← All skills
benchmark
89 / 100 · Low risk
Fine to try. Some of what it can do is expected: a coding skill usually runs build and test commands.
By charlieviettq/awesome-agent-skill (GitHub) · coding · 27 stars · scanned at commit c567ae4
Performance regression detection using the browse daemon. (gstack).
Works with any agent that supports SKILL.md skills.
What this skill can do
Runs commands on your computer
This is disclosed by the author in the skill's SKILL.md or README. Expected for a coding skill.
Found in 21 places.
Show 17 more
- .claude/skills/gstack-benchmark/SKILL.md, line 213
touch ~/.gstack/.telemetry-prompted - .claude/skills/gstack-benchmark/SKILL.md, line 231
touch ~/.gstack/.proactive-prompted - .claude/skills/gstack-benchmark/SKILL.md, line 240
~/.claude/skills/gstack/bin/gstack-telemetry-log --event-type first_task_scaffold_shown --skill "TASK_TOKEN" --outcome shown 2>/dev/null || true - .claude/skills/gstack-benchmark/SKILL.md, line 315
eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true - .claude/skills/gstack-benchmark/SKILL.md, line 331
_GSTACK_HOME="${GSTACK_HOME:-$HOME/.gstack}" - .claude/skills/gstack-benchmark/SKILL.md, line 440
"$_BRAIN_CONFIG_BIN" set artifacts_sync_mode <choice> - .claude/skills/gstack-benchmark/SKILL.md, line 449
"~/.claude/skills/gstack/bin/gstack-brain-sync" --discover-new 2>/dev/null || true - .claude/skills/gstack-benchmark/SKILL.md, line 495
~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":" - .claude/skills/gstack-benchmark/SKILL.md, line 510
_TEL_END=$(date +%s) - .claude/skills/gstack-benchmark/SKILL.md, line 536
_ROOT=$(git rev-parse --show-toplevel 2>/dev/null) - .claude/skills/gstack-benchmark/SKILL.md, line 552
if ! command -v bun >/dev/null 2>&1; then - .claude/skills/gstack-benchmark/SKILL.md, line 591
eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null || echo "SLUG=unknown")" - .claude/skills/gstack-benchmark/SKILL.md, line 602
git diff $(gh pr view --json baseRefName -q .baseRefName 2>/dev/null || gh repo view --json defaultBranchRef -q .defaultBranchRef.name 2>/dev/null || echo main) - .claude/skills/gstack-benchmark/SKILL.md, line 610
$B goto <page-url> - .claude/skills/gstack-benchmark/SKILL.md, line 617
$B eval "JSON.stringify(performance.getEntriesByType('navigation')[0])" - .claude/skills/gstack-benchmark/SKILL.md, line 630
$B eval "JSON.stringify(performance.getEntriesByType('resource').map(r => ({name: r.name.split('/').pop().split('?')[0], type: r.initiatorType, size: r.transfer - .claude/skills/gstack-benchmark/SKILL.md, line 635
$B eval "JSON.stringify(performance.getEntriesByType('resource').filter(r => r.initiatorType === 'script').map(r => ({name: r.name.split('/').pop().split('?')[0
and 1 more places
Changes files outside its own folder
This is disclosed by the author in the skill's SKILL.md or README.
Found in 15 places.
Show 12 more
- .claude/skills/gstack-benchmark/SKILL.md, line 82
echo '{"skill":"benchmark","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(_repo=$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null | tr - - .claude/skills/gstack-benchmark/SKILL.md, line 175
rm -f ~/.gstack/.writing-style-prompt-pending - .claude/skills/gstack-benchmark/SKILL.md, line 176
touch ~/.gstack/.writing-style-prompted - .claude/skills/gstack-benchmark/SKILL.md, line 185
touch ~/.gstack/.completeness-intro-seen - .claude/skills/gstack-benchmark/SKILL.md, line 213
touch ~/.gstack/.telemetry-prompted - .claude/skills/gstack-benchmark/SKILL.md, line 231
touch ~/.gstack/.proactive-prompted - .claude/skills/gstack-benchmark/SKILL.md, line 241
touch ~/.gstack/.activated 2>/dev/null || true - .claude/skills/gstack-benchmark/SKILL.md, line 244
If `ACTIVATED` is `no` but `FIRST_TASK:` is empty or `nongit` (headless, non-git, or nothing actionable): show nothing, just run `touch ~/.gstack/.activated 2>/ - .claude/skills/gstack-benchmark/SKILL.md, line 250
Then run `touch ~/.gstack/.first-loop-tip-shown 2>/dev/null || true`. - .claude/skills/gstack-benchmark/SKILL.md, line 316
touch ~/.gstack/.vendoring-warned-${SLUG:-unknown} - .claude/skills/gstack-benchmark/SKILL.md, line 512
rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true - .claude/skills/gstack-benchmark/SKILL.md, line 517
echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%
Sends data to these websites: bun.sh
This is disclosed by the author in the skill's SKILL.md or README.
Found in 1 place.
Other copies in this repository
charlieviettq/awesome-agent-skill has 1 more folder with a skill named benchmark. This page shows the lowest-scoring copy.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'benchmark' ] || [ -L ~/.agents/skills/'benchmark' ]; then echo 'A skill folder named benchmark already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/charlieviettq/awesome-agent-skill' "$d" && git -C "$d" checkout --quiet 'c567ae426d55fa498e919fc0f5a37c582d5c7a2c' -- '.claude/skills/gstack-benchmark' && mkdir -p ~/.agents/skills && cp -R "$d"/'.claude/skills/gstack-benchmark' ~/.agents/skills/'benchmark' && 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/'benchmark' ~/.claude/skills/'benchmark' (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 charlieviettq/awesome-agent-skill shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/charlieviettq/awesome-agent-skill/)
Score history
| Date | Version | Score |
|---|
| 2026-11-07 | c567ae4 | 89 |