Agent skill

Gather Evidence

by greenfield-inc in greenfield-inc/Pane

A skill your agent uses when handed one factual question about the code or a running system.

Custom licenceAuto-check passed

Install Gather Evidence

skills CLI
$ npx skills add greenfield-inc/Pane --skill gather-evidence -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install greenfield-inc/Pane gather-evidence --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/greenfield-inc/Pane.git skills-src && mkdir -p .claude/skills && cp -r skills-src/main/src/services/paneChatBundle/skills/gather-evidence .claude/skills/gather-evidence && rm -rf skills-src

Use ~/.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/

Facts

Skill name
gather-evidence
GitHub stars
527
Token cost
~372 tokens
SKILL.md length
224 words
Files
1
Skills in repo
35
Repo updated
First seen
Licence
Custom licence

At a glance

A skill your agent uses when handed one factual question about the code or a running system.

  • Works in 5 steps: Restate the question in one line. If it… → Find the likely files with search and… → Trace data flow and control flow only as… → …
  • Handed one factual question about the code
  • SKILL.md covers Method, Rules and Report
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Gather Evidence is an agent skill from greenfield-inc/Pane. Use when handed one factual question about the code or a running system. Returns evidence. Never proposes a fix.

Its SKILL.md is about 370 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Terminal-first, open-source AI agent manager for any CLI agent (agent agnostic), any OS (mac, windows, linux). The Open-Source Agentic Development Environment for running…

When your agent uses it

  • Handed one factual question about the code
  • A running system

Example prompts

  • “/gather-evidence”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Restate the question in one line. If it is really several questions, answer the first and list the rest.
  2. Find the likely files with search and directory listings. Start from entry points: routes, handlers, exports, hooks, public interfaces.
  3. Trace data flow and control flow only as far as the question needs.
  4. For a failure: try to reproduce it. Find the failing test or write down the exact steps. Collect the error, the log lines, and the request…
  5. Read files before making claims. Quote evidence directly.

What it can do on your machine

Read from SKILL.md and the folder at commit 0c471a3. 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

Gather Evidence loads about 372 tokens when it runs. Until then it costs about 32 tokens; SKILL.md has 224 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~32
When it runs · the whole SKILL.md, loaded when a task matches
~372

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 224 words (~372 tokens).

“You answer one question with facts. The agent that asked will do the interpreting.”

— opening of SKILL.md by greenfield-inc, Custom licence
name
gather-evidence

Read the full SKILL.md on GitHub

Files

Just SKILL.md in main/src/services/paneChatBundle/skills/gather-evidence of greenfield-inc/Pane.

Open the folder on GitHubat commit 0c471a3

Compare with similar skills

Gather Evidence 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.

Gather Evidence compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Gather Evidence this skillgreenfield-inc/Pane527—~372Automated safety check: PassCustom licence
Discovery Question Formnexu-io/open-design100k—~1.5kAutomated safety check: PassApache-2.0
Hand Drawn Diagramsnexu-io/open-design100k—~336Automated safety check: PassApache-2.0
Ask User QuestionMemTensor/MemOS12k—~1kAutomated safety check: PassApache-2.0
Five Questionsbrycewang-stanford/Auto-Empirical-Research-Skills4.6k—~1.7kAutomated safety check: NotesCustom licence
Bar Prep Questionsanthropics/claude-for-legal9.6k2 repos~4.9kAutomated safety check: PassApache-2.0

Similar skills

  • Discovery Question Form

    nexu-io/open-design

    Structured clarification form for unresolved material requirements.

    100k GitHub stars~1.5k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Hand Drawn Diagrams

    nexu-io/open-design

    Generate hand-drawn Excalidraw diagrams from a prompt — animated SVG, hosted edit link, and PNG export.

    100k GitHub stars~336 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Ask User Question

    MemTensor/MemOS

    Shows a question as a modal in the interface to clarify a task, collect a preference or get approval, since the user cannot see terminal output.

    12k GitHub stars~1k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed
  • Five Questions

    brycewang-stanford/Auto-Empirical-Research-Skills

    Deeply analyze any empirical economics PDF using the five-question framework (五问框架): research question, identification strategy, core estimand, robustness logic, and scholarly contribution.

