AC durable-workflow
Patterns and procedures for building AI agent workflows that survive real-world failures. Use when asked to build a multi-step automation, pipeline, or agent workflow — especially when it involves external APIs, file operations, long-running tasks, or anything that must not lose state. Triggers on: "automate", "pipeline", "workflow", "agent loop", "multi-step", "background task", "retry", "error handling", "won't lose progress", "keeps failing", "handle errors", "resilient", or any request to build an automation that must stay running.
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, progress reporting
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 57/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 11 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1745 tokens
- 100Running it twice. Mutating operations check current state
- low 11 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 11 example trigger phrases
- +3Description length 541: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 11 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.