🔭
DataPython

Observatory

by juanandresgs

Observatory is a Data skill for Claude Code, published by juanandresgs in claude-ctrl.

192 stars28 forkson juanandresgs/claude-ctrlAdded 2026/09/06Repository updated 2026/08/07
ai-codingclaude-codeclaude-code-configclaude-code-hooksdeprecateddeveloper-toolsmulti-agentsdlcsoftware-engineeringunmaintained
Install in seconds
Install Observatory
Copy Observatory into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/juanandresgs/claude-ctrl/tree/main/skills/observatory ~/.claude/skills/observatory

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/juanandresgs/claude-ctrl.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
skills/observatory/SKILL.md in juanandresgs/claude-ctrl
Installs to
~/.claude/skills/observatory
Collection
One of 10 skills cataloged from this repository
Category
Data779 skills

What Observatory does

Observatory analyzes hook, agent, and dispatch health, then summarizes patterns, trends, and suggestion status. Use it to review operational metrics and manage the improvement loop.

Observatory is cataloged under Data on DirSkills. Observatory comes from a repository tagged ai-coding, claude-code, claude-code-config, claude-code-hooks and deprecated.

Documentation

README

/observatory — System Health Analysis and Self-Improvement Flywheel

Analyze the hook/agent/dispatch system's operational health, surface patterns, and manage the improvement suggestion lifecycle. The observatory is the system's honest self-exam — it tells you what's actually happening, not what should be happening.

Why this exists: Hooks emit metrics into obs_metrics. Agents propose improvements into obs_suggestions. Without synthesis, those signals accumulate silently. The observatory skill runs the analysis layer, presents findings in human-readable form, and drives the accept/reject/converge lifecycle that closes the improvement loop.


Subcommands

Parse $ARGUMENTS to determine the mode:

This is the opening of the README. Read the full README on GitHub.

Commands Observatory provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

  • /observatory

Frequently asked about Observatory

  • What else does juanandresgs publish alongside Observatory?

    Observatory is one of 10 skills that DirSkills catalogs from juanandresgs/claude-ctrl, the repository it ships in. Its siblings there include Codex Result Handling, Codex Runtime and Context Preservation. Each one is a separate skill with its own page in this directory, installs the same way Observatory does, and is maintained by juanandresgs in that same repository. The rest of the collection is listed on the juanandresgs/claude-ctrl page.

  • How does Observatory compare to other Data skills?

    Observatory ranks #709 by stars among the 779 Data skills in this catalog. The most-starred ones next to it are Benchmark Methodology, Jupyter Notebook and Solana. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Observatory against them. Open each page to compare what they document and how they install.

More from juanandresgs/claude-ctrl

Observatory is one of 10 skills cataloged on DirSkills from juanandresgs/claude-ctrl.

See all 10 skills
🧩
5h ago

Codex Result Handling

Codex Result Handling guides how to present Codex helper output back to the user without changing its meaning. Use it for review results, failures, setup issues, and any output that must preserve findings, severity, and boundaries.
AI Engineering
19228
⚙️
5h ago

Codex Runtime

Codex Runtime forwards a single rescue request to the codex-companion runtime from Claude Code. Use it in the codex:codex-rescue subagent when you need diagnosis, research, planning, or a fix request sent through one task call.
AI Engineering
19228
🧠
5h ago

Context Preservation

Context Preservation generates structured session summaries before compaction so work can resume without losing goals, changes, decisions, or next steps. Use it when a Claude Code session is about to be compacted or needs a handoff.
AI Engineering
19228
🧭
5h ago

Decide

Decide generates interactive configurators for complex trade-off decisions from research, plans, or conversation context. It is used when options have costs, dependencies, and multiple criteria to compare.
AI Engineering
19228
🔎
5h ago

Deep Research

Deep Research queries OpenAI, Perplexity, and Gemini in parallel for a topic and compares their findings. Use it when you need a synthesized research summary with agreements, disagreements, and unique insights.
AI Engineering
19228
🧠
5h ago

GPT-5.4 Prompting

GPT-5.4 Prompting gives rules and reusable blocks for writing compact Codex and GPT-5.4 prompts for coding, review, diagnosis, and research tasks. Use it when you need to structure a prompt with clear output, verification, and grounding constraints.
AI Engineering
19228