Slack
paperclipai/paperclip
Use the assigned Slack bot from Slack conversations, Paperclip tasks, and routines to read shared discussions and collaborate.
Full pipeline where an agent team collaborates to build a chatbot system.
Install Chatbot Builder
$ npx skills add revfactory/harness-100 --skill chatbot-builder -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install revfactory/harness-100 chatbot-builder --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/revfactory/harness-100.git skills-src && mkdir -p .claude/skills && cp -r skills-src/en/38-chatbot-builder/.claude/skills/chatbot-builder .claude/skills/chatbot-builder && rm -rf skills-srcUse ~/.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/
Install the "chatbot-builder" agent skill from https://github.com/revfactory/harness-100/tree/main/en/38-chatbot-builder/.claude/skills/chatbot-builder into .claude/skills/chatbot-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chatbot-builder", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/revfactory/harness-100/tree/main/en/38-chatbot-builder/.claude/skills/chatbot-builderType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add revfactory/harness-100 --skill chatbot-builder -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install revfactory/harness-100 chatbot-builder --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/revfactory/harness-100.git skills-src && mkdir -p .agents/skills && cp -r skills-src/en/38-chatbot-builder/.claude/skills/chatbot-builder .agents/skills/chatbot-builder && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "chatbot-builder" agent skill from https://github.com/revfactory/harness-100/tree/main/en/38-chatbot-builder/.claude/skills/chatbot-builder into .agents/skills/chatbot-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chatbot-builder", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add revfactory/harness-100 --skill chatbot-builder -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install revfactory/harness-100 chatbot-builder --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/revfactory/harness-100.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/en/38-chatbot-builder/.claude/skills/chatbot-builder .cursor/skills/chatbot-builder && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "chatbot-builder" agent skill from https://github.com/revfactory/harness-100/tree/main/en/38-chatbot-builder/.claude/skills/chatbot-builder into .cursor/skills/chatbot-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chatbot-builder", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/revfactory/harness-100.git --path en/38-chatbot-builder/.claude/skills/chatbot-builder--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add revfactory/harness-100 --skill chatbot-builder -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install revfactory/harness-100 chatbot-builder --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/revfactory/harness-100.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/en/38-chatbot-builder/.claude/skills/chatbot-builder .gemini/skills/chatbot-builder && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "chatbot-builder" agent skill from https://github.com/revfactory/harness-100/tree/main/en/38-chatbot-builder/.claude/skills/chatbot-builder into .gemini/skills/chatbot-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chatbot-builder", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install revfactory/harness-100 chatbot-builderInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add revfactory/harness-100 --skill chatbot-builder -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/revfactory/harness-100.git skills-src && mkdir -p .github/skills && cp -r skills-src/en/38-chatbot-builder/.claude/skills/chatbot-builder .github/skills/chatbot-builder && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "chatbot-builder" agent skill from https://github.com/revfactory/harness-100/tree/main/en/38-chatbot-builder/.claude/skills/chatbot-builder into .github/skills/chatbot-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chatbot-builder", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add revfactory/harness-100 --skill chatbot-builder -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install revfactory/harness-100 chatbot-builder --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/revfactory/harness-100.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/en/38-chatbot-builder/.claude/skills/chatbot-builder .opencode/skills/chatbot-builder && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "chatbot-builder" agent skill from https://github.com/revfactory/harness-100/tree/main/en/38-chatbot-builder/.claude/skills/chatbot-builder into .opencode/skills/chatbot-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chatbot-builder", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
chatbot-builder- GitHub stars
- 1.3k
- Token cost
- ~1.8k tokens
- SKILL.md length
- 720 words
- Files
- 1
- Skills in repo
- 464
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Full pipeline where an agent team collaborates to build a chatbot system.
