AD minecraft-mod-search
Search and recommend Minecraft Java Edition mods from multiple platforms (Modrinth, CurseForge). Use when the user describes mod functionality needs, provides a mod name, or asks about Minecraft Java mods, mod packs, or compatible mod recommendations. Also use when the user provides a modpack concept (e.g. "我要做一个科技整合包，1.20.4，forge，包含自动化、能源、物流") and needs AI to analyze requirements, decompose into components, recommend best-fit mods for each, and verify MC version and inter-mod compatibility. Triggers include: "帮我找个XX功能的mod", "搜索XX mod", "我的世界mod推荐", "XX模组兼容吗", "mod依赖", "forge模组", "fabric模组", "1.20.4 mod", "minecraft java mod search", "整合包", "modpack推荐", "科技包", "魔法包", "生存包", "我的世界1.20.4 forge 整合包", "枪械mod", "枪包", "tacz", "枪模组", "手枪", "步枪", "霰弹枪", "狙击枪", "左轮", "火枪", "射击mod", "gun mod", "firearm", "gun pack", "tacz gunpack", "机械动力", "create", "create mod", "create addon", "传送带", "齿轮", "自动化", "流水线", "旋转动力", "蒸汽", "铁路", "机械", "工厂", "conveyor", "gear", "automation", "kinetic", "mechanical".
As a process D 48/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
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: 9. 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 48/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 20 mutating operations with no state check
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 4375 tokens
- 100Steps. 91 steps
- 100Consistency. Name and required fields are in place
- low 13 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)
- +3Description length 999: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -231 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 22 example trigger phrases
- +4Structure: 51 headings
- +3Step-by-step instructions: 91 items
- +4Has examples (16 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.