agentleFS
Sign inStart free
bostonaholicbostonaholic/skills/skills/engineering/summarizing-friction-logs/SKILL.md

summarizing-friction-logs

Skill2 starsChanged 21 days agoMITView on GitHub

Aggregates frog friction logs across every repository in a workspace plus the global log into one prioritized dashboard. Use when the user says "show the friction dashboard", or when asked for the friction dashboard, all known friction or papercuts across repos, to list friction logs, or to decide which friction to fix first.

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:

    Read-only: Never run frog resolve or frog publish, never edit entries, and never install frog.

    line 13
  2. Distinctive:

    Exit 2: no log could be read. Report each stderr line and stop.

    line 36

≈ “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

Summarizing friction logs

Collect every frog friction entry in a workspace into one read-only dashboard, so known friction can be prioritized in a single view.

Rules

  • Read-only. Never run frog resolve or frog publish, never edit entries, and never install frog.
  • pending matters most. A pending entry is filed nowhere else, so it is invisible outside this dashboard; a linked one already has an issue.

Collect

The workspace is the directory that holds the user's repositories. Resolve <skill-dir> to this skill's absolute directory and run, adding --workspace <dir> when the user names one:

node "<skill-dir>/scripts/collect-friction.mjs" [--workspace <dir>]

It prints JSON with the rendered header, table, and footer, and the gist_slots to fill.

  • Exit 0: build the dashboard below.
  • Exit 1: report stderr and stop. When it says not in a git repository, ask the user once for the workspace and rerun with --workspace. When it says no friction log was found, name the workspace and suggest pointing the skill at the one that holds the logs.
  • Exit 2: no log could be read. Report each stderr line and stop.

Dashboard

One Markdown dashboard, in this order:

  • Header: header, verbatim.
  • Table: table, verbatim.
  • Detail: one entry per gist_slots item, in that order, grouped under a heading per scope. Read the slot's path and distill its body into a one-line gist: what got in the way, plus the suggested fix when it names one. Gists stay with the model because they summarize prose.
  • Footer: footer, verbatim, when non-empty.

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