- Works in 3 steps: Preparation (performed directly by the… → Team Assembly and Execution → Integration and Final Deliverables
- Requests like build me a chatbot
- SKILL.md covers Execution Mode, Agent Composition, Workflow and Execution Modes by Request Scope, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Chatbot Builder is an agent skill from revfactory/harness-100. Full pipeline where an agent team collaborates to build a chatbot system. Use this skill for requests like 'build me a chatbot', 'conversational bot development', 'customer service bot', 'FAQ chatbot', 'KakaoTalk chatbot', 'Slack bot', 'auto-response system', 'conversational AI', 'chatbot design', and other chatbot construction tasks. Also supports design-only mode when only conversation design is needed. Note: voice assistants (Alexa/Google Home), real-time voice call bots, and video chatbots are outside the…
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Sales & Support, covering Chatbots and conversational support. It works with Slack. The licence is Apache-2.0.
When your agent uses it
- Requests like build me a chatbot
- Conversational bot development
- Customer service bot
- KakaoTalk chatbot
Example prompts
- “build me a chatbot”
- “conversational bot development”
- “customer service bot”
- “/chatbot-builder”
Workflow steps
3 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 8e8d35c. 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
Chatbot Builder loads about 1.8k tokens when it runs. Until then it costs about 138 tokens; SKILL.md has 720 words of instructions outside code blocks.
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 revfactory/harness-100 at commit 8e8d35c, republished under its Apache-2.0 licence (© revfactory). 720 words, ~1,843 tokens.
Download SKILL.mdSave it as
.claude/skills/chatbot-builder/SKILL.md (or your agent's skills folder).- name
- chatbot-builder
- description
- Full pipeline where an agent team collaborates to build a chatbot system. Use this skill for requests like 'build me a chatbot', 'conversational bot development', 'customer service bot', 'FAQ chatbot', 'KakaoTalk chatbot', 'Slack bot', 'auto-response system', 'conversational AI', 'chatbot design', and other chatbot construction tasks. Also supports design-only mode when only conversation design is needed. Note: voice assistants (Alexa/Google Home), real-time voice call bots, and video chatbots are outside the scope of this skill.
Chatbot Builder — Chatbot Construction Pipeline
An agent team collaborates to build a chatbot through persona design > conversation design > NLU > integration > testing.
Execution Mode
Agent Team — Five agents communicate directly via SendMessage and perform cross-validation.
Agent Composition
| Agent | File | Role | Type |
|---|---|---|---|
| persona-architect | .claude/agents/persona-architect.md | Bot persona design | general-purpose |
| conversation-designer | .claude/agents/conversation-designer.md | Conversation scenario design | general-purpose |
| nlu-developer | .claude/agents/nlu-developer.md | NLU pipeline implementation | general-purpose |
| integration-engineer | .claude/agents/integration-engineer.md | Channel integration, deployment | general-purpose |
| dialog-tester | .claude/agents/dialog-tester.md | Quality verification, testing | general-purpose |
Workflow
Phase 1: Preparation (performed directly by the orchestrator)
- Extract the following from user input:
- Chatbot purpose: Customer service/FAQ/reservations/orders/consultation, etc.
- Target users: Age, digital literacy, expectation level
- Integration channels: Slack/KakaoTalk/Telegram/Web/multi-channel
- Domain knowledge: Business rules, FAQ list, product information, etc.
- Constraints (optional): Technology stack, response time requirements
- Create the
_workspace/directory at the project root - Organize the input and save it to
_workspace/00_input.md - Create the
_workspace/src/directory - If pre-existing files are available, copy them to
_workspace/and skip the corresponding phase - Determine the execution mode based on the scope of the request (see "Execution Modes by Request Scope" below)
Phase 2: Team Assembly and Execution
| Order | Task | Owner | Dependencies | Deliverable |
|---|---|---|---|---|
| 1 | Persona design | persona | None | _workspace/01_persona_spec.md |
| 2 | Conversation design | designer | Task 1 | _workspace/02_conversation_design.md |
| 3a | NLU implementation | nlu-dev | Task 2 | _workspace/03_nlu_config.md + src/ |
| 3b | Integration design | integrator | Task 2 | _workspace/04_integration_spec.md + src/ |
| 4 | Testing | tester | Tasks 3a, 3b | _workspace/05_test_report.md |
Tasks 3a (NLU) and 3b (integration) run in parallel.
