See it in action
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptWe want to track how CompetitorZ shifts its messaging from developer-centric to executive-focused over time. Draft an operational plan for this.
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| Includes a change log to record narrative evolution over time | Missed | Passed |
|---|
| Requires dates and source tracking for each narrative entry | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md25 linessingle file
Competitive Intelligence Ops Skill
When to Use
- Preparing battlecards, objection handling, or exec briefings.
- Monitoring competitor launches, pricing changes, or campaigns.
- Running win/loss and market intelligence programs.
Framework
- Collect – pull from sales calls, Gong, analyst notes, communities, social, product updates.
- Analyze – map strengths/weaknesses, feature parity, pricing, GTM motions.
- Package – build battlecards, alerts, teardown docs, highlights for weekly digests.
- Enable – deliver via enablement hubs, Slack alerts, office hours.
- Measure – track adoption, impact on win rates, feedback loops.
Templates
- Competitor dossier structure (Overview, Differentiation, Traps, Assets).
- Alert format for urgent updates.
- Win/loss survey + summary report.
Tips
- Always cite sources and freshness dates.
- Partner with sales enablement to ensure updates are surfaced during deal cycles.
- Keep a change log to monitor how competitor narratives evolve.
Track record
Benchmark
13 / 22
test cases passed, vs 9 / 22 without
Adoption
- Users
- 0
- Times used
- 0
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/product-marketing/skills/competitive-intel/SKILL.md
View on GitHub ↗License Apache-2.0Imported 8/3/2026Version v1