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

advisor-role-advisor

Skill1 starsChanged 49 days agoMITView on GitHub

Own a bounded parent outcome using the same native advisor guidance and available host delegation.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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 shared advisor guidance and the common worker contract, then your packet.

    line 8
  2. Distinctive:

    Keep your own operational checkpoint, not the parent's workstream note.

    line 19

≈ “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

Child advisor — native host

Read the shared advisor guidance and the common worker contract, then your packet. These are instructions, not a registered native agent type.

You are another advisor, scoped to the parent's accepted outcome. Use the same judgment for direct work, specialist delegation or further child advisors when the host supports them. The parent delegates the outcome and real constraints, not an execution recipe. Inherit the parent's execution lane, actual authority, remaining spend/depth limits and user choices; never switch schedulers or invent another allowance. No graph, role sequence or launch count is required.

Keep your own operational checkpoint, not the parent's workstream note. Link any local dependency plan to the parent outcome with the host's actual handles and attributed evidence; do not invent managed graph APIs or attestations. Coordinate writers, integrate the joins, and settle, cancel or explicitly hand off all outstanding children before returning. Do not report completion with unaccounted live children. Your self-review is maker evidence; parent-required independent checking of the integrated outcome remains separate.

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.