See it in action
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptThe prospect agreed during the call to test the API sandbox by Friday if we send documentation. Summarize the conclusion of the call.
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| Assigns designated task owners for follow-up action items | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md25 linessingle file
Call Analysis Framework Skill
When to Use
- Reviewing discovery/diligence calls for coaching or inspection.
- Automating scorecards for enablement or QA teams.
- Prepping executive summaries of key customer conversations.
Framework
- Section Definition – intro, discovery, value, objection handling, next steps (customizable).
- Scoring Rubric – 1-5 scale with observable behaviors for each section.
- Signal Tags – categorize quotes (pain, metrics, stakeholders, commitments, risks).
- Insight Summaries – auto-generate “what went well” vs “improve” lists with evidence.
- Action Routing – push tasks to CRM, assign coaching drills, or escalate to leadership.
Templates
- Call analysis worksheet (scores, notes, quotes, actions).
- Highlight reel brief with timestamp, quote, takeaway.
- Manager inspection summary ready for pipeline reviews.
Tips
- Keep rubric consistent across teams to enable benchmarking.
- Capture 2-3 verbatim quotes per section for credibility.
- Pair with
meddic-checklist when evaluating qualification coverage.
Track record
Benchmark
16 / 22
test cases passed, vs 12 / 22 without
Adoption
- Users
- 1
- Times used
- 4
Safety and source details
SkillSafety
✓ 3 of 3 passed✓Code scan15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026
View 15 scanner checks
live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing
✓IntentSafe
LLM judge · does the skill do what it claims
✓ContentClean
LLM judge · policy & harmful-content review
Source
Importedgtmagents / gtm-agents
plugins/sales-calls/skills/call-analysis-framework/SKILL.md
License Apache-2.0Imported 8/3/2026Version v1