task-observer
task-observer is a skill in rebelytics/one-skill-to-rule-them-all, last changed 26 Oct 2026. It can touch credentials, change agent settings, run shell commands, reach the network, name web addresses and bundle scripts — read the findings before installing. Our pattern check found 1 item to review at commit ba696b2 on 27 Oct 2026.
Pattern check: 1 item to review · commit ba696b2 · 27 Oct 2026
InstallMonitors 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.
- Licence
- CC BY 4.0
- Repo stars
- 3.6k
- Folder last changed
- 26 Oct 2026 (opens in a new tab)
- Publisher
- rebelytics
- Files
- 29 files
- Checked
- ba696b2 (opens in a new tab) · 27 Oct 2026
Install
Each tab says whether it installs commit ba696b2, the one we checked, or the latest version.
No tab for your agent? Use Any agent for OpenCode, Goose, Windsurf (Devin Desktop), Zed, Roo Code, Factory Droid, Junie, Amp and Antigravity, and Claude Code for Cline. Kiro needs the folder copied by hand.
Pinned to commit ba696b2, the one we checked.
From your project's root folder:
tmp="$(mktemp -d)" &&
git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/rebelytics/one-skill-to-rule-them-all.git "$tmp" &&
git -C "$tmp" fetch -q --depth 1 origin ba696b2c2673be959dcd4a1dbdbc92085df8b41a &&
git -C "$tmp" checkout -q ba696b2c2673be959dcd4a1dbdbc92085df8b41a &&
rm -rf "$tmp/.git" &&
mkdir -p .claude/skills &&
mkdir .claude/skills/task-observer &&
cp -R "$tmp"/. .claude/skills/task-observer/ &&
rm -rf "$tmp"If Claude Code was already running and this created the skills folder, run /reload-skills.
Or install the task-observer plugin it ships in. Installs the latest version, not the one we checked. Installs everything in the plugin, including any hooks, MCP servers and scripts our check doesn't cover.
claude plugin marketplace add rebelytics/one-skill-to-rule-them-all --scope project &&
claude plugin install task-observer@one-skill-to-rule-them-all --scope projectPinned to commit ba696b2, the one we checked.
Skills in the Claude apps belong to your account rather than to a project.
Make task-observer.zip, with the skill folder at the top level:
tmp="$(mktemp -d)" &&
git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/rebelytics/one-skill-to-rule-them-all.git "$tmp" &&
git -C "$tmp" fetch -q --depth 1 origin ba696b2c2673be959dcd4a1dbdbc92085df8b41a &&
git -C "$tmp" checkout -q ba696b2c2673be959dcd4a1dbdbc92085df8b41a &&
rm -rf "$tmp/.git" &&
out="$(mktemp -d)" &&
cp -R "$tmp" "$out"/task-observer &&
(cd "$out" && zip -qr - task-observer) > task-observer.zip &&
rm -rf "$tmp" "$out"In Claude, open Customize > Skills, select +, then + Create skill > Upload a skill, and choose task-observer.zip.
On Free, Pro and Max plans, turn on Code execution and file creation (Create and edit files in newer settings) under Settings > Capabilities.
Pinned to commit ba696b2, the one we checked.
From your project's root folder:
tmp="$(mktemp -d)" &&
git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/rebelytics/one-skill-to-rule-them-all.git "$tmp" &&
git -C "$tmp" fetch -q --depth 1 origin ba696b2c2673be959dcd4a1dbdbc92085df8b41a &&
git -C "$tmp" checkout -q ba696b2c2673be959dcd4a1dbdbc92085df8b41a &&
rm -rf "$tmp/.git" &&
mkdir -p .agents/skills &&
mkdir .agents/skills/task-observer &&
cp -R "$tmp"/. .agents/skills/task-observer/ &&
rm -rf "$tmp"Codex picks up new skills on its own; restart it if this one does not appear.
Pinned to commit ba696b2, the one we checked.
From your project's root folder:
tmp="$(mktemp -d)" &&
git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/rebelytics/one-skill-to-rule-them-all.git "$tmp" &&
git -C "$tmp" fetch -q --depth 1 origin ba696b2c2673be959dcd4a1dbdbc92085df8b41a &&
git -C "$tmp" checkout -q ba696b2c2673be959dcd4a1dbdbc92085df8b41a &&
rm -rf "$tmp/.git" &&
mkdir -p .cursor/skills &&
mkdir .cursor/skills/task-observer &&
cp -R "$tmp"/. .cursor/skills/task-observer/ &&
rm -rf "$tmp"Pinned to commit ba696b2, the one we checked.
