harness · market
Harness
Put raw intelligence to work.
Skills, MCP servers, prompts, assistants and connectors. Every listing shows its author, version and the permissions it needs.
On the shelves21,000
- MCP servers18,849
- Skills1,282
- Assistants651
- Prompts218
0 items
Notes and knowledgeSpecialist assistants, also called subagents. Installed in Claude Code, Codex and the like, they take on the work their main session hands them.
- Spinning Up in Deep RLalirezarezvani· spinning-up-deep-rl 28kAnswers from the knowledge base compiled from Spinning Up in Deep RL by Joshua Achiam (OpenAI). Loads the master frameworks first and reads a single chapter file on demand rather than the whole source. Refuses to answer beyond what the source covers.Opus1 skillNotes and knowledgeAI models
- Wiki linteralirezarezvani 28kDispatched sub-agent that runs a periodic health check on an LLM Wiki vault. Runs mechanical checks via scripts (orphans, broken links, stale pages, missing frontmatter, duplicate titles, log gaps), does semantic checks (contradictions, stale claims, cross-reference gaps, concepts missing their own page), and produces a markdown report with suggested actions. Spawn weekly, after batch ingests, or when the user says "check the wiki" / "lint my wiki" / "audit the vault".Opus1 skillDocumentsNotes and knowledgeHealth
- Book Co-Authormsitarzewski 158kStrategic thought-leadership book collaborator for founders, experts, and operators turning voice notes, fragments, and positioning into structured first-person chapters.Notes and knowledgeAudio and speech
- Deep Learning Tutoralirezarezvani· deep-learning-book 28kStudy companion for the Deep Learning textbook (Goodfellow, Bengio & Courville, 2016). Plans a prerequisite-closed reading path, answers chapter questions from the compiled knowledge base, diagnoses training runs against Chapter 11's decision tree, and flags every place the 2016 text has been superseded. Use for studying the book, teaching from it, or checking whether one of its recommendations is still current.Notes and knowledgeEducation
- Project Manageralirezarezvani 28kProject Manager agent for sprint planning, Jira/Confluence workflows, Scrum ceremonies, and stakeholder reporting. Orchestrates project-management skills. Use when running delivery operations — e.g., planning a sprint with capacity and carry-over math in Jira, or assembling a portfolio health report for stakeholders from ticket and velocity data.Sonnet1 skillNotes and knowledgeProject managementHealth
- ZK Stewardmsitarzewski 158kKnowledge-base steward in the spirit of Niklas Luhmann's Zettelkasten. Default perspective: Luhmann; switches to domain experts (Feynman, Munger, Ogilvy, etc.) by task. Enforces atomic notes, connectivity, and validation loops. Use for knowledge-base building, note linking, complex task breakdown, and cross-domain decision support.Notes and knowledge
- Meeting Notes Specialistmsitarzewski 158kExtract structured decisions, action items, and open questions from meeting transcripts or rough notes into a clean 4-section summary.Notes and knowledge
- Wiki librarianalirezarezvani· llm-wiki 28kDispatched sub-agent that answers queries against an LLM Wiki vault. Reads index.md first, drills into 3-10 relevant pages across categories, synthesizes an answer with inline [[wikilink]] citations, and offers to file the answer back into the wiki as a new comparison or synthesis page. Spawn when the user asks a substantive question the wiki might answer, says "what does the wiki say about X", "compare A and B across my sources", or wants to explore a topic.Sonnet1 skillNotes and knowledgeAI models
- Wiki linteralirezarezvani· llm-wiki 28kDispatched sub-agent that runs a periodic health check on an LLM Wiki vault. Runs mechanical checks via scripts (orphans, broken links, stale pages, missing frontmatter, duplicate titles, log gaps), does semantic checks (contradictions, stale claims, cross-reference gaps, concepts missing their own page), and produces a markdown report with suggested actions. Spawn weekly, after batch ingests, or when the user says "check the wiki" / "lint my wiki" / "audit the vault".Opus1 skillDocumentsNotes and knowledgeHealth
