Excel and CSV Data Analysis
bytedance/deer-flow
Analyzes uploaded Excel and CSV files with SQL through DuckDB, producing schema inspections, statistical summaries and exports to CSV, JSON or Markdown.
Use this skill before calling querysystemdb or when diagnosing pokoclaw.
Apache-2.0Auto-check passed
Install System Observe
$ npx skills add danielwpz/pokoclaw --skill system-observe -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install danielwpz/pokoclaw system-observe --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/danielwpz/pokoclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/system-observe .claude/skills/system-observe && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "system-observe" agent skill from https://github.com/danielwpz/pokoclaw/tree/main/skills/system-observe into .claude/skills/system-observe/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "system-observe", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/danielwpz/pokoclaw/tree/main/skills/system-observeType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add danielwpz/pokoclaw --skill system-observe -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install danielwpz/pokoclaw system-observe --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/danielwpz/pokoclaw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/system-observe .agents/skills/system-observe && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "system-observe" agent skill from https://github.com/danielwpz/pokoclaw/tree/main/skills/system-observe into .agents/skills/system-observe/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "system-observe", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add danielwpz/pokoclaw --skill system-observe -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install danielwpz/pokoclaw system-observe --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/danielwpz/pokoclaw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/system-observe .cursor/skills/system-observe && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "system-observe" agent skill from https://github.com/danielwpz/pokoclaw/tree/main/skills/system-observe into .cursor/skills/system-observe/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "system-observe", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/danielwpz/pokoclaw.git --path skills/system-observe--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add danielwpz/pokoclaw --skill system-observe -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install danielwpz/pokoclaw system-observe --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/danielwpz/pokoclaw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/system-observe .gemini/skills/system-observe && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "system-observe" agent skill from https://github.com/danielwpz/pokoclaw/tree/main/skills/system-observe into .gemini/skills/system-observe/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "system-observe", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install danielwpz/pokoclaw system-observeInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add danielwpz/pokoclaw --skill system-observe -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/danielwpz/pokoclaw.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/system-observe .github/skills/system-observe && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "system-observe" agent skill from https://github.com/danielwpz/pokoclaw/tree/main/skills/system-observe into .github/skills/system-observe/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "system-observe", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add danielwpz/pokoclaw --skill system-observe -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install danielwpz/pokoclaw system-observe --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/danielwpz/pokoclaw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/system-observe .opencode/skills/system-observe && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "system-observe" agent skill from https://github.com/danielwpz/pokoclaw/tree/main/skills/system-observe into .opencode/skills/system-observe/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "system-observe", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
system-observe- GitHub stars
- 142
- Token cost
- ~1.5k tokens
- SKILL.md length
- 698 words
- Files
- 6 (incl. references)
- Skills in repo
- 4
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Use this skill before calling querysystemdb or when diagnosing pokoclaw.
- SKILL.md covers Channels, Required first reads, Working rules and Available references, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
System Observe is an agent skill from danielwpz/pokoclaw. Use this skill before calling querysystemdb or when diagnosing pokoclaw. It teaches how to query the read-only system database, including conversation history before compaction or context clear, and how to combine database facts with runtime logs and authoritative source definitions.
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `references/log-recipes.md`, `references/meditation.md` and `references/query-recipes.md`).
It works with SQL. The repository describes itself as: The claw that actually ships 🚀. The licence is Apache-2.0.
Example prompts
- “/system-observe”
What it can do on your machine
Read from SKILL.md and the folder at commit 6cfb6c1. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
System Observe loads about 1.5k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 75 tokens; SKILL.md has 698 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from danielwpz/pokoclaw at commit 6cfb6c1, republished under its Apache-2.0 licence (© danielwpz). 698 words, ~1,483 tokens.
Download SKILL.mdSave it as
.claude/skills/system-observe/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- system-observe
- description
- Use this skill before calling query_system_db or when diagnosing pokoclaw. It teaches how to query the read-only system database, including conversation history before compaction or context clear, and how to combine database facts with runtime logs and authoritative source definitions.
- skillKey
- pokoclaw/system-observe
System Observe
Use this skill to inspect pokoclaw itself.