From your project's root folder:
tmp="$(mktemp -d)" &&
git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/rebelytics/one-skill-to-rule-them-all.git "$tmp" &&
git -C "$tmp" fetch -q --depth 1 origin ba696b2c2673be959dcd4a1dbdbc92085df8b41a &&
git -C "$tmp" checkout -q ba696b2c2673be959dcd4a1dbdbc92085df8b41a &&
rm -rf "$tmp/.git" &&
mkdir -p .github/skills &&
mkdir .github/skills/task-observer &&
cp -R "$tmp"/. .github/skills/task-observer/ &&
rm -rf "$tmp"In a running Copilot CLI session, run /skills reload.
Pinned to commit ba696b2, the one we checked.
From your project's root folder:
tmp="$(mktemp -d)" &&
git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/rebelytics/one-skill-to-rule-them-all.git "$tmp" &&
git -C "$tmp" fetch -q --depth 1 origin ba696b2c2673be959dcd4a1dbdbc92085df8b41a &&
git -C "$tmp" checkout -q ba696b2c2673be959dcd4a1dbdbc92085df8b41a &&
rm -rf "$tmp/.git" &&
mkdir -p .gemini/skills &&
mkdir .gemini/skills/task-observer &&
cp -R "$tmp"/. .gemini/skills/task-observer/ &&
rm -rf "$tmp"In a running session, run /skills reload.
Or use Gemini CLI’s own installer. Installs the latest version, not the one we checked.
gemini skills install https://github.com/rebelytics/one-skill-to-rule-them-all.git --scope workspacePinned to commit ba696b2, the one we checked.
Codex, Cursor, Copilot, VS Code, Gemini CLI, OpenCode, Goose, Amp and Zed all read .agents/skills; Claude Code and Kiro list only their own folders.
From your project's root folder:
tmp="$(mktemp -d)" &&
git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/rebelytics/one-skill-to-rule-them-all.git "$tmp" &&
git -C "$tmp" fetch -q --depth 1 origin ba696b2c2673be959dcd4a1dbdbc92085df8b41a &&
git -C "$tmp" checkout -q ba696b2c2673be959dcd4a1dbdbc92085df8b41a &&
rm -rf "$tmp/.git" &&
mkdir -p .agents/skills &&
mkdir .agents/skills/task-observer &&
cp -R "$tmp"/. .agents/skills/task-observer/ &&
rm -rf "$tmp"Or use the skills CLI from skills.sh. Installs the latest version, not the one we checked. The skills CLI reports installs to skills.sh unless you set DISABLE_TELEMETRY=1.
npx skills@1.7.4 add rebelytics/one-skill-to-rule-them-all --skill task-observerWhat it can touch
From the files and frontmatter at commit ba696b2. This is how much a skill can do, not whether it is risky.
What it can touch: Shell, network or credentials
Runs shell commands
Its instructions or files give the agent commands to run on your computer.
Reaches the network
It sends or fetches data over the internet, for example with curl, an HTTP library or a package install.
Names web addresses
It mentions outside web addresses the agent may visit. We list them but don't follow them.
Bundles scripts
The folder holds code files the agent may run.
scripts/migrate-log.py · scripts/skill-load.sh · scripts/validate-skill-bundle.py
Touches credentials
It reads, asks for or contains keys, tokens, passwords or similar secrets.
scripts/validate-skill-bundle.py:1241
Changes agent settings
It writes to agent memory or settings files such as CLAUDE.md, AGENTS.md or .claude/settings.json.
README.md:20 · README.md:91 · references/environments.md:1001
Pattern check
Pattern check: 1 item to review · commit ba696b2 · 27 Oct 2026
R18 · HighInstructions in HTML comments or hidden HTML
.github/ISSUE_TEMPLATE/report-a-failure.md:17 (opens in a new tab)<!-- Harness (Claude Code, Cowork, Codex, …), OS and shell, installed version of the skill. -->
We checked every text file in this skill, at commit ba696b2 on 27 Oct 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.
