Task Observer: One Skill to Rule Them All

    1

    The meta-skill that builds and improves all your skills, including itself.

    Free

    11 usesSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Task Observer: One Skill to Rule Them All

    Example session with this skill installed

    Any observations logged this session?

    • Read your context and instructions
    • Compiled the task observer

    5 observations logged this session. All are logged for your next scheduled review; nothing has been changed in any skill file.

    Improvements to existing skills

    SkillWhat happenedProposed changeType
    conversation-defaultsTwice this session, something was reported as missing on the strength of a tool that summarises rather than shows: a spreadsheet connector that rendered 11 of 13 rows without saying so, then a page fetch that paraphrased. You corrected both.Second violation of the same rule, so no rewording: an absence claim must name the raw artefact it was checked against, or it does not ship.open-source
    outreach-pipelineThe "is the brand already listed?" check ran against the repository a website names as its source. The site's list and the repository's list turned out to be different lists.Run the check on the page that was actually cited, never on its claimed upstream.open-source
    outreach-pipelineA temporary import file was left for you to delete, as a line in the closing summary.Log temporary files as they are created and delete them as a step of the run, not a line of its report.open-source
    api-companionA tool's required argument is named differently from the field its own discovery call returns, so the first call failed.Document the argument name, not only the concept.open-source
    outreach-pipelineA cap written to limit incremental prompt tuning got in the way of a deliberate scope expansion.State the rule's purpose, so structural changes are recognised as outside it.internal

    Principle captured

    A tool that answers a question about an artefact cannot establish a negative about it. Presence can be established by a summary; absence cannot.

    Next steps

    • Your next scheduled review picks these up automatically.
    • To act on one now instead, say "act on #1626" and a staged update is prepared for you to review.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Creating skills is powerful but time-consuming, and the skills that do get built stay frozen: they never learn from how you actually use them.

    Task Observer is a meta-skill that runs alongside your work, watches what you do, and does two things:

    1. It identifies new skills for you. It spots repeating patterns in your work, flags them as skill candidates and helps you build them, so you get skills without staring at a blank page.

    2. It improves your existing skills. It notices corrections you make, preferences you express and gaps in your current skills, then suggests specific updates.

    It also watches itself. If it misses something, triggers where it shouldn't, or its own observation format could be clearer, it logs that too. The skill that improves all your skills also improves itself.

    The observer never modifies your skills directly. It produces recommendations that you review, so you stay in control of what changes and when. Patterns that apply across skills are captured as cross-cutting principles, and new or updated skills are checked against them.

    Who it's for: anyone who uses skills and wants them to get better over time instead of staying frozen. You don't need to be a developer. One honest boundary: its value compounds with scale. With a handful of skills, your assistant's built-in memory may cover much of the same ground; once editing skills directly stops feeling manageable, the observation log and review cycle pay off.

    Track record: over 1,500 observations logged across 82 skills, most of them turned into skill improvements. The current version includes improvements suggested by 65 different users across 141 issues and 33 pull requests.

    Open source under CC BY 4.0: github.com/rebelytics/one-skill-to-rule-them-all

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skill Creator Skills.

    Built for Claude: other agents need some adaptation, because the content assumes Claude's architecture. Activation needs one extra step: description matching alone under-triggers, so add the activation line to your CLAUDE.md (or your platform's equivalent) and check in a new session that it runs. The full experience needs filesystem access (Claude Cowork, or Claude Code in the desktop app). The formal log and review cycle pay off most as your skill library grows; with a handful of skills, your assistant's built-in memory may be enough.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    11 uses

    Times used to date

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Software
    Node.jsPython

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    File Scopes

    skill-observations/**
    skill-updates/**

    Shell: runs short bash snippets and one helper script to derive observation ids and create log files. Read and write files: only its own observation log and staged skill updates in your workspace folder. It never modifies your installed skills directly, and it never needs to fetch an external URL.

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    Task Observer runs alongside your workflow to identify repetitive patterns you haven't automated yet and suggests improvements to your current skills based on how you actually use them. It solves the 'blank page' problem of creating skills and prevents existing ones from becoming outdated as your needs evolve.

    Task Observer operates on a 'review-first' model; it logs observations and generates specific recommendations, but it never modifies your skill code or prompts without your explicit approval. You retain full control over which patterns are codified and when updates are applied.

    While this skill provides value to any power user, its benefits compound as your library grows; it is most effective once you have enough skills that manually tracking every correction or preference becomes unmanageable. It is designed to bridge the gap between simple chat memory and professional-grade skill management.

    You will receive the core meta-skill prompt, the observation logging framework, and access to the community-driven updates via the CC BY 4.0 open-source repository. This includes the logic for identifying cross-cutting principles that ensure all your skills remain consistent with one another.

    Task Observer is platform-agnostic and designed to work with any sophisticated AI agent or environment that supports custom skills or system prompts, including Claude Code and other advanced LLM interfaces. Because it is licensed under CC BY 4.0, you also benefit from a version history shaped by hundreds of real-world user improvements.

    New in Prompt & Skill Engineering

    Free