- Product Manageralirezarezvani 28kProduct management agent for feature prioritization, customer discovery, PRD development, and roadmap planning using RICE framework. Use when a product decision needs structure and evidence — e.g., RICE-scoring a backlog of 20 feature requests before quarterly planning, or drafting a PRD from raw customer-interview notes.Sonnet8 skillsNotes and knowledge
- Wiki ingestoralirezarezvani· llm-wiki 28kDispatched sub-agent that ingests a new source into an LLM Wiki vault. Reads the source, proposes TL;DR and key claims, identifies which entity/concept/synthesis pages will be touched, flags contradictions with existing pages, and — after user confirmation — writes the source summary, updates cross-references across 5-15 pages, regenerates the index, and appends a standardized log entry. Spawn when the user says "ingest this", "add this paper/article/book to the wiki", or drops a file into raw/.Opus1 skillNotes and knowledgeAI models
- Wiki librarianalirezarezvani 28kDispatched sub-agent that answers queries against an LLM Wiki vault. Reads index.md first, drills into 3-10 relevant pages across categories, synthesizes an answer with inline [[wikilink]] citations, and offers to file the answer back into the wiki as a new comparison or synthesis page. Spawn when the user asks a substantive question the wiki might answer, says "what does the wiki say about X", "compare A and B across my sources", or wants to explore a topic.Sonnet1 skillNotes and knowledgeAI models
- Wiki ingestoralirezarezvani 28kDispatched sub-agent that ingests a new source into an LLM Wiki vault. Reads the source, proposes TL;DR and key claims, identifies which entity/concept/synthesis pages will be touched, flags contradictions with existing pages, and — after user confirmation — writes the source summary, updates cross-references across 5-15 pages, regenerates the index, and appends a standardized log entry. Spawn when the user says "ingest this", "add this paper/article/book to the wiki", or drops a file into raw/.Opus1 skillNotes and knowledgeAI models
- PM Orchestratoralirezarezvani· project-management 28kFlow-first delivery lead. Routes project-management inquiries (sprint/velocity, portfolio health, Jira/JQL, Confluence, Atlassian admin, templates, meetings, comms) to the right sub-skill via the pm-skills orchestrator, and drives delivery goals through bounded agentic loops with machine-checkable gates. Forks context to keep heavy intake (Jira snapshots, retro logs, transcripts) out of the parent thread. Signature forcing question — "What single observable outcome means DONE, and which command proves it?"SonnetNotes and knowledgeProject managementHealth
- Company Architectalirezarezvani· arquiteto-de-empresa 28kCompany Architect — a senior chief of staff who builds a business from scratch as an OKF (Open Knowledge Format) bundle: a tree of version-controllable .md files with frontmatter type, links forming a graph, and reserved index.md/log.md. Guides the founder through a 12-phase interview (foundation, strategy, market, financial, sales, marketing, product, operations, tech, people, legal, governance), one phase at a time, at most 3-5 questions per block, confirming before generating each concept. Trigger when the user wants to create, structure, or document an entire company as folders and markdown files, or mentions company as code, company knowledge base for AI, OKF, or knowledge bundle. Works in English. Never dumps the company all at once — it interviews, validates, and builds phase by phase.Opus1 skillFilesDocumentsNotes and knowledge
- Meeting Discipline Agentalirezarezvani· meetings 28kEnforces personal meeting hygiene end to end. Before a meeting it runs the cost gate (attendees x minutes x rate, optionally + 23-minute refocus overhead per attendee) and refuses to schedule anything without a decision, an agenda, and a named owner — verdict is ASYNC / NOT-READY / MEET, never a shrug. If the meeting survives, it builds a timeboxed, decision-first agenda where every topic has a desired outcome. After the meeting it extracts action items from raw notes into an owner + due-date checklist and flags every ORPHAN and NO-DUE item. Use before calling a meeting or after one ends with messy notes.Opus1 skillNotes and knowledge