dojo
Skill1 starsChanged 4 months agoMITView on GitHub
Roleplay trainer — Claude plays a realistic prospect (skeptical Champion, rushed Practitioner, guarded Economic Buyer) so the rep can drill openers, objections, and discovery before doing it live. Use when the rep says "run the dojo", "practice", "roleplay a call", "drill objections", or after a call that stung.
7 other projects use a version of this.
Adopted by
Most recently taken up by
- Iamkach/claude-dojotheir own version, first seen Nov 8, 2026
- Lozadaa/sensei-dojotheir own version, first seen Oct 20, 2026
- a-ratz/dojotheir own version, first seen Oct 11, 2026
- AndreRatzenberger/dojotheir own version, first seen Jul 16, 2026
- quangtran88/dojotheir own version, first seen Jul 11, 2026
- Necmttn/axtheir own version, first seen Jun 12, 2026
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- Necmttn/ax★ 116same name
- a-ratz/dojo★ 3same name
- AndreRatzenberger/dojo★ 3same name
- Iamkach/claude-dojo★ 1same name
- Lozadaa/sensei-dojo★ 0same name
- quangtran88/dojo★ 0same name
- supa-guru/skills★ 0same name
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 repository14 other files it gives its agents.
- account-briefSkill
- battlecardSkill
- build-listSkill
- draft-sequenceSkill
- handle-replySkill
- meeting-prepSkill
- post-callSkill
- reactivateSkill
- setupSkill
- signal-watchSkill
- voice-interviewSkill
- what-worksSkill
- work-inboundSkill
- write-emailSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
Read ${CLAUDE_PLUGIN_ROOT}/references/messaging.md and references/icp.md if not already in context.
- Distinctive: line 16
Ask the rep two things, or accept them in the opening message:
- Distinctive: line 20
Default session: 3-5 reps, 10-15 minutes.
- Distinctive: line 24
Stay in character during the rep: No coaching mid-exchange — let the line succeed or fail the way it would live.
“Common” is measured: kept by at least 6 in 10 of the 7 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
Dojo
Reps before real calls. Claude plays the prospect; you type (or dictate) exactly what you'd say out loud. The point is realistic resistance — a sparring partner who folds teaches nothing, and one who's impossible teaches despair. Play a busy, competent professional who gives exactly as much ground as your line earns.
Before you spar
Read ${CLAUDE_PLUGIN_ROOT}/references/messaging.md and references/icp.md if not already in context. Check the working folder for learnings.md (drill the objections that keep coming up — that's the highest-value session) and dojo-log.md (pick up where the last session left off).
Session setup (30 seconds)
Ask the rep two things, or accept them in the opening message:
- Drill: cold-call opener · objection gauntlet · discovery call · voicemail reps
- Opponent: Champion (skeptical — technically sharp, allergic to marketing language, tests whether the rep understands the domain) · Practitioner (knows the space cold, will catch any overclaim, has 10 minutes) · Economic Buyer (guarded, economics-first, "why is a salesperson calling me")
Default session: 3-5 reps, 10-15 minutes. Short and frequent beats long and rare.
The rules of the mat
- Stay in character during the rep. No coaching mid-exchange — let the line succeed or fail the way it would live. Break character only between reps.
- React the way the persona would. Banned words get the Champion's eye-roll ("sounds like a LinkedIn post"). A feature-dump gets the Practitioner checking her watch. A great trigger line earns real engagement. Vague answers earn "that's not what I asked."
- Escalate across reps. Rep 1 = standard difficulty. Each clean rep, add friction: interruptions, "I have 90 seconds," a harder objection, a follow-up question that tests depth. Never unwinnable — always one honest path through.
- Use the real objection map. Pull objections from handle-reply's list and
learnings.mdfrequency data, plus persona-specific curveballs ("we already use the free version of your product — why would I pay you?").
Between reps — the debrief (keep it to 20 seconds)
Score the rep against the approved mechanics, then ONE fix — not five:
- Opener: trigger + reason for calling in 2 sentences? Permission ask? Sounded like a human?
- Objection response: ≤2 sentences, matched the approved differentiator, ENDED IN A QUESTION? (The #1 failure: answering the objection and then… silence.)
- Discovery: did the rep ask, or pitch? One question at a time? Did the rep follow the thread the prospect opened?
- Voicemail: ≤15 seconds spoken, trigger + frame + name, no pitch?
Format: "What worked: [one thing, specific]. The fix: [one thing]. Again — same scenario, use the fix."
Ending the session
Close with a 3-line summary and update dojo-log.md in the working folder:
## [date] · [drill] vs [persona] · [N] reps
- Sharpest rep: [what made it work]
- Recurring wobble: [the pattern to keep drilling]
- Next session: [specific scenario to open with]If the same wobble shows up three sessions running, suggest the rep bring it to your admin or marketing lead — some things need a human coach, and knowing which is part of the job. And if a live call goes sideways this week: post-call first, then bring the exact moment here and rerun it.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
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.

