agentleFS
Sign inStart free
vinayagrwvinayagrw/claude-skills/competitive-battle-cards/SKILL.md

competitive-battle-cards

Skill1 starsChanged 26 days agoApache-2.0View on GitHub

Build one-page competitive battle cards from internal content (call notes, lost-deal notes, wiki, product docs) plus public research, and run win-loss analysis on a CSV of closed deals to find patterns and leading signals. Every claim is sourced. Use when the user names a competitor, asks how to beat or position against someone, wants a battle card, or wants win-loss or predictive deal insights, or when presales-ai routes here.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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
  1. Very specific:

    Read deal-context.json first if it exists.

    line 8
  2. Distinctive:

    Check: every claim has a source, nothing says the competitor "can't" without a cited reason, and there are no em-dashes or semicolons.

    line 25

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Battle cards and win-loss

Read deal-context.json first if it exists.

Battle card

  1. Gather. Internal first: search the notes, docs and transcripts the user points to for the competitor name. Then public: the competitor's site, pricing page, release notes, review sites. Record each finding with its source.
  2. Fill the card using references/battle-card-template.md:
    • The 10-second take
    • Why we win (with proof) and why we lose (honest)
    • Feature and approach comparison, scored ahead, even or behind
    • Pricing and packaging differences (public facts only)
    • Objections they plant and our replies
    • Trap questions the buyer can ask the competitor
    • Proof points: customer stories and numbers we can cite
  3. Tailor to the persona and industry in deal-context.json when present.
  4. Render as HTML (visual first: a score strip, colour-coded comparison, tap to expand for detail) plus a markdown copy. Put Sources and Last updated in the footer.
  5. Check: every claim has a source, nothing says the competitor "can't" without a cited reason, and there are no em-dashes or semicolons.

Win-loss

python3 scripts/winloss.py deals.csv -o out/winloss.md

CSV columns (any extra columns are used as factors): deal_id, outcome (won|lost|no_decision), amount, segment, competitor, lane, cycle_days, demo_done, poc_done, se_hours, loss_reason.

It reports win rate overall and by each factor, the factors that move win rate most (lift vs baseline, with sample size), top loss reasons, and 3 to 5 leading signals. Groups under 5 deals are marked low sample. Wording is "linked with", never "causes" or "predicts".

Then write 3 actions: what to change in battle cards, proposals and qualification. If the two-lane pilot is running, compare lane 1 and lane 2 outcomes.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free