agentleFS
Sign inStart free
kvantatechkvantatech/RedLine/.github/skills/perf-run-log/SKILL.md

perf-run-log

Skill1 starsChanged 3 months agoMITView on GitHub

Type: skill (deterministic) · Used by: all workflows / both subagents · Status: STUB (P0 scaffold — not yet implemented)

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When implemented, append numbered milestone log lines (one per milestone, in the rad-log-error shape) to logs/<run-id>.md as a run …

    line 7
  2. Distinctive:

    Every workflow stage and every subagent calls this at its milestones so a run is fully reconstructable from the log alone.

    line 9

≈ “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

perf-run-log

Append numbered milestone log lines per run and write a dated final report.

Type: skill (deterministic) · Used by: all workflows / both subagents · Status: STUB (P0 scaffold — not yet implemented)

Prompt

When implemented, append numbered milestone log lines (one per milestone, in the rad-log-error shape) to logs/<run-id>.md as a run progresses, then write a dated final report to reports/ at completion. Inputs: run-id + a milestone message (or final-report payload) -> Output: the appended log line / the written dated report file. Every workflow stage and every subagent calls this at its milestones so a run is fully reconstructable from the log alone.

Tools

none — deterministic (plain code)

Data

  • Writes: logs/<run-id>.md (numbered milestone lines, append-only)
  • Writes: reports/<dated-report>.md (final report per run)

Notes

Activation: P0. The session-log skill. Hard rules: milestone lines are append-only and numbered in order; log format follows the rad-log-error shape so lines are greppable across runs. Every subagent appends at its milestones — no silent runs.

Frozen skill registry: AGENTS.md in this repo

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