agentleFS
Sign inStart free
cobusgreylingcobusgreyling/grok-bot-templates/skills/investigate-perf/SKILL.md

investigate-perf

Skill14 starsChanged 3 months agoMITView on GitHub

Paste this into Grok Bot after a successful run: Save the process we just used as a skill called “Investigate Perf”. A useful skill states the six fields from Skills and routines. A named latency, error, or resource hotspot needs an evidence write-up from dashboards, traces, and code — without touching alerts or production. The hotspot has a link or screenshot. Facts and hypotheses are labeled. Alerts and production settings are unchanged. Short write-up: Symptom, Window, Hotspot, Facts, Hypotheses, Next…

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Do not change alerts, feature flags, or production settings.

    line 39

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Investigate Perf

Paste this into Grok Bot after a successful run:

Save the process we just used as a skill called “Investigate Perf”.

A useful skill states the six fields from Skills and routines.

1. When to use it

A named latency, error, or resource hotspot needs an evidence write-up from dashboards, traces, and code — without touching alerts or production.

2. Required inputs and access

  • Symptom and time window (e.g. checkout latency since yesterday's release)
  • Observability dashboards, traces, or flamegraphs the owner can open
  • Source-control links (GitHub) for the suspected change

3. Sequence of work

  1. Restate the symptom and window. List which dashboards and traces you actually opened.
  2. Identify the highest-confidence hotspot with screenshots or direct links.
  3. Separate facts (what the chart shows) from hypotheses (why).
  4. Map to a commit or PR when the connector shows one. Do not change alerts, flags, or production settings.

4. How to validate the result

The hotspot has a link or screenshot. Facts and hypotheses are labeled. Alerts and production settings are unchanged.

5. What to return

Short write-up: Symptom, Window, Hotspot, Facts, Hypotheses, Next check, Action log.

6. What requires approval

Do not change alerts, feature flags, or production settings. Do not page anyone or merge a "fix" PR.

Type / in the composer to reference a saved skill. If it does not appear, open Settings → Plugins → Yours and enable it for this Bot.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free