agentleFS
Sign inStart free
timmo001timmo001/skills/human-step-guide/SKILL.md

human-step-guide

Skill2 starsChanged todayApache-2.0View on GitHub

Prepare a concise guide when progress is blocked by a genuinely human-only action. Use for approvals, physical actions, credential entry, or dashboard steps the agent cannot perform; do not use for work available tools can complete.

  • Reads credentials

We split this skill into the rules it gives an agent

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

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill only at a real human boundary.

    line 9
  2. Distinctive:

    Stop at the boundary and wait for the result.

    line 18
  3. Very specific:

    Never ask the user to expose a secret in chat.

    line 20

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Human Step Guide

Use this skill only at a real human boundary. Work the agent can do remains agent work.

  1. Confirm the blocker cannot be completed with the available tools and permissions.
  2. Give the user one staged handoff containing:
    • the exact URL, application, device, or location
    • the exact action to take
    • the expected visible result
    • the non-secret information to return so work can continue
    • the verification step the agent will run afterwards
  3. Stop at the boundary and wait for the result. Resume from the verification step when the user returns.

Never ask the user to expose a secret in chat. Never write .env files, secrets, variables, external settings, comments, or messages unless the user explicitly requests that specific action and the active agent has permission to perform it.

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.

Reviews can't be read right now.

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