Agent skill

Pitch Vs Teach

by mohitagw15856 in mohitagw15856/pm-claude-skills

Know which talk you're giving — the pitch (drive one decision) vs.

MITAuto-check passed

Install Pitch Vs Teach

skills CLI
$ npx skills add mohitagw15856/pm-claude-skills --skill pitch-vs-teach -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mohitagw15856/pm-claude-skills pitch-vs-teach --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/pitch-vs-teach .claude/skills/pitch-vs-teach && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
pitch-vs-teach
GitHub stars
1.4k
Token cost
~1.5k tokens
SKILL.md length
760 words
Files
1
Skills in repo
1,348
Repo updated
First seen
Licence
MIT

At a glance

Know which talk you're giving — the pitch (drive one decision) vs.

  • Works in 5 steps: The success question diagnoses: what… → Pitch structure is asymmetric on… → Teach structure is layered and redundant… → …
  • Asked is this a pitch
  • SKILL.md covers What This Skill Produces, Required Inputs, Framework: The Mode Rules and Output Format, plus 7 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Pitch Vs Teach is an agent skill from mohitagw15856/pm-claude-skills. Know which talk you're giving — the pitch (drive one decision) vs. the teach (build understanding) — because mixing their structures fails both, and most bad presentations are one wearing the other's clothes. Use when asked is this a pitch or a training, my informative deck didn't land the ask, my pitch felt like a lecture, or structure this talk for the right job. Produces the mode diagnosis, the structural implications, the mixed-mandate split, and the mode-check on an existing deck.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.

When your agent uses it

  • Asked is this a pitch
  • My informative deck didnt land the ask
  • My pitch felt like a lecture
  • Structure this talk for the right job

Example prompts

  • “/pitch-vs-teach”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. The success question diagnoses: what happens after, if it works? — one question, asked before any slide exists. "They approve the budget"…
  2. Pitch structure is asymmetric on purpose: tension early (deck-narrative-arc), the answer fast (exec-vs-working-deck), evidence chosen not…
  3. Teach structure is layered and redundant on purpose: foundation before detail, each layer resting on the last, worked examples (the…
  4. The tells of mode confusion: an "informative" deck whose author is frustrated nobody decided → a pitch in denial (the ask was never…
  5. Mixed mandates split, in order: teach-then-pitch when the decision needs understanding ("here's how the system works — 15 min — now here's…

What it can do on your machine

Read from SKILL.md and the folder at commit 1cbf1f0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Pitch Vs Teach loads about 1.5k tokens when it runs. Until then it costs about 126 tokens; SKILL.md has 760 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~126
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 760 words, ~1,484 tokens.

Download SKILL.mdSave it as .claude/skills/pitch-vs-teach/SKILL.md (or your agent's skills folder).
name
pitch-vs-teach
description
Know which talk you're giving — the pitch (drive one decision) vs. the teach (build understanding) — because mixing their structures fails both, and most bad presentations are one wearing the other's clothes. Use when asked is this a pitch or a training, my informative deck didn't land the ask, my pitch felt like a lecture, or structure this talk for the right job. Produces the mode diagnosis, the structural implications, the mixed-mandate split, and the mode-check on an existing deck.

Pitch Vs Teach Skill

Two fundamentally different talks share the same slideware: the pitch exists to drive one decision (structure: tension → answer → evidence → ask; success: the yes) and the teach exists to build durable understanding (structure: foundation → layers → examples → practice; success: they can use it Tuesday). Most presentation failures are mode confusion — the pitch built like a lecture (comprehensive, balanced, ask-less: the room learned a lot and decided nothing) or the training built like a pitch (persuasive, thin, one-sided: the room was convinced but can't operate it). The diagnosis takes one question; the structures then diverge completely.

What This Skill Produces

  • The mode diagnosis — pitch, teach, or genuinely-both (which means two segments, not a blend), from the success-question
  • The structural implications — what the diagnosed mode demands: sequence, density, evidence style, the ending
  • The mode-check — an existing deck audited for mode confusion, with the tells cited
  • The split design — for mixed mandates: the teach-then-pitch sequence with the seam handled

Required Inputs

Ask for these if not provided:

  • The success question — "if this goes perfectly, what happens afterward?" A decision made → pitch. People operating differently → teach. Both answers → the split, and the order matters
  • The audience's starting state — a pitch to people who don't understand the domain needs a teaching segment (not a teaching structure); a training to skeptics needs a pitch opening (why learn this)
  • The existing deck, if any — mode-checks work on real slides, and the tells are findable
  • The time slot — teaches need more time than pitches; a 15-minute slot can pitch or orient, never train

