setup
Skill1 starsChanged 13 days agoMITView on GitHub
This skill should be used when an SDR manager says "set up SDR Manager for my team", "set up SDR Manager with the sample team", "add my team", "add a rep", "a rep left", "change a target", "update our targets", "add a proof point", "change the name on our reports", or "try the sample team". It creates or updates the team's folder and profile.
191 other projects use a version of this.
Adopted by
Most recently taken up by
- hydra-db/hydradb-claude-codetheir own version, first seen Nov 8, 2026
- WALKERKILLER/Look-Tongji-Notestheir own version, first seen Nov 8, 2026
- steerlabs/opensteertheir own version, first seen Nov 8, 2026
- ansvisor/ansvisortheir own version, first seen Nov 8, 2026
- dsifry/metaswarmtheir own version, first seen Nov 8, 2026
- anombyte93/prd-taskmastertheir own version, first seen Nov 8, 2026
Used with
Projects with it also use add-voice-transcription, add-discord and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
juancruzmunozalbeloSkilladd-voice-transcription
Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.
Also in 5 projects that use this
MicrosoftSkilladd-discord
Add Discord bot channel integration via Chat SDK.
Also in 11 projects that use this
MicrosoftSkilladd-slack
Add Slack channel integration via Chat SDK.
Also in 11 projects that use this
juancruzmunozalbeloSkilladd-telegram-swarm
Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".
Also in 7 projects that use this
- +8 more from microsoft
Other versions191 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 191
- anthropics/knowledge-work-plugins★ 35ksame name
- garrytan/gbrain★ 32ksame name
- gavrielc/nanoclaw★ 31ksame name
- nanocoai/nanoclaw★ 31ksame name
- qwibitai/nanoclaw★ 31ksame name
- Q00/ouroboros★ 6.3ksame name
- pytorch/executorch★ 5.2ksame name
- agenticnotetaking/arscontexta★ 3.5ksame name
- aws/agent-toolkit-for-aws★ 3.4ksame name
- spotify/portal-ai-plugins★ 2.8ksame name
181 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository3 other files it gives its agents.
- one-on-oneSkill
- rewriteSkill
- scorecardSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. 0 are common, 3 are distinctive, and 10 are very specific to this project.
0
Common
Most of the 171 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
10
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Run every command like this:
- Very specific: line 21
If python3 doesn't work, try python, then py -3, and keep using whichever works.
- Very specific: line 25
Run check-env, then act on the result:
- Distinctive: line 27
Python is missing or older than 3.9: stop and give these steps.
- Very specific: line 35
If the arguments say sample, or the manager wants to try the plugin first, use the sample path.
- Very specific: line 37
Sample path: run init-workspace --path sdr-demo --sample.
- Very specific: line 39
Real team: ask where to keep the team's data.
- Very specific: line 41
If the result says already_exists: true, this is an update.
- Distinctive: line 45
Ask in small batches, and don't ask for anything the manager already told you:
- Very specific: line 79
Run targets --workspace <folder>.
- Very specific: line 83
If the manager wants to replace a target, add it under targets, using the key from the command's output.
- Very specific: line 89
Leave meeting_rate alone unless the team has its own number, because the plugin calculates it from the other targets.
- Very specific: line 91
If the manager wants a different length limit for rewritten messages, add it under outreach_limits, using first_email, follow_up_email, …
“Common” is measured: kept by at least 6 in 10 of the 171 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Set up an SDR team
Help a sales manager get ready to use this plugin.
Talk to the manager in everyday words, because they may not be technical. Say "your team's folder", not "workspace", and "your files", not "exports" or "mappings". Don't show commands, code, JSON, or folder structures unless they ask. When you suggest a next step, give them a sentence to type.
How to run the tool
Run every command like this:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/sdr.py" check-envIf python3 doesn't work, try python, then py -3, and keep using whichever works. Every command prints JSON. Exit code 2 means the manager needs to decide or fix something, and the output says what.
Step 1: Check the computer
Run check-env, then act on the result:
- Python is missing or older than 3.9: stop and give these steps.
- macOS: download the installer from python.org/downloads, run it, then restart Claude.
- Windows: do the same, and tick Add python.exe to PATH on the first installer screen.
browseris null: continue. Explain that reports will arrive as a web page the manager can open and save as a PDF.openpyxlis false: continue. Explain that Excel files need saving as CSV first.
Step 2: Choose a path
If the arguments say sample, or the manager wants to try the plugin first, use the sample path. Otherwise ask which they'd like.
Sample path: run init-workspace --path sdr-demo --sample. Tell the manager the sample is a made-up team of seven reps, then suggest they say "Run my SDR scorecard." Stop here.
Real team: ask where to keep the team's data. The default is sdr-workspace in the current folder. Run init-workspace --path <folder>, then use the full path from the result for every later command and every file you save.
If the result says already_exists: true, this is an update. Read team-profile.json, ask what changed, and change only that. Never replace an existing profile.
Step 3: Learn about the team
Ask in small batches, and don't ask for anything the manager already told you:
- The company and product, in a sentence or two
- "What name should go on your reports?" Most teams use their company name, so offer that
- The ideal customer
- Each rep's name and start date, plus any other spelling of their name used in sales tools
- Which channels the team uses: calls, email, LinkedIn
- Anyone who appears in exports but isn't a rep, such as the manager
- Any true results or customer names reps may mention in their outreach, which sales teams call proof points. It's fine if there are none
Save the answers to team-profile.json in that folder:
{
"company": "Example Analytics",
"brand": "Example Analytics",
"product": "Forecasting software for retailers",
"ideal_customer": "Operations leaders at mid-size retailers",
"proof_points": ["Northwind Stores cut stockouts by 18% in its first year."],
"channels": ["call", "email", "linkedin"],
"reps": [
{"name": "Ava Reyes", "start_date": "2025-02-03", "aliases": ["A. Reyes"], "active": true}
],
"ignored_names": ["Morgan Lee"],
"targets": {}
}Save the report name under brand, spelled exactly as the manager wants it, in up to 60 characters. Use the company name if they have no preference. If they ask to change it later, change only brand.
Use YYYY-MM-DD for dates. When a rep leaves, set active to false instead of deleting them. If a start date is unknown, leave it blank and say that the rep will be treated as fully ramped. Save proof_points as a list of short sentences, or as an empty list if there are none, so the manager isn't asked again.
Step 4: Agree the targets
Run targets --workspace <folder>. This also confirms the profile is valid.
Show the targets in a simple table with their sources. Explain that they're published averages, so on target means typical, not excellent. Point out that the show rate comes from the oldest source, and that a team's own numbers are always better.
If the manager wants to replace a target, add it under targets, using the key from the command's output. Rates are decimals, so 8% is 0.08:
{"targets": {"connect_rate": {"value": 0.08, "as_of": "2026-10-30"}}}Leave meeting_rate alone unless the team has its own number, because the plugin calculates it from the other targets. Run targets again to confirm.
If the manager wants a different length limit for rewritten messages, add it under outreach_limits, using first_email, follow_up_email, call_script, linkedin_note, or linkedin_message. A team with LinkedIn Premium may want 300 for linkedin_note:
{"outreach_limits": {"linkedin_note": {"value": 300, "as_of": "2026-10-30"}}}Step 5: Finish
Tell the manager:
- Coaching notes and downloaded files are sensitive, so keep this folder out of shared drives.
- Each team needs its own folder.
- The next step is to say "Run my SDR scorecard."
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

