Data Table Manager
n8n-io/n8n
Load before calling data-tables or parse-file. An agent skill from n8n-io/n8n.
Create and revise field-survey plans from supplied GeoJSON boundaries, exclusions, camera geometry and capture requirements.
Install Pilot
$ npx skills add autonomous-ai/openharness --skill pilot -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install autonomous-ai/openharness pilot --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/autonomous-ai/openharness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/store/agents/drone-pilot/skills/pilot .claude/skills/pilot && 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 "pilot" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/drone-pilot/skills/pilot into .claude/skills/pilot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pilot", 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/autonomous-ai/openharness/tree/main/store/agents/drone-pilot/skills/pilotType 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 autonomous-ai/openharness --skill pilot -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install autonomous-ai/openharness pilot --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .agents/skills && cp -r skills-src/store/agents/drone-pilot/skills/pilot .agents/skills/pilot && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "pilot" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/drone-pilot/skills/pilot into .agents/skills/pilot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pilot", 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 autonomous-ai/openharness --skill pilot -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install autonomous-ai/openharness pilot --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/store/agents/drone-pilot/skills/pilot .cursor/skills/pilot && 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 "pilot" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/drone-pilot/skills/pilot into .cursor/skills/pilot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pilot", 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/autonomous-ai/openharness.git --path store/agents/drone-pilot/skills/pilot--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 autonomous-ai/openharness --skill pilot -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install autonomous-ai/openharness pilot --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/store/agents/drone-pilot/skills/pilot .gemini/skills/pilot && 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 "pilot" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/drone-pilot/skills/pilot into .gemini/skills/pilot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pilot", 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 autonomous-ai/openharness pilotInstalls 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 autonomous-ai/openharness --skill pilot -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .github/skills && cp -r skills-src/store/agents/drone-pilot/skills/pilot .github/skills/pilot && 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 "pilot" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/drone-pilot/skills/pilot into .github/skills/pilot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pilot", 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 autonomous-ai/openharness --skill pilot -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install autonomous-ai/openharness pilot --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/store/agents/drone-pilot/skills/pilot .opencode/skills/pilot && 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 "pilot" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/drone-pilot/skills/pilot into .opencode/skills/pilot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pilot", 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
pilot- GitHub stars
- 1.1k
- Token cost
- ~1.3k tokens
- SKILL.md length
- 651 words
- Files
- 3 (incl. scripts, references)
- Skills in repo
- 100
- Repo updated
- First seen
- Licence
- MIT
At a glance
Create and revise field-survey plans from supplied GeoJSON boundaries, exclusions, camera geometry and capture requirements.
- Works in 5 steps: Read flight/project.json and… → Author named boundary/exclusion layers… → Run node tools/build.mjs. DRONE_DSH_DIR… → …
- Tasks that involve CSV and tabular files
- SKILL.md covers Author and revise, Inspect recorded evidence and Deliver and verify
- Runs Shell scripts from its folder; calls node
What it does
Pilot is an agent skill from autonomous-ai/openharness. Create and revise field-survey plans from supplied GeoJSON boundaries, exclusions, camera geometry and capture requirements. Use Drone Pilot for editable routes and sorties, recorded-flight CSV analysis, and portable GIS, CSV and report delivery.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts and reference files (for example `references/project.md` and `scripts/seed-verdict.sh`).
It sits in Documents & Office, covering CSV and tabular files. The repository describes itself as: The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and build across… The licence is MIT.
When your agent uses it
- Tasks that involve CSV and tabular files
Example prompts
- “/pilot”
Requirements
- A Bash shell
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Read flight/project.json and flight/DESIGN.md. Distinguish supplied measurements, user
- Author named boundary/exclusion layers and takeoff in local east/north meters. Keep the WGS 84
- Run node tools/build.mjs. DRONE_DSH_DIR resolves tools for materialized workspaces. The HTML
- Resolve infeasibility explicitly: cadence, narrow geometry, disconnected paths or an inadequate
- Compare directions with the UI when useful. It samples 12 angles in 15-degree steps plus the
What it can do on your machine
Read from SKILL.md and the folder at commit 50da5db. 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
Ships 1 file in scripts/ (Shell), which the agent can run.
Shell commands in SKILL.md call:
node
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
Pilot loads about 1.3k tokens when it runs, and up to ~2.2k if it reads all its reference files. Until then it costs about 63 tokens; SKILL.md has 651 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); the scripts in this folder are not scanned.
SKILL.md
The full file from autonomous-ai/openharness at commit 50da5db, republished under its MIT licence (© autonomous-ai). 651 words, ~1,269 tokens.
