Systems Lab

Agent skill

objection-handling-library

Match embedded objections to a 12-objection canonical library and produce ranked response variants with cadence-state recommendations.

slowingNeeds a keyActs undeclared436 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

Match embedded objections to a 12-objection canonical library and produce ranked response variants with cadence-state recommendations. Use when the user says "handle this objection", "generate response variants", "match objection to library", or "we keep hearing X objection.

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 objection-handling-library

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 "objection-handling-library"
mkdir -p ~/.claude/skills/objection-handling-library
cp -R "/tmp/gtm-agent-skills/objection-handling-library/." ~/.claude/skills/objection-handling-library/

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/objection-handling-library/SKILL.md, which is licensed MIT (skill frontmatter). 436 words, 6 headings.

Objection Handling Library

Match an embedded objection to a 12-objection canonical library, produce 2–3 response variants ranked by fit, and recommend a cadence-state action. Never invent library entries on the fly.

When to Use

  • Reply-classification flags an embedded objection
  • A not-now reply needs a graceful response
  • Objection patterns recur and need codified responses
  • Sales reps need pre-approved objection templates
  • User says "handle this objection" or "generate response variants"
  • Library refresh after 30+ new objections collected

Quick Reference

ConceptValue
12-objection libraryalready-using-competitor / no-budget / no-authority / no-need-now / bad-timing / happy-with-status-quo / tried-similar-failed / too-expensive / too-small / send-me-email / wrong-person / compliance-security-blocker
Match confidence floor≥0.7 to use library response; below = new-objection-pattern flag
Response frameworksFeel-Felt-Found (empathy) / Re-discovery (Bosworth pain) / Time-shift (resume date) / Counter-position (Dunford reframe)
Variants per objection2–3 (light / medium / direct tone)
Cadence actionsresume-stated-date / nurture-90d / nurture-12mo / exit-permanent / re-enrich / discovery-prep

Procedure

  1. Validate inputs. Read classified reply + cadence context + lead record. Confirm embedded objection present. If absent, recommend follow-up-management instead.
  2. Match against 12-library. LLM-backed match with confidence per entry. Output: {best_match, confidence, second_best}. See ${HERMES_SKILL_DIR}/references/objection-library.md.
  3. Confidence gate. ≥0.7 → use library framework. <0.7 → flag new-objection-pattern; route to manual response; collect for refresh.
  4. Generate 2–3 response variants. Pick framework per matched entry. Generate light/medium/direct tone variants. Each ≤80 words, one CTA. Reference verified context only. See ${HERMES_SKILL_DIR}/references/frameworks.md.
  5. Recommend cadence-state action. bad-timing → resume per date. already-using-competitor → nurture-90d. no-budget → nurture-90d + flag lead-scoring re-tier. compliance → discovery-prep mode.
  6. Capture intel for downstream. Competitor mentions → competitive-intelligence. Pricing pushback → revenue-forecasting. Persistent pain → icp-refinement-loop.
  7. Push to CRM. Per-objection interaction:reply-response with library match + variants + cadence action. PATCH person with new state. See ${HERMES_SKILL_DIR}/scripts/push_to_crm.py.

Pitfalls

  • Inventing library entries on the fly — flag as new-pattern instead
  • Generic "I understand" responses — Feel-Felt-Found requires specifics
  • Counter-positioning by attacking competitor — reframe the alternative, not the competitor
  • Re-discovery on a clean not-interested — honor the no
  • Multi-objection replies handled as one — match both, respond to more-removable first
  • Skipping intel capture — competitor mentions are gold for competitive-intelligence

Verification

  1. Every objection has a library-match record OR new-pattern flag
  2. Response variants reference only verified context (no invented quotes)
  3. Cadence-state action propagated to person record
  4. Intel routed to downstream skills (sample-check competitor / pricing mentions)

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 objection-handling-library 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.