From agy
Internal guidance for composing Agy prompts for coding, review, diagnosis, and research tasks inside the Agy Claude Code plugin
How this skill is triggered — by the user, by Claude, or both
Slash command
/agy:agy-promptingThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill when `agy:agy-rescue` needs to ask Agy for help. Agy runs Claude and Gemini family models in print mode, so the prompt is the entire contract for the run.
Use this skill when agy:agy-rescue needs to ask Agy for help. Agy runs Claude and Gemini family models in print mode, so the prompt is the entire contract for the run.
Prompt Agy like an operator, not a collaborator. Keep prompts compact and block-structured with XML tags. State the task, the output contract, the follow-through defaults, and the small set of extra constraints that matter.
Core rules:
Default prompt recipe:
<task>: the concrete job and the relevant repository or failure context.<structured_output_contract> or <compact_output_contract>: exact shape, ordering, and brevity requirements.<default_follow_through_policy>: what Agy should do by default instead of asking routine questions.<verification_loop> or <completeness_contract>: required for debugging, implementation, or risky fixes.<grounding_rules> or <citation_rules>: required for review, research, or anything that could drift into unsupported claims.When to add blocks:
completeness_contract, verification_loop, and missing_context_gating.grounding_rules, structured_output_contract, and dig_deeper_nudge.research_mode and citation_rules.action_safety so Agy stays narrow and avoids unrelated refactors.How to choose prompt shape:
review or adversarial-review commands when the job is reviewing local git changes. Those prompts already carry the review contract.task when the task is diagnosis, planning, research, or implementation and you need to control the prompt more directly.task --resume-last for follow-up instructions on the same Agy conversation. Send only the delta instruction instead of restating the whole prompt unless the direction changed materially.Model fit (no effort flag — effort tiers are baked into the labels):
pro / pro-high: larger Gemini tier for long-context investigation or multi-file work.sonnet / opus: Claude thinking models for the hardest reasoning, design judgment, or adversarial review.gpt-oss: lightweight alternative for simple mechanical tasks.--model when the user asked for one; otherwise leave it unset.Working rules:
Prompt assembly checklist:
<task>.Reusable blocks live in references/prompt-blocks.md. Concrete end-to-end templates live in references/agy-prompt-recipes.md. Common failure modes to avoid live in references/agy-prompt-antipatterns.md.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub nguyenhieuec/agy-plugin-cc --plugin agy