tactic-extraction
Skill0 starsChanged 4 months agoMITView on GitHub
Read a long video or podcast transcript and extract the named, specific tactics worth keeping — not the stories and filler around them. Processing a YouTube transcript, a podcast, or a long talk into something useful. When the owner wants the moves, not a book report.
In this repository29 other files it gives its agents.
- devils-advocate-first-passSkill
- load-bearing-assumptionSkill
- pre-mortemSkill
- reversibility-checkSkill
- three-option-framingSkill
- boundary-setting-declineSkill
- cold-intro-structureSkill
- customer-reply-tone-matchSkill
- quote-follow-upSkill
- subject-line-not-filteredSkill
- end-of-day-reflectionSkill
- inbox-triageSkill
- project-scaffoldingSkill
- quote-drafting-from-notesSkill
- vendor-invoice-categorizationSkill
- competitor-pricing-extractSkill
- customer-voice-extractSkill
- source-verificationSkill
- vertical-landscape-scanSkill
- discovery-call-note-captureSkill
- lead-qualificationSkill
- objection-handlingSkill
- proposal-drafting-frameworkSkill
- stack-the-deck-closeSkill
- dont-be-a-chatbotSkill
- honest-hedgingSkill
- lead-with-the-actionSkill
- specific-over-genericSkill
- write-like-the-userSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 22
Keep it concrete enough to act on.
- Distinctive: line 30
Don't: Write "He talked about the importance of optimizing your sales funnel and providing massive value to your audience" — a summary of …
≈ “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.
Files
Pull the Plays, Skip the Fluff
Most of a talk is throat-clearing and stories. The value is the handful of specific, repeatable plays. Pull those — named, concrete, actionable — and drop the rest.
The technique
- Hunt for the specific move: a number, a sequence, a rule, a script. "Default to the highest package" is a play; "always provide value" is filler.
- Skip the stories unless the story IS the tactic. A war story that demonstrates a repeatable move is worth keeping; one that's just a flex isn't.
- Keep it concrete enough to act on. If you can't picture doing it tomorrow, it's not a tactic, it's a vibe.
- Name each play in a few words so it's findable later — that's how it becomes reusable instead of lost in a transcript.
- Note who said it and where, so the owner can go back to the source if a play pays off.
Do this, not that
Do: "Play: on the order form, default-select the highest-margin package and let buyers downsize — most stay on the default, turning a 1-unit sale into 3. (Brunson, on order-form design.)"
Don't: Write "He talked about the importance of optimizing your sales funnel and providing massive value to your audience" — a summary of nothing the owner can actually do.
Why this works
A 60-minute talk has maybe five minutes of plays you can run. The rest is rapport, repetition, and stories. Extracting the named, concrete tactics turns hours of content into a short list the owner can act on this week — and naming each one makes it a reusable move instead of a half-remembered idea that evaporates by Friday.
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
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.