Download SKILL.mdSave it as
.claude/skills/pilot/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- pilot
- description
- Create and revise field-survey plans from supplied GeoJSON boundaries, exclusions, camera geometry and capture requirements. Use Drone Pilot for editable routes and sorties, recorded-flight CSV analysis, and portable GIS, CSV and report delivery.
From a site to a field kit
Read the project contract. Start with what the person needs to document and the measurements they can supply. Translate ground-sampling or overlap requirements into camera geometry. Preserve their boundary and approved exclusions. Explain missing inputs in plain language; do not fabricate a georeferenced site, aircraft specifications or flight records.
Author and revise
- Read
flight/project.jsonandflight/DESIGN.md. Distinguish supplied measurements, user decisions and explicit draft assumptions. The agent can create original polygon geometry; the starter orchard is only an example. Importing a GeoJSON file can replace or extend a site. - Author named boundary/exclusion layers and takeoff in local east/north meters. Keep the WGS 84 origin and locked geometry stable during targeted edits. Camera sensor width is across a run; sensor height is along it. Line angles are counterclockwise from east.
- Run
node tools/build.mjs.DRONE_DSH_DIRresolves tools for materialized workspaces. The HTML embeds its runtime; no CDN, map key or cloud service is needed to use or share the planner. - Resolve infeasibility explicitly: cadence, narrow geometry, disconnected paths or an inadequate return budget. Do not silently relax requested height, speed, overlap, margin or reserve.
- Compare directions with the UI when useful. It samples 12 angles in 15-degree steps plus the current direction and reports time and coverage. This is not a global route optimization. Photo footprints and source paths are inspectable. Never imply that a straight geometric segment models the aircraft's turn radius, acceleration or navigation error.
The UI supports named area edits, direct vertex dragging, new polygons, precise coordinate edits,
geometry locks, moving takeoff, camera/cadence settings, undo/redo and a take-home project file.
Workspace saves keep prior source in .harness/history/. Source changes arriving while the user
has a draft offer both versions. Do not overwrite either without an explicit save/restore choice.
Offline HTML has the same model and browser file import/export; native path opening uses only the
local viewer's explicit home-folder project picker.
Show full SKILL.md (328 more words)Show less
Inspect recorded evidence
Import a CSV with explicit latitude/longitude and time columns. Select elapsed seconds, milliseconds, or ISO 8601 timestamps with timezone. Altitude requires meters/feet and takeoff/AMSL reference; AMSL requires supplied takeoff elevation. Heading is degrees clockwise from north. Battery is a percentage. Events use 1/0, true/false or yes/no, with blank meaning unknown.
The retained original CSV and SHA-256 establish provenance. Row numbers and missing-coordinate breaks remain in the normalized records. Time gaps above the selected continuity threshold are not connected. Compare nearest-route distances with all planned routes or one sortie, inspect individual records and report samples/segments outside the inset region.
Footprint estimates need an event flag, positive height and heading, plus the current camera and level-ground/nadir assumptions. Do not infer events from ordinary telemetry, fill unknown fields, call nominal footprints observed images or claim an orthomosaic/photogrammetric reconstruction. The model does not process photographs. Reimport the original source to revise its mapping.
Deliver and verify
Run node tools/check.mjs for source, geometry and budget checks, then node tools/export.mjs:
.vector.json: editable boundaries, settings, camera and retained flight source, if supplied.planner.html: one offline file with editing and all required runtime/license text embedded.survey.geojson: source polygons, inset region, routes, planned captures, footprint estimates and gaps. Recorded paths/estimated event coverage are separate named features when present.overlay.kml: map overlay with ground-clamped site and routes; not an altitude or mission file.planned-photos.csv/planned-route.csv: explicit coordinates, height above takeoff and nominal times. CSV values are review data, not commands or tested autopilot configuration.site-map.svg,report.htmlandreport.json: portable map and calculations; print HTML to PDF.- Original and normalized recorded CSV when supplied, full dependency licenses, README and ZIP.
Browser exports use the current draft. Reopen GIS/CSV/HTML with an independent reader and review scale, coordinate order, dates, gaps and source retention. Test the actual viewer edits and an offline reopen. Record exact commands and outcomes. Unit/schema checks do not establish native GIS or ground-station imports, a completed real flight, a customer's success or visual quality.
© autonomous-ai, MIT. 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 2 other files (scripts, references) in store/agents/drone-pilot/skills/pilot of autonomous-ai/openharness.
