Skip to content
mcp/skillhub

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.

3.5kCC-BY-4.0

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.

WhenWhat loadsCost
Every sessionName and description196 tok
When the agent uses itThe SKILL.md instructions10,366 tok
Only if opened13 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