Channels
- Live runtime status: Main Agent only, global current-running state across active runs, background tasks, cron task runs, and suspect durable rows that still claim to be running without a matching live run. Use
get_runtime_statusfirst when you need to know what is actively running right now. Use itsrunIdform to inspect one low-level run, including a retained just-finished snapshot when still available in process memory. - System database: durable facts such as sessions, messages, task runs, cron jobs, approvals, permission grants, and delegated approval history.
- Runtime log: host-side operational evidence such as failures, routing decisions, retries, crashes, and subsystem errors.
- Source code and references: authoritative schema definitions and implementation behavior.
- Meditation self-harness: a background self-optimization flow. It is not part of the core live run-status surface, but when the question is specifically about whether Meditation ran, why it skipped or failed, or where its artifacts and outputs live, use
references/meditation.md.
Choose one or more channels based on the question. Do not force a fixed order for every task.
Required first reads
- If the task involves database facts, approval history, delegated approval, or SQL:
- Read
references/query-recipes.mdfirst. - If exact table or column names matter, read
references/schema-overview.md. - If that is still insufficient, inspect:
../../src/storage/schema/tables.ts../../src/storage/schema/types.ts../../src/storage/migrate/files/0001_init.sql../../src/storage/migrate/files/0002_agent_runtime_modes.sql../../src/storage/migrate/files/0003_a2ui_surface_publications.sql../../src/storage/migrate/files/0004_shell_process_runs.sql../../src/storage/migrate/files/0005_shell_process_output_chunks.sql../../src/storage/migrate/files/0006_context_clear.sql../../src/storage/migrate/files/0007_context_clear_recovery.sqlThe schema truth lives intables.tsplus the migration SQL files.
- Only then use
query_system_dbfor live schema discovery.
- Read
- If the task involves live runtime status payload semantics for
get_runtime_status:- Read
references/runtime-status.mdfirst.
- Read
- If the task involves runtime logs:
- Read
references/log-recipes.mdfirst.
- Read
- If the task explicitly involves Meditation or self-harness background runs:
- Read
references/meditation.mdfirst.
- Read
- If the task is really about implementation behavior:
- Read the relevant source files first, then use DB facts or logs as supporting evidence.
Working rules
- For a question about what is running now, start with
get_runtime_statusbefore querying the DB. - In the default
get_runtime_statusresult,runningWorkis the current-running main view. Do not treat completed, failed, cancelled, or not-yet-scheduled work as missing evidence; query the DB/logs only when the user asks for history or cause. - If
get_runtime_statusreturnssuspectRunningTaskRunsorsuspectRunningCronJobs, treat those as explicit inconsistency signals: durable state still says running, but the matching live run/current task linkage is absent. - If the
runIdform says a run is not present in live memory, treat that as "not currently active here and no retained in-memory snapshot was found" rather than proof of success; then use the DB to determine whether it completed, failed, or was cancelled. - If the answer depends on live in-memory state that
get_runtime_statusdoes not expose, say that clearly and do not guess. - Adapt an existing query recipe before inventing a new exploratory query.
- When recovering conversation history before compaction or context clear, start with the dedicated recipe in
references/query-recipes.md. Do not begin by listing tables or runningPRAGMA table_info(...)unless that recipe fails because the schema has actually changed. - For conversation history, extract user-visible text and page by
seq. Do not bulk-select rawpayload_json, which may contain large reasoning signatures and tool payloads that pollute the current context. - Delegated approval investigation uses the same DB and log channels; start from the approval recipes and approval log hints in the references.
- Separate facts from inference.
- Include exact IDs, statuses, timestamps, and error text when available.
- If one source is insufficient, combine multiple sources and say how they relate.
Show full SKILL.md (132 more words)Show less
Available references
references/schema-overview.mdreferences/query-recipes.mdreferences/log-recipes.mdreferences/runtime-status.mdreferences/meditation.md
Do not skip the required first reads above when they directly apply.
Anti-patterns
- Do not guess table names or column names.
- Do not skip required reference files when they directly cover the task.
- Do not start with exploratory schema probing when the references or source files already tell you what to query.
- Do not spam repeated
sqlite_masterorPRAGMA table_info(...)queries unless you genuinely need schema discovery. - Do not use
query_system_dbas your first move for schema exploration when a recipe or source definition is already available. - Do not bulk-load raw message payloads when a text-only, bounded history query can answer the question.
- Do not rely on logs alone when the database already contains the durable fact you need.
- Do not present inference as fact.
© danielwpz, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 5 other files (references) in skills/system-observe of danielwpz/pokoclaw.