Framework: The Mode Rules

  1. The success question diagnoses: what happens after, if it works? — one question, asked before any slide exists. "They approve the budget" and "they can run the process" produce different talks from the same material, and the diagnosis is the fork everything else follows (deck-outline-first headers should carry the mode).
  2. Pitch structure is asymmetric on purpose: tension early (deck-narrative-arc), the answer fast (exec-vs-working-deck), evidence chosen not comprehensive, risks conceded strategically (proposal-skeleton), and the ask closes. Balance is the pitch's enemy dressed as virtue — a pitch that "presents all sides equally" has delegated its job to the room.
  3. Teach structure is layered and redundant on purpose: foundation before detail, each layer resting on the last, worked examples (the handbook-page example logic — examples teach what assertions can't), deliberate repetition (the pitch's sin is the teach's method), and it ends in practice or application, not an ask. Persuasion energy in a teach reads as agenda and undermines the trust teaching needs.
  4. The tells of mode confusion: an "informative" deck whose author is frustrated nobody decided → a pitch in denial (the ask was never written). A pitch running 40 comprehensive slides → a teach costume (the decision drowned in curriculum). Q&A asking "so what do you want from us?" → mode failure, diagnosed live by the room.
  5. Mixed mandates split, in order: teach-then-pitch when the decision needs understanding ("here's how the system works — 15 min — now here's the change we propose — 10 min"), with the seam announced ("that's the background; now the recommendation") — because audiences process the two modes with different postures, and the announcement lets them switch. Blended modes make the teaching feel slanted and the pitch feel padded.
Show full SKILL.md (221 more words)Show less

Output Format

Mode Diagnosis: [talk] — verdict: [pitch / teach / split]

The Success Question

[The after-state, in their words → the diagnosis]

Structural Implications

[The diagnosed mode's sequence, density, evidence style, and ending — as build instructions]

Mode-Check (existing deck)

[The tells found: slides cited · the confusion's cost · the restructure direction]

The Split (if both)

[Teach segment (scope, minutes) → the announced seam → pitch segment (tension, ask) · which comes first and why]

Quality Checks

  • The success question was answered before structure was touched
  • Pitch verdicts produce an ask; teach verdicts produce practice/application
  • Mode-confusion tells are cited from actual slides
  • Splits are sequenced segments with an announced seam, never a blend
  • The time slot supports the diagnosed mode's real needs

Anti-Patterns

  • Do not build "informative" pitches — a pitch without an ask is a lecture with an agenda
  • Do not persuade in a training — advocacy energy poisons the trust that teaching runs on
  • Do not balance a pitch into neutrality — the risks slide is where balance lives; the thesis is not
  • Do not blend mixed mandates — split, sequence, announce the seam
  • Do not let the room diagnose the mode in Q&A — "what do you want from us?" is the autopsy question

Example Trigger Phrases

  • "Is this a pitch?"
  • "My informative deck didn't land the ask."
  • "My pitch felt like a lecture."
  • "Structure this talk for the right job."

© mohitagw15856, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/pitch-vs-teach of mohitagw15856/pm-claude-skills.

Open the folder on GitHubat commit 1cbf1f0

Compare with similar skills

Pitch Vs Teach next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Pitch Vs Teach compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pitch Vs Teach this skillmohitagw15856/pm-claude-skills1.4k—~1.5kAutomated safety check: PassMIT
Ib Pitch Booknexu-io/open-design100k—~2kAutomated safety check: PassApache-2.0
HTML Ppt Pitch Decknexu-io/open-design100k—~1.3kAutomated safety check: PassApache-2.0
Teachcursor/plugins11k9 repos~1.4kAutomated safety check: PassNone
Feishu Driveopenclaw/openclaw392k—~375Automated safety check: PassMIT
Conference Talk Slides from PapersOrchestra-Research/AI-Research-SKILLs13k—~2.5kAutomated safety check: PassMIT

Similar skills

  • Ib Pitch Book

    nexu-io/open-design

    OpenDesign's investor pitch book: market map, moat, unit economics, and the ask — analyst-grade and diligence-ready.

    100k GitHub stars~2k tokensUpdated yesterday
    Business, Finance & HRAuto-check passed
  • HTML Ppt Pitch Deck

    nexu-io/open-design

    OpenDesign's demo-day pitch: hook, traction, moat, and the raise — built to make a partner sit up by page three.

