results-report

80 / 100 · Low risk

Fine to try.

By Galaxy-Dawn/claude-scholar (GitHub) · research · 6,038 stars · scanned at commit d394fb5

This skill should be used when the user asks to "write an experiment report", "summarize experimental results", "do experiment retrospection", "write a results report", "写实验总结报告", "写实验复盘", or mentions turning completed experiment artifacts into a structured, decision-oriented research report. It assumes strict analysis should come from `results-analysis` first.

Works with any agent that supports SKILL.md skills.

What this skill can do

Downloads and installs other software

The author does not mention this.

Found in 1 place.

scripts/lib/package-manager.js, line 27execCmd: 'pnpm dlx',

Runs commands on your computer

The author does not mention this. It runs automatically when the plugin is installed.

Found in 17 places.

scripts/lib/utils.js, line 11const { execSync, spawnSync } = require('child_process');
scripts/lib/utils.js, line 52const result = spawnSync('where', [cmd], { stdio: 'pipe' });
scripts/lib/utils.js, line 56const result = spawnSync('which', [cmd], { stdio: 'pipe' });

Show 14 more

scripts/lib/utils.js, line 72const result = execSync(cmd, {
hooks/hook-common.js, line 10const { execSync } = require('child_process');
hooks/hook-common.js, line 20execSync('git rev-parse --git-dir', {
hooks/hook-common.js, line 28branch = execSync('git branch --show-current', {
hooks/hook-common.js, line 40changes = execSync('git status --porcelain', {
hooks/hook-common.js, line 128return execSync('git rev-parse --show-toplevel', {
hooks/hook-common.js, line 290const unstaged = execSync('git diff --name-status', {
hooks/hook-common.js, line 298const staged = execSync('git diff --cached --name-status', {
hooks/hook-common.js, line 306const untracked = execSync('git status --porcelain', {
hooks/hooks.json, line 10"command": "node \"${CLAUDE_PLUGIN_ROOT}/hooks/security-guard.js\"",
hooks/hooks.json, line 22"command": "node \"${CLAUDE_PLUGIN_ROOT}/hooks/session-summary.js\"",
hooks/hooks.json, line 34"command": "node \"${CLAUDE_PLUGIN_ROOT}/hooks/session-start.js\"",
hooks/hooks.json, line 46"command": "node \"${CLAUDE_PLUGIN_ROOT}/hooks/stop-summary.js\"",
hooks/hooks.json, line 58"command": "node \"${CLAUDE_PLUGIN_ROOT}/hooks/skill-forced-eval.js\"",

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'results-report' ] || [ -L ~/.agents/skills/'results-report' ]; then echo 'A skill folder named results-report already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/Galaxy-Dawn/claude-scholar' "$d" && git -C "$d" checkout --quiet 'd394fb599ed9e6ea2212a9e6daa864345fe97a26' -- 'skills/results-report' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/results-report' ~/.agents/skills/'results-report' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'results-report' ~/.claude/skills/'results-report' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for Galaxy-Dawn/claude-scholar shows the score of its lowest-scoring skill.

SkillTrust badge for Galaxy-Dawn/claude-scholar

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/Galaxy-Dawn/claude-scholar.svg)](https://zalavijaysinh.github.io/skilltrust/repos/Galaxy-Dawn/claude-scholar/)

Score history

Date	Version	Score
2026-11-12	`d394fb5`	80