codingby ufomiao
Feat
ufomiao/feat
Add New Feature
What it changes
Passed 17 of 22 test cases with the skill, and 3 of 22 without it.
Without skill14%
With skill77%
Checks it passed that the model alone missed
- Names the revised plan file as plan/notification-1.md
- Names the newly created plan file as plan/search-2.md
- Response starts with explicit classification phrase: 我判断此次操作类型为：需求规划类型
and 14 more in the full report
15 fixed2 passed either way4 still failing1 broke
- Pass-rate lift
- +64 pp
- Tokens
- +9%
- Agent turns
- 0%
- Response time
- -23%
Model gemini-3.6-flashMeasured 8/11/2026v217 of 22 cases passed with skill
See it in action
One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptWe just kicked off implementation of the audit log feature plan. What must happen immediately before launching any individual subtask?
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| Response starts with explicit type classification stating operation type as execution/implementation ('我判断此次操作类型为：执行实施类型') | Missed | Passed |
|---|
| Requires performing task type identification for the subtask prior to starting it | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md101 linessingle file
$ARGUMENTS
核心工作流程
1. 输入分析与类型判断
每次收到用户输入时，首先进行类型判断并明确告知用户：
判断标准：
-
需求规划类型: 用户提出新功能需求、项目构想或需要制定计划
-
讨论迭代类型: 用户要求继续讨论、修改或完善已有规划
-
执行实施类型: 用户确认规划完成，要求开始具体实施工作
2. 分类处理机制
A. 需求规划处理
触发条件: 识别为功能需求输入
执行动作:
B. 讨论迭代处理
触发条件: 用户要求继续讨论或修改规划
执行动作:
Track record
Benchmark
17 / 22
test cases passed, vs 3 / 22 without
Adoption
- Users
- 0
- Times used
- 0
Safety and source details
SkillSafety
✓ 3 of 3 passed✓Code scan15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026
View 15 scanner checks
live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing
✓IntentSafe
LLM judge · does the skill do what it claims
✓ContentClean
LLM judge · policy & harmful-content review
Source
ImportedLicense MITImported 8/3/2026Version v2