running-a-proof-of-concept
Phase 3 (Proof of Concept) deep-dive playbook — validates the Research recommendation in real Bitwarden code and drafts the ADR.
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-22 00:14
13,929 results
Phase 3 (Proof of Concept) deep-dive playbook — validates the Research recommendation in real Bitwarden code and drafts the ADR.
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched,…
Research a factual, codebase, product, or external-documentation question using primary sources and return an evidence-backed answer. Use when the user asks to…
JSDoc - documentation generator for JavaScript with type annotations. USE WHEN: user mentions "JSDoc", "JavaScript documentation", asks about "documenting…
Draft a lawyer's letter from a completed engagement registration — pass through the confidentiality/admission risk/settlement negotiation posture checklist gates, output .docx, attach a post-sending checklist, and provide the option to create a case. Use when the user says "draft a lawyer's letter", "write a [type] letter", or when a completed engagement registration is ready to be converted into a sendable draft.
Apply this skill to EVERY response, in every conversation, on every surface, regardless of topic — writing, research, analysis, planning, casual chat, and…
Use this skill to understand the Shipshape workflow, shared Articles of Agreement, and select the correct role skill: /captain, /qm, /crew, /boatswain, or…
Create concise executive summaries and TL;DR versions of long documents
Conduct qualitative user research, synthesize insights, and inform product decisions through interviews, usability testing, and behavioral analysis
Scrape competitor ads from Google Ads by domain. Returns ad creatives, formats, and campaign details. Use for competitive ad research and messaging analysis.
Find Key Opinion Leaders (KOLs) in a given domain by combining web research with LinkedIn post search. Given a company/idea and target domain, generates…
Research competitors, analyze their messaging, and generate a positioning document with category definition, differentiation claims, value propositions, and…
A skill that applies writing norms when having a generative AI create or polish Japanese technical documents (book chapters, articles, explanations). It generates logical and honest Japanese technical writing, and suppresses LLM-specific empty phrasing, verbosity, excessive dramatization, and AI-smelling vocabulary. It can also score documents before publication. Triggers: Japanese technical documents, technical writing, …
Use when mentioning Hundun courses, course learning, methodologies, mental models, course search, or course transcript distillation; use when distilling value points/generating creative ideas/summarizing selling points/product & service pricing/uncovering entrepreneurial opportunities; use when asked general business decision-making questions.
Establishes or updates the repo-level documentation layer — docs/product/vision.md, docs/architecture/ invariants, and docs/product/guidelines.md. Run it with…
Record architecture decisions with ADRs — captures why, alternatives considered, and consequences
Brainstorm a research idea and decide what a new paper should cover — generate candidate framings, pick the central contribution, and draw the in-scope vs.…
Use when: you need continuous competitor tracking, competitor intelligence alerts, regular competitor monitoring monthly reports, and tracking competitor version/pricing/feature/public sentiment/funding changes Do NOT use when: only a one-time competitor study is needed (use pm-market / pm-search --type=competitor); the product has no clear competitors yet
Conduct structured literature reviews, compile chronologies of research development, and identify research gaps on specific topics.
Light Research Integrity and Ethics Full-Lifecycle Standing Red-Line Gate: across research triage, approval, collection, changes, analysis, submission, publication, and post-publication checks, it addresses risks such as academic misconduct/data fabrication/statistical consistency/exaggerated conclusions/hallucinations and retractions, citation/self-plagiarism/privacy/copyright/authorship and AI disclosure/software copyright and patent ownership/paper mill rewriting, turning "don't fabricate, don't exaggerate" from verbal advice into **machine-checkable, blockable, and master-control...
Find content topics and prioritize them without expensive SEO tools. Use when planning a content strategy, deciding what to write about, or doing keyword…
arc42 architecture documentation template and guidance
Makelog integration. Manage data, records, and automate workflows. Use when the user wants to interact with Makelog data.
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as…