agentsclimarketplace

Lab report autopilot

Skill Fldicoahkiin/lab-report-autopilot/skills/lab-report-autopilot

Complete Chinese university computing lab, training, coursework, and professional-practice reports from the user's instructions, identity fields, reference reports, and DOCX template. Use when an agent must choose a Windows, Linux, or macOS environment; operate terminals or GUI software; run simple course code; capture actual screenshots or packet files; analyze results; preserve the supplied Word format; and return a checked report for networking, cybersecurity, databases, programming, data visualization, web development, or computer architecture.From its SKILL.md

Install
npx -y skills add Fldicoahkiin/lab-report-autopilot --skill lab-report-autopilot

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 23 days oldThe repository was created 23 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

9.4 KB, ~1.8k tokens by cl100k_base, as published. Nobody here has run it

Lab Report Autopilot

Drive the report from assignment to delivery: inspect the files, choose the environment, run the experiment, capture the useful results, fill the user's template, and inspect the finished DOCX. Once the required files and personal fields are available, continue without asking the user to perform routine steps.

Never invent software output, screenshots, user details, citations, or environment values. Interrupt only when an unavailable environment, missing authorization, or missing required field would make the report false.

Set up

Resolve the directory containing this SKILL.md as SKILL_DIR. Run bundled scripts by absolute path; the current directory may be the user's report folder rather than the skill folder.

Treat the bundled Python scripts as task tools, not as a requirement for the user to repair their global environment. Prefer a Python 3.10 or newer runtime supplied by the host Agent.

On Windows, unless the host Agent provides a known isolated runtime, run the bootstrap before any Python helper:

$runtime = & powershell.exe -NoProfile -ExecutionPolicy Bypass `
  -File "$SKILL_DIR\scripts\bootstrap_windows.ps1" `
  -Workspace "work\report-name" | ConvertFrom-Json
$PYTHON = $runtime.python

The bootstrap tests py, python, and python3, creates a task-local virtual environment, and installs the bundled requirements there. If no usable interpreter exists, it downloads a checksum-pinned CPython installer from python.org and installs it under the report workspace without administrator rights, PATH changes, file associations, shortcuts, or global pip.

On Linux or macOS, resolve a working Python 3.10 or newer from the host Agent or the current system, create a task-local virtual environment, and install requirements.txt into that environment. Do not install packages into an unrelated global Python.

If no report workspace exists:

"$PYTHON" "$SKILL_DIR/scripts/init_report.py" work/report-name \
  --kind lab \
  --discipline packet-analysis \
  --title "ARP 协议抓包与字段分析"

Use --kind practice for professional practice. A supplied DOCX remains the report template; do not replace it with the generic Markdown draft.

Read the material

Classify each input before writing:

  • Template: controls sections, fields, page layout, and visual style.
  • Good reference: shows useful step length, wording, or screenshot placement.
  • Counterexample: shows problems to avoid.
  • Task material: supplies the required data, code, topology, and expected result.
  • Private material: follows the user's handling instructions and supplies only authorized facts. Read user-data-and-privacy.md.

Learn the pattern, not another person's identity or results. Do not copy names, screenshots, addresses, private records, or first-person claims.

Read disciplines.md, then load the one matching discipline file. Load a second only when the assignment actually crosses subjects.

Decide what must be delivered

Record:

  • required sections and grading prompts;
  • fields the user has supplied;
  • software, operating system, data, topology, and expected output;
  • the visible result needed for each submitted claim;
  • length, date, filename, and file-format rules.

Fill names, student numbers, class, teacher, organization, role, dates, and other fields only from values the user supplies or confirms. Use the same value everywhere it appears. Ask once for missing fields that the template requires. Leave signatures, scores, and approval fields empty unless the user explicitly provides them. Do not reuse a filename pattern from an unrelated report.

Before editing Word, read docx-qa.md and complete the workspace's format-contract.md. Read requirements from ordinary paragraphs, table cells, headers, footers, text boxes, content controls, comments, and colored instruction text. Record every stated minimum word count, screenshot count, naming rule, field rule, and formatting rule with its source location.

