Agent Skill
Task Observer skill
task-observerrebelytics/one-skill-to-rule-them-allSKILL.md
Monitors task execution for skill improvement opportunities: logs patterns, user corrections and methodology worth preserving to the workspace, turns them into skill updates in a weekly review, and flags repeating work as new skills. Use during ANY multi-step task, agentic workflow, or work session. 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 session-start hook (references/environments.md). A subagent dispatched by a session already running it does not run it: it writes nothing and puts its findings in its report.
always on
196 tokname + description
once used
10,366 tokSKILL.md body
bundled files
135 scripts
repo stars
3.5kGitHub
Install the Task Observer skill
Skills CLI (Claude Code, Codex, Cursor and others)
npx skills add https://github.com/rebelytics/one-skill-to-rule-them-all --skill task-observer
Claude Code, by hand (all projects)
git clone --depth 1 https://github.com/rebelytics/one-skill-to-rule-them-all.git /tmp/one-skill-to-rule-them-all mkdir -p ~/.claude/skills cp -R /tmp/one-skill-to-rule-them-all ~/.claude/skills/task-observer
For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.
What it costs your context
Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.
| When | What loads | Cost |
|---|---|---|
| Every session | Name and description | 196 tok |
| When the agent uses it | The SKILL.md instructions | 10,366 tok |
| Only if opened | 13 bundled files (600 KB) | varies |
Until it is used, task-observer costs about 7.0× less than the median MCP server we measured (1,363 tokens on every turn). Skills vs MCP study
Checks
- Ships scripts the agent can run. Read them before installing.
- The instructions are over 5,000 tokens, the Agent Skills specification's guideline for SKILL.md.
- The instructions are over 500 lines; the specification suggests moving detail into reference files.
Checked 2026-10-22 · method
What's inside
The headings of its SKILL.md. Read the full file on GitHub.
- Task Observer — Continuous Skill Discovery & Improvement
- Reference files — load on demand, not up front
- Session Start Protocol
- When to Observe
- What to Watch For
- How to Log
- Referencing Observations
- Taxonomy (quick version)
- Archival on Write
- Surfacing Protocol
- Acting on Observations
- Feedback on this skill
- Quick Reference