    100k GitHub stars~1.3k tokensUpdated yesterday
    Business, Finance & HRAuto-check passed
  • Teach

    cursor/plugins

    Official

    Explain a body of work plainly so a person actually understands it.

    11k GitHub starsUsed in 9 repos~1.4k tokens
    EducationAuto-check passed
  • Feishu Drive

    openclaw/openclaw

    Feishu cloud-storage and comment workflows. An agent skill from openclaw/openclaw.

    392k GitHub stars~375 tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Conference Talk Slides from Papers

    Orchestra-Research/AI-Research-SKILLs

    Generates Beamer LaTeX PDF and editable PPTX slides from a compiled paper, with speaker notes and an optional talk script, sized to four talk lengths.

    13k GitHub stars~2.5k tokensUpdated 3 mo ago
    Documents & OfficeAuto-check passed
  • Crossframe Teach

    sickn33/agentic-awesome-skills

    A skill your agent uses when CrossFrame Suite routes explicit Chinese teaching of CrossFrame concepts, misreading boundaries, plain-language examples, signals, or exercises.

    47k GitHub starsUsed in 1 repo~943 tokens
    Writing & ContentAuto-check passed

More from mohitagw15856/pm-claude-skills

All 1,348 skills in this repo
  • Car Tco

    mohitagw15856/pm-claude-skills

    Compare the total cost of car ownership across buy-new, buy-used, lease, and keep-your-current-car — depreciation, insurance, maintenance ramp, and fuel over a real horizon, not just the monthly…

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Cs Health Scorecard

    mohitagw15856/pm-claude-skills

    Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.

    1.4k GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed
  • Exit Waterfall

    mohitagw15856/pm-claude-skills

    Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Feature Prioritisation

    mohitagw15856/pm-claude-skills

    Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.

    1.4k GitHub stars~2k tokensUpdated yesterday
    Auto-check passed
  • Fire Number

    mohitagw15856/pm-claude-skills

    Compute a financial-independence (FIRE) target and years-to-reach with every assumption labeled as an assumption — plus a sensitivity table instead of a single false-precision answer.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Freelance Rate

    mohitagw15856/pm-claude-skills

    Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.

    1.4k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

Questions about Pitch Vs Teach

What does Pitch Vs Teach do?

Know which talk you're giving — the pitch (drive one decision) vs. Pitch Vs Teach is an agent skill from mohitagw15856/pm-claude-skills. Know which talk you're giving — the pitch (drive one decision) vs.

When should I use Pitch Vs Teach?

Pitch Vs Teach fits situations like: asked is this a pitch; my informative deck didnt land the ask; my pitch felt like a lecture; structure this talk for the right job.

How do I install Pitch Vs Teach in Claude Code?

Run `npx skills add mohitagw15856/pm-claude-skills --skill pitch-vs-teach -a claude-code`. Or copy the skill folder (skills/pitch-vs-teach in mohitagw15856/pm-claude-skills) into .claude/skills/pitch-vs-teach in your project. Claude Code loads it when a task matches its description.

How do I install Pitch Vs Teach in Codex?

Run `npx skills add mohitagw15856/pm-claude-skills --skill pitch-vs-teach -a codex`. Or copy the skill folder (skills/pitch-vs-teach in mohitagw15856/pm-claude-skills) into .agents/skills/pitch-vs-teach in your project. Codex loads it when a task matches its description.

Can I use Pitch Vs Teach in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mohitagw15856/pm-claude-skills --skill pitch-vs-teach -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pitch-vs-teach, .gemini/skills/pitch-vs-teach, .github/skills/pitch-vs-teach and .opencode/skills/pitch-vs-teach in your project.

What does Pitch Vs Teach need to run?

SKILL.md names no scripts, command-line tools or credentials: Pitch Vs Teach is instructions for the agent only.

Does Pitch Vs Teach access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Pitch Vs Teach safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Pitch Vs Teach use?

Pitch Vs Teach is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Pitch Vs Teach use?

About 1.5k tokens (SKILL.md is roughly 5.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Pitch Vs Teach?

Skills that share tags, products or a category with Pitch Vs Teach: Ib Pitch Book (nexu-io/open-design, 100k stars), HTML Ppt Pitch Deck (nexu-io/open-design, 100k stars), Teach (cursor/plugins, 11k stars) and Feishu Drive (openclaw/openclaw, 392k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pitch Vs Teach?

mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,434 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 9, 2026.

Source: mohitagw15856/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.