Measure the supplied template: paper size, margins, sections, tables, fonts, sizes, line spacing, indents, image widths, captions, headers, footers, and page numbering. Record the source file hash. Do not begin assembly until the explicit requirements and measured values are in the contract.

Choose the environment

Read environment-playbook.md, then inspect the current machine:

"$PYTHON" "$SKILL_DIR/scripts/probe_environment.py" --json

Do not assume the author's computer or virtualization product. Follow the operating system and software named by the assignment. For common Chinese university coursework, treat Windows as the main route for Office, PowerShell, SQL Server, eNSP, vendor simulators, and Windows-only teaching software. Use Linux or Kali for Linux networking and security tools. Use macOS natively only when the named software and required screenshots remain equivalent; otherwise use any available Windows or Linux VM, container, WSL, or authorized remote lab.

Keep permission fixes and failed attempts in working notes unless they change the submitted result. Security work must stay inside local labs, course systems, deliberately vulnerable targets, or other authorized systems.

Run and capture

Read evidence-and-screenshots.md and the selected discipline file.

  1. Build the smallest setup that satisfies the task.
  2. Run every command and code path that will appear in the report.
  3. After a meaningful GUI action, inspect the fresh application state.
  4. Record the exact inputs, filenames, versions, addresses, frame numbers, and observed values.
  5. Capture the screen that shows the result; do not capture every click.
  6. Keep original screenshots, packet files, data, and source code unchanged.

Generated diagrams may explain a concept but may not stand in for a real software result. Screenshots used in one report must agree on filenames, addresses, ports, values, and environment.

Check the image folder before drafting:

"$PYTHON" "$SKILL_DIR/scripts/evidence_manifest.py" path/to/evidence \
  --output evidence-manifest.json

Fix corrupt files, accidental duplicates, unreadable captures, exposed private data, and missing result screens.

Write from the observed result

Read writing-and-code.md.

For each practical step, state the operation, the value or behavior observed, the nearby screenshot, and a short explanation only when it helps. Keep theory and summaries proportional to the examples and the assignment.

For professional practice, write it as assigned work: what was received, what was checked or operated, how the judgment was made, and what result was recorded. Do not add presentation notes about screenshot counts, report structure, retained artifacts, or what the report chooses not to introduce. Do not add a company homepage merely to fill a source line.

For code, implement only the requested behavior. Do not add unused abstractions, speculative options, impossible-case checks, or comments that restate simple code.

Build and check the DOCX

Use the host agent's document tools when available; otherwise use compatible DOCX tooling and a real renderer. Fill the supplied template in place. Preserve the template paragraph and cell properties while replacing text; rebuilding a cell from plain text may silently remove font hints, line spacing, indents, or pagination settings. Do not reduce a required font size merely to force a long field onto one line. Remove sample text only where the report content replaces it.

Before visual review, compare the finished DOCX with format-contract.md and record the measured result for every rule. Count required section lengths from the finished document, not from the draft. Check package structure, sections, margins, table geometry, merged cells, fonts, sizes, line spacing, indents, fields, image count, and source-template hash.

Render the latest DOCX and inspect every page at 100%:

  • screenshots and captions are readable and aligned;
  • text, tables, and images do not clip or overlap;
  • Chinese and Latin glyphs render correctly;
  • headings, numbering, spacing, indents, margins, headers, and footers match the template;
  • names, dates, commands, addresses, frame numbers, figures, and conclusions agree;
  • no extra blank page or nearly empty carried-over page remains;
  • the filename follows this assignment's rule;
  • no credentials, private workplace data, or unrelated personal information remain.

When the template targets Microsoft Word and Word is available, open the final DOCX in Word and confirm the page count and first/last pages after the renderer check. Repeat both the structural checks and the render after every layout change. Deliver only the requested files unless the user asks for working material.

What ships with it: 23 files

58.6 KB alongside SKILL.md, 4 of them executable

agents/

Keep looking

Skills are one crate of 326,144. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.