How the check worksReport an incorrect finding
Outside links we did not follow
- https://json.schemastore.org/claude-code-marketplace.json
- https://rebelytics.com
- https://json.schemastore.org/claude-code-plugin-manifest.json
- https://github.com/rebelytics/one-skill-to-rule-them-all
- https://github.com/rebelytics/one-skill-to-rule-them-all/blob/main/SECURITY.md
- https://www.contributor-covenant.org/version/2/1/code_of_conduct.html][v2.1
- https://www.contributor-covenant.org/faq][FAQ
- https://www.contributor-covenant.org/translations][translations
- https://www.contributor-covenant.org
- https://www.contributor-covenant.org/version/2/1/code_of_conduct.html
Show 40 more
- https://github.com/mozilla/diversity
- https://www.contributor-covenant.org/faq
- https://www.contributor-covenant.org/translations
- https://www.rebelytics.com/augmented-expertise/
- https://github.com/AllstarGER/one-skill-to-rule-them-all
- https://github.com/tmogeid/skill-prompt-evolution
- https://github.com/hqhq1025/skill-optimizer
- https://github.com/rebelytics/one-skill-to-rule-them-all/blob/main/USER-GUIDE.md
- https://creativecommons.org/licenses/by/4.0/
- https://github.com/rebelytics/one-skill-to-rule-them-all/
- https://github.com/VoltAgent/awesome-agent-skills
- https://www.getclaudeskills.com/skills/task-observer-rebelytics
- https://claudemarketplaces.com/skills/rebelytics/one-skill-to-rule-them-all/task-observer
- https://surfskills.surf/s/rebelytics/one-skill-to-rule-them-all/task-observer
- https://github.com/BehiSecc/awesome-claude-skills
- https://www.kimi.ai/resources/claude-code-skills
- https://www.corpusiq.io/docs/hermes/skills/catalog/task-observer-setup
- https://skillfoxx.ru/en/skills/task-observer-one-skill-to-rule-them-all
- https://zread.ai/rebelytics/one-skill-to-rule-them-all
- https://www.typingmind.com/skills/rebelytics-task-observer
- https://github.com/karanb192/awesome-claude-skills
- https://github.com/iamneilroberts/claude-skills
- https://x.com/DanKornas/status/2074370062031462787
- https://www.linkedin.com/posts/kellihrivnak_to-those-building-out-skills-in-claude-lets-share-7478433968837517312-UhPj/
- https://www.tiktok.com/@maverickgpt/video/7661705764901227807
- https://levelupwithai.substack.com/p/this-is-how-you-use-claude-in-2026
- https://dreasaez.medium.com/your-ai-skills-are-silos-heres-how-to-fix-that-bdb04a507785
- https://www.instagram.com/p/DXwqpPQj62s/
- https://www.instagram.com/reels/DaN0yYtPzjY/
- https://www.instagram.com/reels/DavN_06t105/
- https://www.linkedin.com/posts/myriamjessier_i-feel-like-i-am-part-of-an-mlm-sponsored-share-7483809490992140288-6Lwm/
- https://brainfck.org/t/self-improving-agents/
- https://core.today/blog/task-observer-meta-skill
- https://x.com/tom_doerr/status/2072251701608784049
- https://x.com/VaibhavSisinty/status/2063290847723192610
- https://www.instagram.com/reels/DaHqy6MApwN/
- https://www.instagram.com/reels/Dayv8dvjeLi/
- https://www.linkedin.com/posts/johannesmanske_vor-8-wochen-war-ki-noch-sparringspartner-share-7461096580809547777-0ty7/
- https://xaviertingai.com/tools/task-observer.html
- https://lazyowen.com/guides/claude-skills-top5-0815
Format check
Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.
Agent Skills specPasses with warnings
The open format from agentskills.io, held to what the strictest agents enforce, so one folder loads everywhere.
- Warning
Fields outside the spec: core_max_lines and version. Uploads to the Claude apps and API, and the spec's validator, reject the file; most agents ignore these fields. O1
Fix: Delete them for a portable skill, or keep them if you only target the agents that read them.
- Warning
The body is 671 lines; the spec suggests under 500. B1
Fix: Move detailed sections into reference files and link to them from SKILL.md.
