present
Skill0 starsChanged 4 months agoMITView on GitHub
Use when Gera asks to prep a presentation, build a talk or deck, turn a wiki page or topic into slides, prepare speaker content, or "help me present X to coworkers / the team". Renders a polished, self-contained HTML presentation artifact from a wiki page or topic, following Servy's HTML-as-LLM-output doctrine.
12 other projects use a version of this.
Adopted by
Most recently taken up by
- pietz/skillstheir own version, first seen Nov 8, 2026
- StasPotapov/presenttheir own version, first seen Nov 3, 2026
- grainulation/grainulatortheir own version, first seen Nov 3, 2026
- sassarini-marco/track-to-demotheir own version, first seen Nov 1, 2026
- qwwiwi/agentos-skills-publictheir own version, first seen Nov 1, 2026
- bisque-cloud/presentertheir own version, first seen Oct 25, 2026
Used with
Projects with it also use tdd.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
GoogleSkilltdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
Also in 3 projects that use this
Other versions12 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 12
- glebis/claude-skills★ 410same name
- grainulation/grainulator★ 86same name
- bisque-cloud/presenter★ 40same name
- StasPotapov/present★ 16same name
- qwwiwi/agentos-skills-public★ 4same name
- michaelengland/deckwright★ 2same name
- NguyenHuy190303/EEP★ 2same name
- pietz/skills★ 2same name
- godmarch33/power-presentation★ 1same name
- OHOKAYYEAH/claude-skills★ 1same name
2 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository50 other files it gives its agents.
- aegisSkill
- agent-builderSkill
- agents-team-builderSkill
- ai-applySkill
- auditSkill
- bottleneckSkill
- buildSkill
- capability-radarSkill
- clay-leadsSkill
- cowatchSkill
- deepforkSkill
- design-blueprintSkill
- evalSkill
- fable-modeSkill
- financesSkill
- forgeSkill
- framework-builderSkill
- grill-meSkill
- hooks-builderSkill
- level-upSkill
- loops-builderSkill
- meeting-hudSkill
- multi-brainSkill
- nate-watchSkill
- onboardSkill
- plugin-builderSkill
- ponytailSkill
- prompt-evalSkill
- radar-harvestSkill
- rag-forgeSkill
- rlsgateSkill
- rnd-loopSkill
- rndSkill
- roastSkill
- routines-builderSkill
- servy-routineSkill
- session-handoffSkill
- skill-builderSkill
- skill-harvestSkill
- sparkSkill
- storm-researchSkill
- studySkill
- talkSkill
- taste-skillSkill
- verify-loopSkill
- verify-specificsSkill
- wheel-of-lifeSkill
- workanaSkill
- workaround-builderSkill
- workflow-builderSkill
The file
Files
What This Skill Does
Takes a wiki page or topic and produces a polished HTML presentation artifact Gera can present to coworkers. Serves quarter priority #5 (build a speaker profile) and activates the HTML-as-LLM-output doctrine adopted 2026-05-31 — turning "structure your response as HTML" from a trigger phrase into a repeatable speaker-prep workflow.
This has a side effect (writes an artifact file), so it is manual-invoke only (/present).
Context to Load
references/html-as-llm-output.md— the rubric for when/how to render HTML (self-contained, polished, scannable, shareable). The output must honor this doctrine.- The source: a named wiki page in
references/, or — if Gera names a topic — readreferences/index.mdand pull the matching page(s). If he pastes raw content, use that. references/voice.md— for any speaker notes or spoken-script text written in Gera's voice.- The frontend-design skill — invoke it to do the actual visual build so the deck avoids generic AI aesthetics.
Steps
- Resolve the source. Named wiki page → read it. Topic → search
references/index.md, read the best-matching page(s), confirm the pick in one line. Pasted content → use directly. - Clarify only what you can't infer (one short round, skip what's obvious): audience (default: SoftServe coworkers / internal talk), length (default: a tight 5–8 slide deck), and the angle/takeaway. If Gera gave a topic with enough framing, skip this.
- Outline the talk: hook → 3–5 key points → one takeaway. Show the outline in chat in 4–6 lines and let him nudge it before rendering. (Skip the pause if he said "just build it".)
- Render an HTML slide deck via the frontend-design skill, following
html-as-llm-output.md: one self-contained.htmlfile, inline CSS/JS, keyboard-navigable slides, scannable, no external dependencies. Cite the source wiki page(s) on a closing slide. - Save to
artifacts/presentations/<today>-<slug>.htmland open it. Report the path.
Output
- An HTML presentation in
artifacts/presentations/<today>-<slug>.html(tracked in git, private repo). - A one-line chat summary with the path and the slide count.
Notes / Guardrails
- Voice rule: speaker notes / spoken script in Gera's voice (
voice.md). But don't finalize external-facing content (anything leaving SoftServe, or a named client deck) without showing Gera a draft first — same rule as LinkedIn/email. - Cite sources. A talk built from the wiki should name the wiki page(s) it drew from.
- Don't fabricate data, quotes, or claims to fill a slide. If the source page doesn't support a point, drop the point or flag the gap.
- Naming:
artifacts/presentations/<date>-<slug>.html(date = today, ISO). One topic per file. - This is for Gera's own presentations. For a finished client/pitch deck or brand-from-zero work, the heavier tool is Claude Design (
references/claude-design.md) — mention it if the ask outgrows a wiki-page talk.
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.

