marks97
7 skills with substantive source documentation and an official publisher or observed installation demand. Read each skill’s original documentation through its card.
marks97meeting-brief
Transcribe meeting or call recordings, archive them under the project's arch/ folder, and brief you back as a spoken audio link instead of a wall of text. Use this whenever you point at audio or video recordings and want them transcribed, summarised, "read", or turned into a meeting report, and whenever you ask for a briefing, recap, or rundown of a call. Also use it for the audio-reply mode on its own ("send it as audio", "give me a link", "voice mode", "audio only", "1.5 velocity", "just talk
- installations
- 3
- GitHub Stars
- 0
- Mis à jour
- 1 oct.
marks97task-estimator
Estimate how long a coding task will take, using the user's own measured history instead of intuition. Use this skill whenever someone asks for an estimate, an ETA, a timeline or a deadline for a feature, bug, refactor, migration, script or investigation — "how long will this take", "give me an estimate", "how many hours is this", "can this ship today", "is this a one-day job", "how many days for the whole epic", "what should I tell the client", "estimate this ticket", "size this" — and equally
- installations
- 2
- GitHub Stars
- 0
- Mis à jour
- 1 oct.
marks97work-hours
Measure how many hours a person really works per day, per client or project, and at what clock times, from the digital exhaust they already leave — Claude Code transcripts, Slack, WhatsApp, meeting recordings, laptop screen time, browser history and chess games — with leisure subtracted and the idle threshold calibrated against their own stated breaks. Use it whenever someone asks "how many hours do I actually work", "how much time do I spend on client X vs Y", "what are my working hours / routi
- installations
- 2
- GitHub Stars
- 0
- Mis à jour
- 9 oct.
marks97youtube-transcribe
Absorb the knowledge in YouTube videos — find them, transcribe them with ElevenLabs Scribe v2, inspect their visuals, and digest what they actually teach. Use this whenever someone wants a video's content as text or knowledge rather than just a link — "transcribe this YouTube video", "what does this video say", "summarize/explain this talk", "pull the transcript", "get subtitles", "turn this lecture into notes", or research-style asks like "find 10-20 videos about and tell me everything", "resea
- installations
- 2
- GitHub Stars
- 0
- Mis à jour
- 8 oct.
marks97bug-iterate
Iterates one-by-one through a multi-bug report with a hard confirmation gate before any code touches disk. Use this skill when the user has a report of 2+ bugs and wants to work through them sequentially. Trigger phrases: "let's tackle these", "let's iterate", "go one by one", "loop through the findings", "work through the bugs", "bug iteration", or any time the user presents a numbered list of bugs and signals they want to resolve them in order. Do NOT trigger for a single bug (just investigate
- installations
- 1
- GitHub Stars
- 0
- Mis à jour
- 1 oct.
marks97compact-handoff
Compact the current conversation into a large standalone handoff file on disk, then open a BRAND NEW Claude Code session named after the current chat with an incremented counter, seeded with only a pointer to that file, leaving the current chat fully intact. Use this whenever the user wants a clean context window without losing what was learned, or says any of — "compact to a new chat", "compact but start fresh", "carry this over to a new session", "hand this off", "new chat with this context",
- installations
- 1
- GitHub Stars
- 0
- Mis à jour
- 1 oct.
marks97runpod-vllm-claude-code
Deploy any HuggingFace model to RunPod as a vLLM server, bridge it to Claude Code (which speaks Anthropic's Messages API, not OpenAI's), smoke-test that tool-calling actually works end to end, and tear everything down with zero trace (pod, network volumes, local processes, scratch files). Use this whenever you want to run a model on RunPod, try a model with Claude Code, test whether a HF/GGUF/abliterated checkpoint supports tool use, benchmark a model for coding-agent use, or spin up/kill a disp
- installations
- 1
- GitHub Stars
- 0
- Mis à jour
- 1 oct.