Systems Lab

Agent skill

discovery-call-prep

Produce a 1-page founder/AE briefing for an upcoming discovery call with MEDDPICC slots, discovery questions, objection prep, and competitive context.

slowingNeeds a keyActs undeclared425 words

Filed under Calls, demos and discovery.

From devangk003/gtm-agent-skills · 32 skills · 0 · pushed 2026-06-18

What it does when it runs

Produce a 1-page founder/AE briefing for an upcoming discovery call with MEDDPICC slots, discovery questions, objection prep, and competitive context. Use when the user says "prep me for this call", "brief me for the meeting", "discovery call tomorrow", or "refresh the briefing.

Read from the skill and the 4 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.

Keys and connectors you must supply
  • AGENTIC_APP_TOKEN
Hosts it reaches
No third-party host appears in the skill or its bundled files.
Tool permissions it declares
No allowed-tools in the frontmatter. It does act, so it runs under whatever permissions your session already grants.
Actions present in the files
shell

Ask about discovery-call-prep

Opens your assistant with this page's verified links already in the prompt.

Is this safe to install?ClaudeChatGPT
Adapt it to my stackClaudeChatGPT
What else do I need for it to workClaudeChatGPT
Rather ask a human? Talk to Cheetah

Install it

View source on GitHub ↗
git clone --depth 1 --filter=blob:none --sparse https://github.com/devangk003/gtm-agent-skills.git /tmp/gtm-agent-skills
git -C /tmp/gtm-agent-skills sparse-checkout set "discovery-call-prep"
mkdir -p ~/.claude/skills/discovery-call-prep
cp -R "/tmp/gtm-agent-skills/discovery-call-prep/." ~/.claude/skills/discovery-call-prep/

Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗

The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.

Before you install: this skill will not complete its job on a bare agent. It needs AGENTIC_APP_TOKEN, which you have to obtain separately.

The skill

Source on GitHub ↗

Reproduced in full from devangk003/gtm-agent-skills/blob/6b9a1b0094ffd83d6c02bc03b7ce1610661a1644/discovery-call-prep/SKILL.md, which is licensed MIT (skill frontmatter). 425 words, 6 headings.

Discovery Call Prep

Produce a 1-page founder/AE briefing for an upcoming discovery call: recipient profile, MEDDPICC slots, 9 discovery questions, 3 pre-staged objections, competitive context, and recommended agenda. Hard ceiling: ≤450 words.

When to Use

  • Discovery call booked and briefing needed
  • Call rescheduled and prior briefing is stale (>48h)
  • High-stakes Tier-1 call needs deep brief
  • 5+ calls on the calendar — batch prep
  • Founder hand-off from SDR cadence
  • User says "prep me for this call" or "brief me for the meeting"

Quick Reference

ConceptValue
Briefing length1 page (≤450 words / single screen)
MEDDPICC 8 slotsMetrics / Economic Buyer / Decision Criteria / Decision Process / Paper Process / Identify Pain / Champion / Competition
Discovery questions3 per genre: open-discovery / pain-quantify / next-step (9 total)
Objection prep3 most-likely objections with pre-staged responses
Briefing freshness≤48h at call time; stale → re-prep
Competitive context1–3 likely competitors with 1-line counter-positioning each

Procedure

  1. Validate inputs + assemble profile. Read meeting context + lead record + cadence/reply thread. Confirm meeting <48h. Profile ≤80 words: name, title, company, ICP tier+score, hook, most-recent reply. See ${HERMES_SKILL_DIR}/references/profile-template.md.
  2. Populate MEDDPICC slots. Fill from existing intel (function-1 + function-2 data). Each slot: populated or unknown — ask. See ${HERMES_SKILL_DIR}/references/meddpicc-slots.md.
  3. Generate 3 questions per genre. Open-discovery (current state), pain-quantify (cost of doing nothing), next-step (decision process/champion/timeline). Anchor to verified pain.
  4. Pre-stage 3 objections + competitive context. Pull from objection-handling-library. 1–3 likely competitors with counter-positioning lines.
  5. Recommend call agenda + push. 3 bullets: 5min context / 15min pain-quantify / 5–10min next-step. Push briefing as interaction:research. PATCH person with timestamps. See ${HERMES_SKILL_DIR}/scripts/push_to_crm.py.

Pitfalls

  • 8-page briefings — founder reads first paragraph only; 1 page is the discipline
  • Including open rate — Apple MPP made it noise; reply rate is the signal
  • Inventing MEDDPICC slot content — unknown is honest; ask in the call
  • Stale briefing — >48h → re-prep cheaply
  • Missing reply context — founder needs "they replied to Touch 2 with X"
  • Over-prepping objections — 3 likely is enough; 8 is paralysis

Verification

  1. Total word count ≤450; every named entity has provenance
  2. MEDDPICC slot content traces to real data or unknown
  3. Questions reference verified pain anchors (not generic)
  4. 3 objections + 9 questions + 1–3 competitors all present
  5. Freshness timestamp ≤48h

Files bundled with it

These load only when the skill asks for them, so they cost nothing until it runs.

Other skills for the same job

Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.

Need help setting it up?

This page tells you what discovery-call-prep does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.

Book a call →

The directory stays free. There is nothing gated behind this.