relux:effect-write
Author a new `effect` declaration -- `expect` set, deps, expose surface, shell body, and cleanup -- with discipline about identity (one effect per service, unique-resources rule), config decomposition (Config + Service when the service rejects ENV), and the wrapper-effect re-expose rule. Use when the user asks to write a new effect, add an effect for a service the suite does not yet manage, wrap an existing effect with seed data / migrations / post-init steps, or decompose a file-configured service into Config + Service. Fires on phrasings like "write an effect for X", "add a Postgres effect", "wrap Db with seeded data", "this service needs a config file -- how do I model it". Modifying an existing effect's body or surface is `relux:effect-edit`; moving an effect between modules or removing one are mechanical operations with no skill of their own. Authoring tests that use the effect is `relux:test-write` (which hard-switches here when a required service has no effect yet).
Security AStatic scan found no risk patternsHow grading works ›
From the source SKILL.md
Write an effect declaration that models a single external service -- the SUT, or a dep of it. The discipline covers what goes in expect (identity = unique resources the service contends for), how the body decomposes when the service rejects ENV-shaped configuration (Config + Service), which shells survive setup (expose), whether cleanup is needed (usually no), and how wrapper effects re-export their dep shells.
What this skill does
relux:effect-write is a community-contributed Claude Code skill in the tools-misc sub-category. It ships as a SKILL.md file that Claude Code auto-discovers under ~/.claude/skills/effect-write/ and loads when your prompt matches the skill's trigger.
When to invoke it: Use when the user asks to write a new effect, add an effect for a service the suite does not yet manage, wrap an existing effect with seed data / migrations / post-init steps, or decompose a file-configured service into Config + Service. Fires on phrasings like "write an effect for X", "add a Postgres effect", "wrap Db with seeded data", "this service needs a config file -- how do I model it".
Who uses this skill
The relux:effect-write Claude Code skill is built for developers, power users, and teams automating repetitive workflows and improving developer experience. It's part of ClaudSkills (also referred to as Claude Skills or Claude Code Skills) — the open community-curated registry of 196,000+ SKILL.md files for Anthropic's Claude Code agent and the wider Claude ecosystem (Claude API, Claude Agent SDK).
How to install
Free
Manual install (2 steps)
mkdir -p ~/.claude/skills/effect-write
curl -L https://claudskills.com/skills/effect-write/SKILL.md \
-o ~/.claude/skills/effect-write/SKILL.md
Or just download SKILL.md directly and drop it into ~/.claude/skills/effect-write/. Claude Code auto-discovers it on next session.
Skills live at ~/.claude/skills/effect-write/SKILL.md on macOS/Linux, or %USERPROFILE%\.claude\skills\effect-write\SKILL.md on Windows. See the full install guide for step-by-step instructions.
Telegram
📱 Install from your phone or desktop Telegram
Open @claudskills_bot on Telegram, tap Open Desktop App, and the desktop app installs this skill for you. Or share the bot link with a colleague — they get the same one-tap install. Learn more →
Pro
One-click install via the desktop app
The ClaudSkills desktop app installs any skill directly into ~/.claude/skills/ with one click — no terminal required. Pro starts at $9/mo or $149 lifetime.
Pro
For the full experience including quality scoring and one-click install features for each skill — upgrade to Pro.
Frequently asked questions
How do I install the relux:effect-write Claude Code skill?
Install via the ClaudSkills desktop app (one click) or copy
SKILL.md from the source repository to
~/.claude/skills/effect-write/SKILL.md and restart Claude Code. Both flows are detailed at
claudskills.com/install/.
What does the relux:effect-write skill do?
Author a new `effect` declaration -- `expect` set, deps, expose surface, shell body, and cleanup -- with discipline about identity (one effect per service, unique-resources rule), config decomposition (Config + Service when the service rejects ENV), and the wrapper-effect re-expose rule. Use when the user asks to write a new effect, add an effect for a service the suite does not yet manage, wrap an existing effect with seed data / migrations / post-init steps, or decompose a file-configured service into Config + Service. Fires on phrasings like "write an effect for X", "add a Postgres effect", "wrap Db with seeded data", "this service needs a config file -- how do I model it". Modifying an existing effect's body or surface is `relux:effect-edit`; moving an effect between modules or removing one are mechanical operations with no skill of their own. Authoring tests that use the effect is `relux:test-write` (which hard-switches here when a required service has no effect yet).
Is this skill free to install?
Yes. ClaudSkills is an open registry — every skill keeps its source repository's license, and manual install via copy is free. ClaudSkills Pro ($9/mo, $79/yr, or $149 one-time) adds one-click install via the desktop app and a multi-signal Quality Score.
When should I use the relux:effect-write skill?
Use relux:effect-write when your Claude Code task falls under the Dev Tools category — specifically in the tools misc area. Claude Code auto-discovers installed skills and invokes the right one based on the task description, so you can also ask Claude directly (e.g. "use relux:effect-write" or describe the task and let Claude pick). Browse related skills at
/category/tools/.
What is a Claude Code skill and how does the relux:effect-write skill fit in?
A Claude Code skill is a
SKILL.md file that lives under
~/.claude/skills/<name>/ and tells the Claude Code CLI agent how to perform a specific task (instructions, prompts, allowed tools). Skills are auto-discovered at session start. relux:effect-write is one of 67,000+ skills indexed in the open ClaudSkills catalog, classified under the Dev Tools category. Learn more at
/learn/what-is-a-claude-skill/.
Attribution & license
Cite this skill
If you reference this skill in a blog post, paper, or documentation, you can cite it as:
APA
shizzard. (2026). relux:effect-write [Claude Code skill]. ClaudSkills. https://claudskills.com/skills/effect-write/
BibTeX
@misc{effect-write-2026,
author = {shizzard},
title = {relux:effect-write [Claude Code skill]},
year = {2026},
publisher = {ClaudSkills},
url = {https://claudskills.com/skills/effect-write/}
}Embed this skill
Promote, attribute, or link this skill from your own README, blog post, or documentation. All three snippets are free to use — no sign-up, no API key. More distribution surfaces →
Badge
[](https://claudskills.com/skills/effect-write/?utm_source=badge&utm_medium=readme&utm_campaign=skill_badge)
<script>
<script src="https://claudskills.com/embed/effect-write.js" async></script>
<iframe>
<iframe src="https://claudskills.com/embed/effect-write.html" width="100%" height="160" frameborder="0" loading="lazy" title="ClaudSkills: relux:effect-write"></iframe>
Security scan
Grade A · scanned 2026-09-28 — free static scan against the OWASP Agentic Skills Top 10.
The scan flagged 1 of 10 categories (filesystem), including lower-severity patterns. Patterns shown inside code fences are weighted as examples rather than instructions — read the grading methodology for what this does and does not guarantee.
- ✓ Prompt injection
- ✓ Data exfiltration
- ✓ Supply chain
- ✓ Reverse shell
- ✓ Credentials
- ✓ Execution
- ⚠ Filesystem
- ✓ Persistence
- ✓ Obfuscation
- ✓ Network
Show this grade on your repo (click to copy):
[](https://claudskills.com/skills/effect-write/#security)
More Dev Tools skills
Browse all Dev Tools skills in the ClaudSkills registry, or explore these other picks from the same category:
Part of Acreator Store — Adam Lankamer's AI tools:
PerfectStudio ·
Ucaption ·
UTagger ·
AutoXPoster ·
TestYourSkills ·
AutomationFlows ·
Au Naturel ·
Telegram @acreatorstore