AIDocxWorkFlow: Skill for Claude Code

.cursor/skills/aidocx-feedback-logger/SKILL.md

aidocx-feedback-logger is a skill for Claude Code, Cursor from SilenceInsect/AIDocxWorkFlow. It costs 69 tokens per session (1,953 once invoked), scanned A, original, MIT.

A tool for importing test-execution feedback and review results from Excel, CSV, or JSON files, standardizing the data, and saving it in a feedback-logs folder. Test-execution feedback records what happened when test cases were run.

In plain words
What is it for?
Use it to import feedback from Excel workbooks, including test-case tracking sheets, and optionally import a separate review file. It can be run from Python or the command line.
Why use it?
It removes the need to manually copy results between files or standardize different column names. It can also combine duplicate feedback according to a chosen rule.

Skill for Claude CodeCursor

Written for Claude Code and Cursor: disable-model-invocation in frontmatter, but also installed under .cursor/. Also seen: mentions Claude Code; mentions Codex; mentions Cursor.

This is SilenceInsect/AIDocxWorkFlow's own configuration. It tells Claude Code and Cursor how to work on AIDocxWorkFlow itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything AIDocxWorkFlow configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/gleon/Documents/TestDev/AIDocxWorkFlow.

Reuse

Borrowing it

Nothing to install: this file belongs to SilenceInsect/AIDocxWorkFlow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/SilenceInsect/AIDocxWorkFlow/main/.cursor/skills/aidocx-feedback-logger/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/SilenceInsect/AIDocxWorkFlow

Made for: Claude Code, Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for aidocx-feedback-logger

README.md
[![agentmods](https://agentmods.dev/badge/skills/silenceinsect/aidocxworkflow/aidocx-feedback-logger.svg)](https://agentmods.dev/skills/silenceinsect/aidocxworkflow/aidocx-feedback-logger)
Your own site
<a href="https://agentmods.dev/skills/silenceinsect/aidocxworkflow/aidocx-feedback-logger"><img src="https://agentmods.dev/badge/skills/silenceinsect/aidocxworkflow/aidocx-feedback-logger.svg" alt="Measured on agentmods" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,953 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00069 $0.01953
Opus 5 $0.00034 $0.00977
Sonnet 5 $0.00014 $0.00391
Haiku 4.5 $0.00007 $0.00195

Measured 8d ago against content hash 9a88518fd237, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

aidocx-feedback-logger scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/skills/aidocx-feedback-logger/SKILL.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AIDocxWorkFlow — 反馈收集与导入 Skill

功能概述

feedback_logger 模块支持从多种来源导入反馈,自动识别 Excel sheet 列名,标准化后保存。

核心函数

import_feedback() — 通用导入

from ai_workflow.feedback_logger import import_feedback

result = import_feedback(
    feedback_file="/path/to/feedback.xlsx",
    review_file="/path/to/review.xlsx",   # 可选
    output_dir="/path/to/feedback_logs/",
    version="v1.0",
    req_name="游戏道具商城系统",
    merge_duplicates="latest",            # "latest" | "first" | "all"
)

import_from_test_cases_xlsx() — 从 test_cases.xlsx 导入

from ai_workflow.feedback_logger import import_from_test_cases_xlsx

# 自动读「反馈结果」或「执行追踪」sheet
result = import_from_test_cases_xlsx(
    xlsx_path="/path/to/test_cases.xlsx",
    version="v1.0",
)

CLI 用法

# 从 Excel 导入(自动探测反馈结果 sheet)
python3 -m ai_workflow.feedback_logger --file feedback.xlsx

# 从 test_cases.xlsx 读执行追踪 sheet
python3 -m ai_workflow.feedback_logger --file test_cases.xlsx

# 同时提供反馈和审查结果
python3 -m ai_workflow.feedback_logger \
    --file feedback.xlsx \
    --review review.xlsx \
    --version v1.0

支持的文件格式

Excel 文件

自动探测以下 sheet,按优先级依次查找:

反馈 sheet(import_feedback):

  1. 反馈结果
  2. 执行追踪
  3. 执行记录
  4. 用例详情

审查 sheet(import_feedback --review):

  1. 审核结果
  2. 审查结果
  3. review

test_cases.xlsx 专属 sheet(import_from_test_cases_xlsx):

  1. 反馈结果
  2. 执行追踪test_cases.xlsx 的这个 sheet 就是反馈数据
  3. 执行记录

CSV 文件

自动识别 GBK/UTF-8 编码,首行作为列头。

JSON 文件

支持三种格式:

// 格式 1: 顶层数组
[{"case_id": "UI-TC-001", "result": "PASS", ...}]

// 格式 2: 对象含 entries 字段
{"entries": [{"case_id": "...", ...}]}

// 格式 3: 单条记录
{"case_id": "UI-TC-001", "result": "PASS", ...}

自动列名映射

模块自动将各种中文/英文列名映射到标准字段:

标准字段 支持的中文列名 支持的英文列名
case_id 用例ID, 用例编号, 测试用例ID case_id, test_case_id
result 执行结果, 测试结果, 执行状态 result, test_result, status
actual_result 实际结果, 实际输出, 观测结果 actual_result, actual_output
defect_desc 缺陷描述, 问题描述, 缺陷说明 defect_desc, bug_description, issue
severity 严重程度, 缺陷等级 severity, bug_severity, priority
reviewer 审核人, 审核者 reviewer, auditor
review_result 审核结果, 审查结果 review_result, audit_result
module 模块, 所属模块 module
title 用例描述, 用例名称 title, test_title
execution_time 执行时间, 测试时间 execution_time, test_time

Read the full file on GitHub · 246 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 246 lines · 69 tokens per session scan A 9a88518fd237

Subscribe to this mod's changes

aidocx-feedback-logger is a skill published in the GitHub repository SilenceInsect/AIDocxWorkFlow (2 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 1,953 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

spreadsheet-direct-verification

Use a deterministic Python/openpyxl inspection pass to verify workbook structure, counts, marked rows, and output-file existence when delegated spreadsheet summaries seem inconsistent.

HKUDS/OpenSpace · 36 tokens

spreadsheet-create-verify-gate

Create or edit Excel workbooks with openpyxl-specific pitfall handling, anchored preflight audit, and deterministic post-write proof that every criterion is satisfied.

HKUDS/OpenSpace · 38 tokens

spreadsheet-proof-gate-merged-fedf41-merged

The derived skill is complete and provides a meaningful enhancement.

HKUDS/OpenSpace · 12 tokens

define-data

Standalone Phase 4 of SAP UI testing. Authors one tests/ /test-cases/TC-XXX.data.md requirement spec per case marked dataRequired: yes — choosing the narrowest correct source (sql/static/generated/seeded), and generating upload fixtures in the EXACT file format the program parses (xlsx vs csv). Validates that every…

marcellourbani/vscode_abap_remote_fs · 0 tokens

icedq-mapping-doc-rules

Uses a mapping document provided by the user (Excel, CSV, or Word source-to-target mapping specification) to identify and generate iceDQ rules — Validation, Duplicate, Checksum, Recon, and Pushdown. Use whenever the user uploads or points to a mapping doc or ETL mapping sheet and wants rules derived from it, e.g.…

icedq-tools/mcp-server · 169 tokens

xz-cases

A generator for acceptance-test checklists covering the core feature changes between specified software versions. It writes the checklist to an XLSX spreadsheet, a format used by Microsoft Excel and similar programs.

Xuzan9396/plugin_claude · 66 tokens