#140140th of 149 in Skills, plugins and rules

one-skill-to-rule-them-all

Claude meta-skill that logs corrections and proposes updates to your other skills

Documentation ↗ Website ↗ Repository on GitHub ↗

Stars: 3.3k
License: CC-BY-4.0
Last commit: Oct 2026
Last release: Oct 2026
Language: Markdown

Missed the latest GitHub check; these facts may be older.

Overview

task-observer is a SKILL.md bundle with reference files and five helper scripts. It runs alongside Claude sessions, records corrections and repeated manual work as observation files, and proposes edits to existing skills or candidates for new ones. Changes go to staged copies, and nothing goes live until you install the updated bundle.

Who it is for: Claude users maintaining several skills who want them refined over time

Strengths

Proposals only: changes land in staged copies, installed skills stay untouched
Installs via `npx skills add` or a .skill bundle upload in the Claude apps
Writes one small observation file per entry under skill-observations/observation-log/
README reports 80+ contributors and 200+ issues and PRs closed

Weaknesses

Description matching under-triggers; needs a CLAUDE.md instruction or session-start hook
Written around Claude concepts; other platforms need adaptation
Claude.ai web and mobile get handoff documents only, with no filesystem logging
README says small skill libraries may be served as well by built-in memory

What it needs

no GPU
Needs Node.js (for skills CLI install), Claude or another skills-compatible agent
Models: Claude

Also in Skills, plugins and rules

See all 149

Also in Skills, plugins and rules
Rank	Project	Score
1	cavemanCuts token use in coding agents with terse replies and compressed inputs Live demo ↗ (opens in a new tab)112.2k starsApache-2.0	95 out of 100
2	skillsAgent skills for planning, TDD, debugging and code review292.4k starsMIT	94 out of 100
3	eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses280k starsMIT	94 out of 100
#4	impeccableDesign skill with 24 commands and a detector for AI-generated frontends Live demo ↗ (opens in a new tab)81.5k starsApache-2.0	94 out of 100
#5	ponytailSkill prompt that makes coding agents write less code and add tests164.1k starsMIT	92 out of 100

How to choose

Check which agent it targets and whether it works with the version you run.
Read what it adds to every prompt; big rule sets cost tokens on each call.
Prefer add-ons you can turn off per project.

Health

Releases: Not checked
Top contributor: Not checked
Security advisories: Not checked
Package advisories: Not checked
OpenSSF Scorecard: Not checked

Not read for this project yet: each refresh reads the facts of a few projects. Bots and coding-agent accounts are left out of the commit counts. Not part of the score: how we check.

License in plain words

CC-BY-4.0 Custom terms

Use it at work: Check
Change it and rebrand it: Check
Sell it or host it for others: Check

Your part: GitHub could not match these terms to a standard license. Read the license before you use it at work, rebrand it or host it for others.

A plain summary, not legal advice. Read the license on GitHub ↗ (opens in a new tab)

#140 of 149 in Skills, plugins and rules on Archestack, as of 15 Oct 2026.

In your README

The badge updates twice a day.

[![Archestack](https://archestack.com/badge/rebelytics/one-skill-to-rule-them-all.svg)](https://archestack.com/best-of-vibe-coding/projects/one-skill-to-rule-them-all/)

How badges work

On your site or blog

A card with the rank, score and signals, in light or dark to match the reader.

<iframe src="https://archestack.com/embed/best-of-vibe-coding/one-skill-to-rule-them-all/" title="one-skill-to-rule-them-all on Archestack" width="400" height="270" style="border:0;max-width:100%" loading="lazy"></iframe>

Preview the card

Best of Vibe Coding on GitHub

Each review comes from the project's README and facts we check on GitHub. The fix form opens with one-skill-to-rule-them-all filled in.