Inter-agent communication flow:
- persona completes > passes tone and manner guide to designer, passes domain keywords to nlu-dev
- designer completes > passes intent/entity catalog to nlu-dev, passes external integration flows to integrator
- nlu-dev completes > passes NLU interface to integrator, passes test data to tester
- integrator completes > passes test environment info to tester
- tester cross-validates all deliverables. On CRITICAL findings, requests corrections from the relevant agent > rework > re-verification (up to 2 rounds)
Phase 3: Integration and Final Deliverables
Finalize deliverables based on the tester's report:
- Verify all files in
_workspace/andsrc/code - Confirm that all CRITICAL findings have been resolved
- Report the final summary to the user
Execution Modes by Request Scope
| User Request Pattern | Execution Mode | Agents Deployed |
|---|---|---|
| "Build me a chatbot", "full build" | Full pipeline | All 5 agents |
| "Just do the conversation design", "write scenarios" | Design mode | persona + designer |
| "Just develop the NLU" (design complete) | NLU mode | nlu-dev + tester |
| "Integrate chatbot with KakaoTalk" (implementation complete) | Integration mode | integrator + tester |
| "Test the chatbot" (implementation complete) | Test mode | tester only |
Reusing existing files: If the user provides an existing conversation design document or NLU configuration, copy those files to _workspace/ and skip the corresponding steps.
Show full SKILL.md (294 more words)Show less
Data Transfer Protocol
| Strategy | Method | Purpose |
|---|---|---|
| File-based | _workspace/ directory | Design documents and configuration sharing |
| Message-based | SendMessage | Real-time key information transfer, correction requests |
| Code-based | _workspace/src/ | Executable source code |
Error Handling
| Error Type | Strategy |
|---|---|
| Insufficient domain knowledge | Request additional FAQ list/business information from user, supplement with web search |
| Channel API changes | Verify latest API documentation via WebFetch, then update integration code |
| NLU accuracy below threshold | Augment training data > redesign prompts > strengthen fallback, in that order |
| Agent failure | Retry once > if still failing, proceed without that deliverable and note in report |
Test Scenarios
Normal Flow
Prompt: "Build a KakaoTalk chatbot for cafe order processing. It should support menu browsing, ordering, and payment guidance" Expected result:
- Persona: Bright, friendly cafe staff character, formal tone, active emoji usage
- Conversation design: Menu browsing/ordering/payment guidance/business hours intents, slots (menu name/quantity/options)
- NLU: LLM prompt-based intent classification, menu name entity dictionary construction
- Integration: KakaoTalk chatbot API integration, card-type messages for menu display
- Testing: Order flow happy path, fallback for unavailable menu items, multi-turn ordering
Existing File Reuse Flow
Prompt: "I have this conversation design document; implement the NLU and integrate it with KakaoTalk" + design document attached Expected result:
- Copy existing design document to
_workspace/02_conversation_design.md - Skip persona and designer; deploy nlu-dev + integrator + tester
- Implement NLU based on existing intent/entity catalog
Error Flow
Prompt: "Build me a chatbot" (purpose, channel unclear) Expected result:
- persona proposes a generic persona and requests purpose confirmation from user
- Proceed with remaining pipeline after purpose is confirmed
- Note in report: "Channel undetermined — web widget applied as default"
Agent Extension Skills
Extension skills that enhance agent domain expertise:
| Skill | File | Target Agent | Role |
|---|---|---|---|
| intent-taxonomy-builder | .claude/skills/intent-taxonomy-builder/skill.md | nlu-developer, conversation-designer | Intent taxonomy design, entity-slot mapping, training data generation, confusion matrix |
| conversation-flow-validator | .claude/skills/conversation-flow-validator/skill.md | dialog-tester, conversation-designer | Dialog flow defect detection, Happy/Sad/Edge testing, fallback hierarchy, quality metrics |
© revfactory, 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
Just SKILL.md in en/38-chatbot-builder/.claude/skills/chatbot-builder of revfactory/harness-100.
