Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →shinpr/recipe-task
Execute tasks following appropriate rules with rule-advisor metacognition
Passed 2 of 9 test cases with the skill, and 2 of 9 without it.
and 4 more in the full report
4 fixed1 passed either way12 still failing5 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
Instead of using standard Jira tickets or a plain bulleted Markdown list, we want to initialize our development tasks. What specific task structure tool and initial boundary task should be registered first?
| Checked | Without skill | With skill |
|---|---|---|
| Uses TaskCreate as the tool to register tasks | Missed | Passed |
| Designates rule selection and mapping as the first item in the task list | Missed | Passed |
| Designates rule verification and completion reporting as the final item in the task list | Missed | Passed |
The instructions your model reads when the skill loads.
Execute Skill: llm-friendly-context before writing Agent prompts, handoffs, or generated artifacts. Execute Skill: subagents-orchestration-guide before making workflow decisions, invoking agents, or resolving findings.
Task: $ARGUMENTS
Step 1: Rule Selection via rule-advisor (REQUIRED)
Invoke rule-advisor using Agent tool:
subagent_type: "dev-workflows-fullstack:rule-advisor"description: "Rule selection"prompt: "Task: $ARGUMENTS. Select appropriate rules and perform metacognitive analysis."Step 2: Utilize rule-advisor Output
After receiving rule-advisor's JSON response, proceed with:
Understand Task Essence (from taskAnalysis.essence)
Follow Selected Rules (from selectedRules)
skill name and read it completelyRecognize Past Failures (from metaCognitiveGuidance.pastFailures)
Execute First Action (from metaCognitiveGuidance.firstStep)
Step 3: Create Task List with TaskCreate
Register work steps using TaskCreate. Use "Select and map applicable rules" as the first task and "Verify selected rules and report completion" as the final task.
test cases passed, vs 2 / 9 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.