Agent skill

Satisfaction Feedback

by Harryoung in Harryoung/efka

Handle user satisfaction feedback. An agent skill from Harryoung/efka.

Apache-2.0Auto-check passedSales & Support

Install Satisfaction Feedback

skills CLI
$ npx skills add Harryoung/efka --skill satisfaction-feedback -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Harryoung/efka satisfaction-feedback --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Harryoung/efka.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/satisfaction-feedback .claude/skills/satisfaction-feedback && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
satisfaction-feedback
GitHub stars
104
Token cost
~346 tokens
SKILL.md length
133 words
Files
2
Skills in repo
6
Repo updated
First seen
Licence
Apache-2.0

At a glance

Handle user satisfaction feedback. An agent skill from Harryoung/efka.

  • Works in 3 steps: Use file locks: Must use SharedKBAccess… → Concurrency safety: Avoid data conflicts… → Status update: Set session_status to…
  • Words: satisfied/unsatisfied/resolved/not resolved/thanks/满意/不满意/解决了/没解决/谢谢
  • SKILL.md covers Trigger Words, Processing Logic, Key Principles and Detailed Operations
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Satisfaction Feedback is an agent skill from Harryoung/efka. Handle user satisfaction feedback. When users respond with "satisfied"/"unsatisfied", update FAQ usage count or record BADCASE. Trigger words: satisfied/unsatisfied/resolved/not resolved/thanks/满意/不满意/解决了/没解决/谢谢.

Its SKILL.md is about 350 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `FAQ_OPERATIONS.md`).

It sits in Sales & Support, covering Help center and FAQ content. The repository describes itself as: AI-powered knowledge management without vector embeddings. Built upon Claude Agent SDK, File system based, Agent driven. Maybe slower, but results are much more reliable! The licence is Apache-2.0.

When your agent uses it

  • Words: satisfied/unsatisfied/resolved/not resolved/thanks/满意/不满意/解决了/没解决/谢谢
  • Tasks that involve Help center and FAQ content

Example prompts

  • “satisfied”
  • “unsatisfied”
  • “/satisfaction-feedback”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Use file locks: Must use SharedKBAccess file locks when updating FAQ.md and BADCASE.md
  2. Concurrency safety: Avoid data conflicts when multiple users operate simultaneously
  3. Status update: Set session_status to "resolved" after satisfied feedback

What it can do on your machine

Read from SKILL.md and the folder at commit 9e6d3a4. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Satisfaction Feedback loads about 346 tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 133 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~59
When it runs · the whole SKILL.md, loaded when a task matches
~346

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Harryoung/efka at commit 9e6d3a4, republished under its Apache-2.0 licence (© Harryoung). 133 words, ~346 tokens.

Download SKILL.mdSave it as .claude/skills/satisfaction-feedback/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
satisfaction-feedback
description
Handle user satisfaction feedback. When users respond with "satisfied"/"unsatisfied", update FAQ usage count or record BADCASE. Trigger words: satisfied/unsatisfied/resolved/not resolved/thanks/满意/不满意/解决了/没解决/谢谢.

Satisfaction Feedback Processing

Process user satisfaction feedback and update FAQ or record issues based on the answer source.

Trigger Words

Satisfied: satisfied, resolved, thanks, understood, ok, got it, clear, I see, 满意, 解决了, 谢谢, 明白了, 好的, 懂了, 清楚了, 知道了 Unsatisfied: unsatisfied, not resolved, wrong, incorrect, doesn't work, 不满意, 没解决, 不对, 错了, 不行

Processing Logic

Process feedback based on answer source from previous round (metadata answer_source):

Answer SourceSatisfied FeedbackUnsatisfied Feedback
FAQIncrement usage countRemove entry + Record BADCASE
Knowledge base fileAdd to FAQRecord BADCASE

Key Principles

  1. Use file locks: Must use SharedKBAccess file locks when updating FAQ.md and BADCASE.md
  2. Concurrency safety: Avoid data conflicts when multiple users operate simultaneously
  3. Status update: Set session_status to "resolved" after satisfied feedback

Detailed Operations

For FAQ add/delete/modify operation details, see FAQ_OPERATIONS.md

© Harryoung, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/satisfaction-feedback of Harryoung/efka.

  • SKILL.md
  • FAQ_OPERATIONS.md

Open the folder on GitHubat commit 9e6d3a4

Compare with similar skills

Satisfaction Feedback next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Satisfaction Feedback compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Satisfaction Feedback this skillHarryoung/efka104—~346Automated safety check: PassApache-2.0
Brand Product Knowledge Builderlimecloud/lime1.5k—~709Automated safety check: PassApache-2.0
Cc10x Guideromiluz13/cc10x164—~2.2kAutomated safety check: PassMIT
Yao Geo Intent Mineryaojingang/yao-geo-skills868—~500Automated safety check: PassMIT
Faq CollectorCherryHQ/cherry-studio52k—~154Automated safety check: PassAGPL-3.0
Eol Internal Enablementdeanpeters/Product-Manager-Skills7.2k—~3.1kAutomated safety check: PassCustom licence

Similar skills

  • 将品牌产品资料、规格参数、卖点证据、FAQ、价格权益、竞品区别和合规边界,整理成符合 Agent Knowledge v0.6 document-first 标准、可被 AI 安全调用的产品资料知识库。适用于用户要求“整理产品知识库”“沉淀产品 FAQ”“把品牌产品资料变成项目资料”“维护产品资料包”的场景。

    1.5k GitHub stars~709 tokensUpdated yesterday
    Sales & SupportAuto-check passed
  • Cc10x Guide

    romiluz13/cc10x

    Answers questions about cc10x itself — what it is, how to install and configure it, how the router, workflows, memory, and hooks operate, and how to troubleshoot.

