curl -fsSL https://api.cheatcodehq.com/install.sh | sh -s -- one-skill-to-rule-them-all --to allCopies 1 skill into each app's skills folder (Claude Code: ~/.claude/skills), after checking every file against rebelytics/one-skill-to-rule-them-all at commit c479475. Nothing else on your computer changes. To undo it, run the terminal command with --uninstall at the end; that also removes what the app added.
Then start a new session in your AI app and ask for the work in plain words; it picks the skill from its description. In Claude Code you can also type /one-skill-to-rule-them-all:task-observer.
See it in use
After installing, start a new session and say: Use the task-observer skill to set up an observation log in this folder, then review the session in session-notes.md and log what should change in my skills.
What else it can do, and its limits
- One skill, task-observer, that watches work sessions for corrections, repeated workflows and broken rules
- Writes each finding as its own Markdown file in an observation log, and never edits a skill on its own
- A weekly review turns open observations into staged skill updates you approve
- A rule that fails twice gets a proposed check, not a louder sentence
- Works best switched on for every session through a CLAUDE.md line or a session start hook; needs a folder it can write to and a terminal for its scripts
- Its instructions are long, about 700 lines plus reference files it loads when a step needs them
Sample input Recorded Oct 24, 2026 in Claude Code 2.1.308 with Sonnet 5.5. The video replays that session; nothing in it was acted or edited.
What's inside 1 skill
task-observerMonitors task execution for skill improvement opportunities. Use during ANY multi-step task, agentic workflow, or work session. Captures patterns, user corrections and methodology worth preserving as reusable skills. Also triggers in post-task feedback discussions and when the user mentions skill observations, the observation log, or skill taxonomy. Also known as \"One Skill to Rule Them All\" — trigger on this phrase too. IMPORTANT: invoke this skill before the FIRST tool call of any session and before writing or proposing a plan — any turn that will involve a tool call counts. This sentence is the session-start trigger and the only activation layer that survives an unreachable config file; pair it with a CLAUDE.md instruction or a harness session-start hook (references/environments.md) — description matching alone is not enforceable.
Monitors task execution for skill improvement opportunities. Use during ANY multi-step task, agentic workflow, or work session. Captures patterns, user corrections and methodology worth preserving as reusable skills. Also triggers in post-task feedback discussions and when the user mentions skill observations, the observation log, or skill taxonomy. Also known as \"One Skill to Rule Them All\" — trigger on this phrase too. IMPORTANT: invoke this skill before the FIRST tool call of any session and before writing or proposing a plan — any turn that will involve a tool call counts. This sentence is the session-start trigger and the only activation layer that survives an unreachable config file; pair it with a CLAUDE.md instruction or a harness session-start hook (references/environments.md) — description matching alone is not enforceable.
About
The meta-skill that builds and improves all your skills, including itself. Watches your work sessions (autonomous or human-led), captures patterns, corrections and judgement calls, and turns them into skill improvements and new skill candidates for your review. Practical application of the Augmented Expertise methodology. Open source: CC BY 4.0
Something wrong with this listing, or it did not install? Tell us