    4.6k GitHub stars~1.7k tokensUpdated 5 days ago
    Documents & OfficeAuto-check: notes
  • Bar Prep Questions

    anthropics/claude-for-legal

    Official

    Bar prep questions — MBE or essay, targeted at your weak subjects and bar jurisdiction.

    9.6k GitHub starsUsed in 2 repos~4.9k tokens
    Auto-check passed
  • Question Tuning

    garrytan/gstack

    Shows which questions gstack skills ask you, lets you set per-question preferences and compares your declared style with what your behavior suggests.

    136k GitHub stars~14k tokensUpdated today
    Agent WorkflowsAuto-check: notes

More from greenfield-inc/Pane

All 35 skills in this repo
  • Page

    greenfield-inc/Pane

    House standard for any HTML page written for a person. An agent skill from greenfield-inc/Pane.

    529 GitHub stars~759 tokensUpdated today
    Auto-check passed
  • Session Trace

    greenfield-inc/Pane

    Publish an agent session as a readable trace page in Grain, with the story, key moments, every request and step on a timeline, subagents, and the pull requests it opened.

    529 GitHub stars~836 tokensUpdated today
    Auto-check passed
  • Discussion

    greenfield-inc/Pane

    Have an interactive discussion about a topic, approach, feature, or bug without making code changes.

    529 GitHub stars~666 tokensUpdated today
    Auto-check passed
  • Excalidraw PR Diagrams

    greenfield-inc/Pane

    Create Excalidraw diagram JSON files and PR visual overviews that make visual arguments.

    529 GitHub stars~9.4k tokensUpdated today
    Auto-check passed
  • HTML Explainer

    greenfield-inc/Pane

    The house standard for any skill that renders an HTML page for a person to read, covering design tokens, typography, components, diagrams, and quality gates so every generated page shares one calm…

    529 GitHub stars~1.6k tokensUpdated today
    Auto-check: notes
  • Pane Work

    greenfield-inc/Pane

    Answer questions about the user's own work in Pane, read-only.

    529 GitHub stars~1.8k tokensUpdated today
    Auto-check passed

Questions about Gather Evidence

What does Gather Evidence do?

A skill your agent uses when handed one factual question about the code or a running system. Gather Evidence is an agent skill from greenfield-inc/Pane. Use when handed one factual question about the code or a running system.

When should I use Gather Evidence?

Gather Evidence fits situations like: handed one factual question about the code; A running system.

How do I install Gather Evidence in Claude Code?

Run `npx skills add greenfield-inc/Pane --skill gather-evidence -a claude-code`. Or copy the skill folder (main/src/services/paneChatBundle/skills/gather-evidence in greenfield-inc/Pane) into .claude/skills/gather-evidence in your project. Claude Code loads it when a task matches its description.

How do I install Gather Evidence in Codex?

Run `npx skills add greenfield-inc/Pane --skill gather-evidence -a codex`. Or copy the skill folder (main/src/services/paneChatBundle/skills/gather-evidence in greenfield-inc/Pane) into .agents/skills/gather-evidence in your project. Codex loads it when a task matches its description.

Can I use Gather Evidence 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 greenfield-inc/Pane --skill gather-evidence -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gather-evidence, .gemini/skills/gather-evidence, .github/skills/gather-evidence and .opencode/skills/gather-evidence in your project.

What does Gather Evidence need to run?

SKILL.md names no scripts, command-line tools or credentials: Gather Evidence is instructions for the agent only.

Does Gather Evidence 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 Gather Evidence 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 Gather Evidence use?

Gather Evidence has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Gather Evidence use?

About 372 tokens (SKILL.md is roughly 1.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Gather Evidence?

Skills that share tags, products or a category with Gather Evidence: Discovery Question Form (nexu-io/open-design, 100k stars), Hand Drawn Diagrams (nexu-io/open-design, 100k stars), Ask User Question (MemTensor/MemOS, 12k stars) and Five Questions (brycewang-stanford/Auto-Empirical-Research-Skills, 4.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Gather Evidence?

greenfield-inc (a GitHub organization) maintains it in greenfield-inc/Pane, which has 527 GitHub stars. The repository holds 35 skills in this directory. The repository was last updated on October 10, 2026.

Source: greenfield-inc/Pane on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.