- Warning
The body is about 10,890 tokens (approx.); the spec suggests under 5,000. B2
Fix: Move detail into reference files that the agent reads only when needed.
- Note
Reference files that SKILL.md doesn't link: .github/ISSUE_TEMPLATE/propose-a-change.md, .github/ISSUE_TEMPLATE/report-a-failure.md, .github/pull_request_template.md, CODE_OF_CONDUCT.md, SECURITY.md and 2 more. Anthropic suggests linking every reference file directly from SKILL.md. B4
Fix: Link each one from SKILL.md and say when to read it.
- Note
Reference files over 100 lines with no table of contents at the top: USER-GUIDE.md (125 lines), references/migration.md (263 lines) and references/starter-principles.md (505 lines). B5
Fix: Add a short list of the sections at the top of each.
- Warning
Claude CodePasses
Claude Code reads its own extra fields, ignores unknown ones, and still loads a skill whose frontmatter is broken, without its fields.
- Note
Claude Code ignores fields it doesn't know: core_max_lines and version. O1
Fix: Check the spelling against Claude Code's field list, or delete them.
- Note
The body is 671 lines; the spec suggests under 500. Claude Code's docs say the same. B1
Fix: Move detailed sections into reference files and link to them from SKILL.md.
- Note
The body is about 10,890 tokens (approx.); the spec suggests under 5,000. After compaction Claude Code keeps only the first 5,000 tokens of a skill. B2
Fix: Move detail into reference files that the agent reads only when needed.
- Note
Reference files that SKILL.md doesn't link: .github/ISSUE_TEMPLATE/propose-a-change.md, .github/ISSUE_TEMPLATE/report-a-failure.md, .github/pull_request_template.md, CODE_OF_CONDUCT.md, SECURITY.md and 2 more. Anthropic suggests linking every reference file directly from SKILL.md. B4
Fix: Link each one from SKILL.md and say when to read it.
- Note
Reference files over 100 lines with no table of contents at the top: USER-GUIDE.md (125 lines), references/migration.md (263 lines) and references/starter-principles.md (505 lines). B5
Fix: Add a short list of the sections at the top of each.
- Note
Claude apps & API uploadFails
Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.
- Error
Upload and packaging fail on fields outside the spec: core_max_lines and version. O1
Fix: Delete them, and keep your own data under metadata as text values.
- Note
The description is 999 characters. The claude.ai Help Center says 200 at most, though Anthropic's API docs and validator allow 1,024. D4
Fix: If the claude.ai upload refuses it, trim the description to 200 characters.
- Note
The body is 671 lines; the spec suggests under 500. Anthropic's guidance says the same. B1
Fix: Move detailed sections into reference files and link to them from SKILL.md.
- Note
The body is about 10,890 tokens (approx.); the spec suggests under 5,000. Anthropic's guidance says the same. B2
Fix: Move detail into reference files that the agent reads only when needed.
- Note
Reference files that SKILL.md doesn't link: .github/ISSUE_TEMPLATE/propose-a-change.md, .github/ISSUE_TEMPLATE/report-a-failure.md, .github/pull_request_template.md, CODE_OF_CONDUCT.md, SECURITY.md and 2 more. Anthropic suggests linking every reference file directly from SKILL.md. B4
Fix: Link each one from SKILL.md and say when to read it.
- Note
Reference files over 100 lines with no table of contents at the top: USER-GUIDE.md (125 lines), references/migration.md (263 lines) and references/starter-principles.md (505 lines). B5
Fix: Add a short list of the sections at the top of each.
- Error
OpenAI (Codex & API)Passes with warnings
Codex finds SKILL.md by its exact name and needs a description; OpenAI's Skills API checks the frontmatter against the spec and caps uploads.
- Warning
Fields outside the spec: core_max_lines and version. Codex ignores them; OpenAI doesn't say whether its upload accepts them. O1
Fix: Delete them, or move your own data under metadata as text values.
- Warning
VS Code & CopilotPasses
VS Code reads skills one folder below .github/skills, .claude/skills or .agents/skills and falls back to the folder name when the name is missing or differs; GitHub's Copilot docs require the exact name SKILL.md.
- Note
VS Code ignores fields it doesn't support: core_max_lines and version. O1
Fix: Delete them unless another agent you target reads them.
- Note
SKILL.md
Files
29 files