- SKILL.md
- references/log-recipes.md
- references/meditation.md
- references/query-recipes.md
- references/runtime-status.md
- references/schema-overview.md
Open the folder on GitHubat commit 6cfb6c1
Compare with similar skills
System Observe next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| System Observe this skilldanielwpz/pokoclaw | 142 | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | |
| Excel and CSV Data Analysisbytedance/deer-flow | 83k | 4 repos | ~2.2k | Automated safety check: Pass | MIT | |
| Clickhouse Logs Queriessupabase/supabase | 111k | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | |
| Review PRapache/shardingsphere | 21k | — | ~6.4k | Automated safety check: Pass | Apache-2.0 | |
| Django Filter Benchmarksaleor/saleor | 23k | — | ~2.3k | Automated safety check: Pass | BSD-3-Clause | |
| Geoflowyaojingang/GEOFlow | 3.8k | — | ~722 | Automated safety check: Pass | AGPL-3.0 |
Similar skills
- Official
Clickhouse Logs Queries
supabase/supabase
Write, review, and migrate Supabase logs queries against the ClickHouse-backed logs table (the logs.all.otel analytics endpoint).
Review PR
apache/shardingsphere
Review Apache ShardingSphere or user-authorized downstream pull requests and PR discussions from public or authorized repository evidence.
Django Filter Benchmark
saleor/saleor
Benchmarks Django ORM filters in Saleor by generating bulk data, extracting the SQL and running EXPLAIN ANALYZE to check index usage.
Geoflow
yaojingang/GEOFlow
Operate/develop GEOFlow CLI/Laravel/admin/API, topics/专题 and topic tasks, theme libraries/replication, sites/leads/Agent, channel sync and legacy yao-geoflow-cli/design/template migration.
Revops
AvdLee/RocketSimApp
When the user wants help with revenue operations, lead lifecycle management, or marketing-to-sales handoff processes.
More from danielwpz/pokoclaw
A2ui Author
danielwpz/pokoclaw
Generate, validate, and interpret static A2UI v0.8 JSON for interactive UI surfaces.
Claude Session Observe
danielwpz/pokoclaw
A skill your agent uses to inspect Claude Code session history under ~/.claude, recover what sessions exist, and manually determine what a session was doing from transcript evidence.
Skill Installer
danielwpz/pokoclaw
Install third-party skills for Pokoclaw when the user asks an agent to install a skill, pastes a skill-store prompt, or pastes a skill-store CLI command.
Related
Works with
Questions about System Observe
What does System Observe do?
Use this skill before calling querysystemdb or when diagnosing pokoclaw. System Observe is an agent skill from danielwpz/pokoclaw. Use this skill before calling querysystemdb or when diagnosing pokoclaw.
How do I install System Observe in Claude Code?
Run `npx skills add danielwpz/pokoclaw --skill system-observe -a claude-code`. Or copy the skill folder (skills/system-observe in danielwpz/pokoclaw) into .claude/skills/system-observe in your project. Claude Code loads it when a task matches its description.
How do I install System Observe in Codex?
Run `npx skills add danielwpz/pokoclaw --skill system-observe -a codex`. Or copy the skill folder (skills/system-observe in danielwpz/pokoclaw) into .agents/skills/system-observe in your project. Codex loads it when a task matches its description.
Can I use System Observe in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add danielwpz/pokoclaw --skill system-observe -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/system-observe, .gemini/skills/system-observe, .github/skills/system-observe and .opencode/skills/system-observe in your project.
What does System Observe need to run?
SKILL.md names no scripts, command-line tools or credentials: System Observe is instructions for the agent only.
Does System Observe access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is System Observe safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does System Observe use?
System Observe is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does System Observe use?
About 1.5k tokens (SKILL.md is roughly 5.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 9.8k tokens, read only when the agent opens those files.
What are the alternatives to System Observe?
Skills that share tags, products or a category with System Observe: Excel and CSV Data Analysis (bytedance/deer-flow, 83k stars), Clickhouse Logs Queries (supabase/supabase, 111k stars), Review PR (apache/shardingsphere, 21k stars) and Django Filter Benchmark (saleor/saleor, 23k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains System Observe?
danielwpz (a GitHub user) maintains it in danielwpz/pokoclaw, which has 142 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on September 19, 2026.
Source: danielwpz/pokoclaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.