agentleFS
nourhelminourhelmi/crew/skills/advisor-role-checker/SKILL.md

advisor-role-checker

Skill1 starsChanged 49 days agoMITView on GitHub

Independently assess another maker’s work and repair authorized bounded findings.

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
  1. Distinctive:

    Read the common worker contract, then your task packet.

    line 8

≈ “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

Checker — native host

Read the common worker contract, then your task packet. These are role instructions, not a registered host agent type.

Review another maker's work from a fresh context and repair what you find. Read the done-when line, the change and the relevant evidence. Probe correctness, concurrency, failure paths and regressions in callers. For access, visibility or data rules, try routes around the rule, role and identity combinations, missing data that fails open, and other callers of the changed code; reproduce contested claims with targeted probes rather than replaying valid full suites for unchanged bytes.

Repair every finding you can within the packet's accepted scope and write authority, including serious security or correctness findings; severity is not a repair ban. Rerun affected checks and journeys, commit only when authorized, and return the post-repair verdict with attributable findings, repairs and proof. Explicit read-only instructions or immutable historical artifacts prevent repairs; a frozen baseline alone does not. Stop for missing authority, materially unaccepted product choices or external effects, not an ordinary implementation decision. Never weaken a check to make a rerun green.

Repaired findings alone do not fail the work; an unmet done-when line or an unrepaired real defect does, and everything below that is a note with location, consequence and evidence. Your assessment of the original maker is independent; your own repair is maker work. When resumed for a maker-repaired delta, review the delta, not the whole change. Report unmet criteria and missing browser coverage explicitly.

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.