- SKILL.md
- references/project.md
- scripts/seed-verdict.sh
Open the folder on GitHubat commit 50da5db
Compare with similar skills
Pilot 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 |
|---|---|---|---|---|---|---|
| Pilot this skillautonomous-ai/openharness | 1.1k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Data Table Managern8n-io/n8n | 207k | — | ~2.3k | Automated safety check: Pass | Custom licence | |
| Instrument Data To Allotropeaws-samples/amazon-bedrock-agents-healthcare-lifesciences | 274 | 2 repos | ~2.7k | Automated safety check: Pass | Apache-2.0 | |
| Abuse Hunternexu-io/harness-engineering-guide | 663 | — | ~1.9k | Automated safety check: Pass | MIT | |
| Markitshift-labs-ai/markit | 1.3k | — | ~299 | Automated safety check: Pass | MIT | |
| Sector Analysttradermonty/claude-trading-skills | 3k | 1 repos | ~2.3k | Automated safety check: Pass | MIT |
Similar skills
- Official
- Official
Instrument Data To Allotrope
aws-samples/amazon-bedrock-agents-healthcare-lifesciences
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV.
Abuse Hunter
nexu-io/harness-engineering-guide
Detect and investigate bulk registration abuse on SaaS platforms.
Markit
shift-labs-ai/markit
Convert files and URLs to Markdown. An agent skill from shift-labs-ai/markit.
Sector Analyst
tradermonty/claude-trading-skills
This skill should be used when analyzing sector rotation patterns and market cycle positioning.
Uap Release Analyzer
ckpxgfnksd-max/uap-release-analyzer
Inventory, extract, and analyze tranches of declassified UAP/UFO files — including war.gov/UFO/ "PURSUE" releases, FBI Vault, NARA boxes, and AARO publications.
More from autonomous-ai/openharness
All 100 skills in this repoG-code Slicer Tool
autonomous-ai/openharness
Slices 3D mesh files into printer-profiled plain G-code through real slicer CLIs, with backend discovery, input inspection, dry runs and static validation.
Home Assistant Automation Builder
autonomous-ai/openharness
Turns a home-automation request into standard, testable automations.yaml, run against Home Assistant Core's real triggers and verified with its own trace tool.
Score Music Composer
autonomous-ai/openharness
Turns a musical brief into LilyPond concert-pitch music, checked parts for each instrument and a playable practice pack.
OrcaSlicer 3MF and G-code Workflow
autonomous-ai/openharness
Turns an STL and explicit printer and material requirements into compared OrcaSlicer plans, an editable 3MF project, checked G-code and a portable handoff.
Sheets and Docs Report Builder
autonomous-ai/openharness
Builds an editable DOCX report, a formula-driven XLSX workbook and a fresh LibreOffice PDF preview from one structured source file, then checks them together.
Bambu Labs
autonomous-ai/openharness
Dry-run, upload, and cautiously initiate local Bambu Lab print jobs from validated plain .gcode, using Bambu LAN FTPS/MQTT handoffs.
Related
Categories
Questions about Pilot
What does Pilot do?
Create and revise field-survey plans from supplied GeoJSON boundaries, exclusions, camera geometry and capture requirements. Pilot is an agent skill from autonomous-ai/openharness. Create and revise field-survey plans from supplied GeoJSON boundaries, exclusions, camera geometry and capture requirements.
When should I use Pilot?
Pilot fits situations like: tasks that involve CSV and tabular files.
How do I install Pilot in Claude Code?
Run `npx skills add autonomous-ai/openharness --skill pilot -a claude-code`. Or copy the skill folder (store/agents/drone-pilot/skills/pilot in autonomous-ai/openharness) into .claude/skills/pilot in your project. Claude Code loads it when a task matches its description.
How do I install Pilot in Codex?
Run `npx skills add autonomous-ai/openharness --skill pilot -a codex`. Or copy the skill folder (store/agents/drone-pilot/skills/pilot in autonomous-ai/openharness) into .agents/skills/pilot in your project. Codex loads it when a task matches its description.
Can I use Pilot 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 autonomous-ai/openharness --skill pilot -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pilot, .gemini/skills/pilot, .github/skills/pilot and .opencode/skills/pilot in your project.
What does Pilot need to run?
Going by SKILL.md and its folder, Pilot needs a shell for the scripts in its folder and the command-line tools its instructions call (node). Our summary lists: A Bash shell.
Does Pilot 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 Pilot 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Pilot use?
Pilot is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Pilot use?
About 1.3k tokens (SKILL.md is roughly 5.1k 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 927 tokens, read only when the agent opens those files.
What are the alternatives to Pilot?
Skills that share tags, products or a category with Pilot: Data Table Manager (n8n-io/n8n, 207k stars), Instrument Data To Allotrope (aws-samples/amazon-bedrock-agents-healthcare-lifesciences, 274 stars), Abuse Hunter (nexu-io/harness-engineering-guide, 663 stars) and Markit (shift-labs-ai/markit, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Pilot?
autonomous-ai (a GitHub organization) maintains it in autonomous-ai/openharness, which has 1,149 GitHub stars. The repository holds 100 skills in this directory. The repository was last updated on October 8, 2026.
Source: autonomous-ai/openharness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.