Open the folder on GitHubat commit 8e8d35c
Compare with similar skills
Chatbot Builder 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Chatbot Builder this skillrevfactory/harness-100 | 1.3k | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| Slackpaperclipai/paperclip | 98k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Teams App Developermicrosoft/work-iq | 1k | — | ~1.8k | Automated safety check: Notes | Custom licence | |
| Outreachyc-software/recruiting | 116 | — | ~3k | Automated safety check: Notes | None | |
| AirweaveCraftOS-dev/CraftBot | 392 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Slack To Teamsmicrosoft/work-iq | 1k | 1 repos | ~2.3k | Automated safety check: Pass | Custom licence |
Similar skills
- Official
Teams App Developer
microsoft/work-iq
Build, test, and deploy code-based Teams apps using the M365 Agents Toolkit CLI.
Outreach
yc-software/recruiting
Draft personalized cold outreach to a candidate the hiring manager hasn't contacted yet.
Airweave
CraftOS-dev/CraftBot
Context retrieval layer for AI agents across users' applications.
- Official
Slack To Teams
microsoft/work-iq
Sub-skill of microsoft-365-agents-toolkit. An agent skill from microsoft/work-iq.
Slack Bot Builder
davila7/claude-code-templates
Build Slack apps using the Bolt framework across Python, JavaScript, and Java.
More from revfactory/harness-100
All 464 skills in this repoAnti Bot Analyzer
revfactory/harness-100
A skill for analyzing website anti-bot defense mechanisms and developing legitimate evasion strategies.
API Error Design Patterns
revfactory/harness-100
Reference for designing how an API reports failures: structured error codes, response shapes, client-friendly messages, an error catalog and retry or fallback advice.
API Security Checklist
revfactory/harness-100
Walks a backend-dev agent through OWASP API Top 10 checks, authentication and authorization patterns, and defense code during API design.
Arg Parser Generator
revfactory/harness-100
Methodology for systematically designing and generating CLI tool argument parser structures.
Audience Segmentation
revfactory/harness-100
Audience segmentation skill used by the analyst and curator agents.
Audio Storytelling
revfactory/harness-100
Audio storytelling skill used by the podcast scriptwriter and show note editor.
Related
Works with
Categories
Questions about Chatbot Builder
What does Chatbot Builder do?
Full pipeline where an agent team collaborates to build a chatbot system. Chatbot Builder is an agent skill from revfactory/harness-100. Full pipeline where an agent team collaborates to build a chatbot system.
When should I use Chatbot Builder?
Chatbot Builder fits situations like: requests like build me a chatbot; conversational bot development; customer service bot; kakaoTalk chatbot.
How do I install Chatbot Builder in Claude Code?
Run `npx skills add revfactory/harness-100 --skill chatbot-builder -a claude-code`. Or copy the skill folder (en/38-chatbot-builder/.claude/skills/chatbot-builder in revfactory/harness-100) into .claude/skills/chatbot-builder in your project. Claude Code loads it when a task matches its description.
How do I install Chatbot Builder in Codex?
Run `npx skills add revfactory/harness-100 --skill chatbot-builder -a codex`. Or copy the skill folder (en/38-chatbot-builder/.claude/skills/chatbot-builder in revfactory/harness-100) into .agents/skills/chatbot-builder in your project. Codex loads it when a task matches its description.
Can I use Chatbot Builder 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 revfactory/harness-100 --skill chatbot-builder -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/chatbot-builder, .gemini/skills/chatbot-builder, .github/skills/chatbot-builder and .opencode/skills/chatbot-builder in your project.
What does Chatbot Builder need to run?
SKILL.md names no scripts, command-line tools or credentials: Chatbot Builder is instructions for the agent only.
Does Chatbot Builder 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 Chatbot Builder 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 Chatbot Builder use?
Chatbot Builder 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 Chatbot Builder use?
About 1.8k tokens (SKILL.md is roughly 7.4k 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 Chatbot Builder?
Skills that share tags, products or a category with Chatbot Builder: Slack (paperclipai/paperclip, 98k stars), Teams App Developer (microsoft/work-iq, 1k stars), Outreach (yc-software/recruiting, 116 stars) and Airweave (CraftOS-dev/CraftBot, 392 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Chatbot Builder?
revfactory (a GitHub user) maintains it in revfactory/harness-100, which has 1,290 GitHub stars. The repository holds 464 skills in this directory. The repository was last updated on March 22, 2026.
Source: revfactory/harness-100 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.