DigiNomads
Ask the help desk
Sandbox build. This deployment is noindex and takes no payment; the public site is the production build.
Skill pack

Agent ops

Four skills for running agents on real work: a project brief, a workflow audit, a prompt-to-skill conversion and a fallback plan.

Intermediate 4 skills Reviewed 10 November 2026 Markdown mirror
Skill

project-brief

Trigger
When a harness needs project instructions, or the same rules are repeated in every chat
Output
A short AGENTS.md with commands, boundaries, workflow, ask-first rules and a definition of done
Guardrail
Every command is one the user has run; no secret or client name appears in the file.
Skill

workflow-audit

Trigger
Before handing a recurring workflow to an agent
Output
A step map with agent/human ownership, failure modes, reversibility and human checkpoints
Guardrail
No irreversible step is automated without a checkpoint before it.
Skill

prompt-to-skill

Trigger
When the same prompt is pasted more than twice a week
Output
A SKILL.md folder plan with a specific description, procedure, output contract and two pass tests
Guardrail
The description excludes a nearby task; the skill does not trigger for everything.
Skill

fallback-plan

Trigger
When a workflow depends on an API, model, queue or network
Output
Failure classes, detection signals, capped retries, labelled fallbacks and a runbook
Guardrail
Silent wrong output is a failure; a non-idempotent write is never retried without a key.
Install

Put the pack in the project

  1. Create `skills/project-brief/`, `workflow-audit/`, `prompt-to-skill/` and `fallback-plan/` in the repository.

  2. Give each skill a description written as the moment it should fire, not the topic it covers.

  3. Put project-specific commands and paths in `references/`; keep the shared skill vendor-neutral.

  4. Run the tests below against a real repository. If the project brief invents a command, the skill is not being followed.

Folder layout 
skills/my-pack/
|-- SKILL.md
|-- references/
|-- scripts/
`-- assets/
Test

Prove the pack does something

Write the AGENTS.md for this repository. The test command is `npm test` and the generated client is off-limits.

Pass condition: The brief names `npm test`, the generated-client path and the ask-first decisions, and contains no secret.

Should I automate the weekly client report with an agent?

Pass condition: The audit marks drafting vs deciding, puts a checkpoint before sending, and proposes one pilot step with a metric.

Turn this prompt I paste every Monday into a skill.

Pass condition: The output includes a specific description, a SKILL.md body, a guardrail and one test that should not trigger.

Why this pack

Prompts make a single task repeatable. This pack makes the system repeatable: the project rules, the workflow boundaries, the skill that loads without a reminder, and the fallback when a dependency fails.

It is the difference between “the agent worked in that chat” and “a new session can pick up the work tomorrow”.

The rule behind the pack

Write the rule down once, then test it. A project brief, a skill and a fallback plan are all claims about how the work behaves. Each one needs a test that would fail if the claim were false.

Adapting it

  • For a team, review the project brief like code and keep the skills in the repository.
  • For a client repository, add the data-handling section and the approval path for a new dependency.
  • For a solo workflow, keep the pack small: one project brief, one workflow audit, one fallback.

Failure modes

  • The brief is a second README. Cut the description and keep the commands and boundaries.
  • The skill triggers for everything. Rewrite the description as a situation, not a topic.
  • The fallback is untested. Inject the failure in staging before you need the runbook.

Related

Sources

What this pack is based on

Agent Skills specification
Official documentation
Open
Codex CLI documentation
Official documentation
Open
Claude Code documentation
Official documentation
Open
Skills are instructions, not a security boundary. Read a skill before you install it, keep secrets out of the folder, and treat scripts as code you are about to run. The full pack is in the Markdown mirror at /skills/agent-ops.md.

Found a gap in the library?

Send the scenario, the prompt that failed, or the harness change that broke your setup. The help desk takes questions and corrections from humans and agents, and every accepted fix updates the page date.

Ask the help desk Browse the prompt library