    164 GitHub stars~2.2k tokensUpdated yesterday
    Sales & SupportAuto-check passed
  • Yao Geo Intent Miner

    yaojingang/yao-geo-skills

    A skill your agent uses when a user asks for GEO 意图拓词、AI 搜索意图挖掘、AI 搜索问题集、问题簇、追问链路、查询重写、内容选题库、FAQ 题库、监测 Prompt 库, or AI Intent Miner.

    868 GitHub stars~500 tokensUpdated 7 days ago
    Sales & SupportAuto-check passed
  • Faq Collector

    CherryHQ/cherry-studio

    将成功解决的用户问题收录到 FAQ 知识库。问题解决后自动判断是否收录。也可以在用户说"收录到 FAQ"、"记录这个问题"、"add to FAQ"时手动触发。

    52k GitHub stars~154 tokensUpdated today
    Sales & SupportAuto-check passed
  • Eol Internal Enablement

    deanpeters/Product-Manager-Skills

    Build the support FAQ, sales talking points, and objection handling teams need before an EOL announcement.

    7.2k GitHub stars~3.1k tokensUpdated 1 mo ago
    Sales & SupportAuto-check passed
  • Summary Faq Workflow

    ArmDeveloperEcosystem/arm-learning-paths

    Generate, style-review, and patch AI-assisted Learning Path summaries and FAQs for one path, a path subset, a category, or the repository.

    154 GitHub stars~1.5k tokensUpdated yesterday
    Sales & SupportAuto-check passed

More from Harryoung/efka

  • Excel Parser

    Harryoung/efka

    Smart Excel/CSV file parsing with intelligent routing based on file complexity analysis.

    104 GitHub stars~2.3k tokensUpdated 6 mo ago
    Auto-check passed
  • Document Conversion

    Harryoung/efka

    Convert DOC/DOCX/PDF/PPT/PPTX documents to Markdown format. An agent skill from Harryoung/efka.

    104 GitHub stars~505 tokensUpdated 6 mo ago
    Auto-check passed
  • Batch Notification

    Harryoung/efka

    Send IM messages to users in batch. An agent skill from Harryoung/efka.

    104 GitHub stars~512 tokensUpdated 6 mo ago
    Auto-check passed
  • Expert Routing

    Harryoung/efka

    Domain expert routing. An agent skill from Harryoung/efka.

    104 GitHub stars~325 tokensUpdated 6 mo ago
    Auto-check passed
  • Large File Toc

    Harryoung/efka

    Generate table of contents overview for large files. An agent skill from Harryoung/efka.

    104 GitHub stars~293 tokensUpdated 6 mo ago
    Auto-check passed

Categories

Questions about Satisfaction Feedback

What does Satisfaction Feedback do?

Handle user satisfaction feedback. An agent skill from Harryoung/efka. Satisfaction Feedback is an agent skill from Harryoung/efka. Handle user satisfaction feedback.

When should I use Satisfaction Feedback?

Satisfaction Feedback fits situations like: words: satisfied/unsatisfied/resolved/not resolved/thanks/满意/不满意/解决了/没解决/谢谢; tasks that involve Help center and FAQ content.

How do I install Satisfaction Feedback in Claude Code?

Run `npx skills add Harryoung/efka --skill satisfaction-feedback -a claude-code`. Or copy the skill folder (skills/satisfaction-feedback in Harryoung/efka) into .claude/skills/satisfaction-feedback in your project. Claude Code loads it when a task matches its description.

How do I install Satisfaction Feedback in Codex?

Run `npx skills add Harryoung/efka --skill satisfaction-feedback -a codex`. Or copy the skill folder (skills/satisfaction-feedback in Harryoung/efka) into .agents/skills/satisfaction-feedback in your project. Codex loads it when a task matches its description.

Can I use Satisfaction Feedback in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Harryoung/efka --skill satisfaction-feedback -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/satisfaction-feedback, .gemini/skills/satisfaction-feedback, .github/skills/satisfaction-feedback and .opencode/skills/satisfaction-feedback in your project.

What does Satisfaction Feedback need to run?

SKILL.md names no scripts, command-line tools or credentials: Satisfaction Feedback is instructions for the agent only.

Does Satisfaction Feedback access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Satisfaction Feedback safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Satisfaction Feedback use?

Satisfaction Feedback is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Satisfaction Feedback use?

About 346 tokens (SKILL.md is roughly 1.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Satisfaction Feedback?

Skills that share tags, products or a category with Satisfaction Feedback: Brand Product Knowledge Builder (limecloud/lime, 1.5k stars), Cc10x Guide (romiluz13/cc10x, 164 stars), Yao Geo Intent Miner (yaojingang/yao-geo-skills, 868 stars) and Faq Collector (CherryHQ/cherry-studio, 52k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Satisfaction Feedback?

Harryoung (a GitHub user) maintains it in Harryoung/efka, which has 104 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on March 16, 2026.

Source: Harryoung/efka on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.