add lstr-1/skills/refactor-solo-maintenance@git:20260807.6f46eea

Pins git:20260807.6f46eea in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
lstr-1/skills
Path
refactor-solo-maintenance/SKILL.md
Versions recorded
1
Latest version
git:20260807.6f46eea, committed Aug 7, 2026
Size
18,846 bytes
Repository stars
2
License
none declared

Produces a measured, RICE-ranked refactoring plan plus a machine-readable backlog that drives a solo developer's repository toward ~1 active maintenance month per year. Invoke when analyzing an existing codebase, GitHub Actions pipeline, AI-agent configuration, or maintenance cadence for refactoring opportunities, when maintenance load must be reduced to a fixed annual budget, or when refactors must be prioritized by effort and impact. Triggers on "refactor my workflow…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# refactor-solo-maintenance

Audits an existing repository across four domains — codebase architecture, GitHub Actions CI/CD, AI-agent integration, and maintenance cadence — then emits a RICE-ranked refactoring plan and a machine-readable backlog reconciled against a hard annual maintenance budget of ~160 hours (~1 active month per year).

## When to Use

- A solo developer wants to reduce recurring maintenance load on an existing repository to a fixed annual budget.
- Existing CI/CD workflows, module boundaries, or agent configuration must be evaluated for automation and delegation opportunities.
- A refactoring backlog exists but is unprioritized, and quick wins must be sequenced ahead of architectural surgery.
- Maintenance time must be quantified and defended against a target rather than estimated by intuition.

## When NOT to Use

- Do NOT use for greenfield repositories. There is no baseline to measure, so every finding would be fabricated.
- Do NOT use to implement refactors. This skill produces a plan and a backlog; execution is a separate, explicitly requested task.
- Do NOT use for single-PR review, syntax questions, or mechanical renames.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add lstr-1/skills/refactor-solo-maintenance@sha256:f0c30e3d9dc08a1a

The line at the top of this page pins the label git:20260807.6f46eea, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_e4f3ullmstuu77vb.svg)](https://markdownregistry.com/a/art_e4f3ullmstuu77vb)

5 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Aug 7, 2026.

versioncommittedcommitsizeaudit
git:20260807.6f46eea latest2026-08-07 6f46eea 18,846 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (18846 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

lstr-1/skills · 2 stars · license none declared · pushed 2026-11-04 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_e4f3ullmstuu77vb
GET https://markdownregistry.com/api/v1/resolve?ref=lstr-1/skills/refactor-solo-maintenance
GET https://markdownregistry.com/api/v1/blob/f0c30e3d9dc08a1ac93876fbf78a1aae34cecfa3f0321dd12cff2f4770b06127

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from lstr-1/skills

create-skill SKILL.md skill
lstr-1/skills · create-skill/SKILL.md · Use when the user wants to create, design, or generate a new AI agent skill (SKILL.md) from a problem description. This…
v0.1.0 · audit A · 2 stars
nlm-meta-study SKILL.md skill
lstr-1/skills · nlm-meta-study/SKILL.md · Create scientific meta-studies on any topic using Gemini Notebook (NotebookLM). Invoke for systematic reviews…
v0.1.0 · audit A · 2 stars
reasoning-framework SKILL.md skill
lstr-1/skills · reasoning-framework/SKILL.md · Enforces the mandatory 6-step Zero-Shot Chain-of-Thought reasoning framework on complex queries using the MCP Reasoning…
v0.2.4 · audit A · 2 stars
research-to-feature SKILL.md skill
lstr-1/skills · research-to-feature/SKILL.md · Produces a single RICE-scored feature recommendation backed by a NotebookLM meta-study and a business use-case review…
v0.1.3 · audit A · 2 stars
review-business-use-case SKILL.md skill
lstr-1/skills · review-business-use-case/SKILL.md · Reviews provided resources (files, documents, codebases, MCP server definitions, third-party skill manifests) for the…
v0.1.3 · audit A · 2 stars
rice-scoring SKILL.md skill
lstr-1/skills · rice-scoring/SKILL.md · Guides the user through calibrated RICE prioritization (Reach × Impact × Confidence ÷ Effort) and produces a ranked…
v0.1.1 · audit A · 2 stars

Every file in lstr-1/skills

Browse by kind, by grade A, or by owner.