Menu
SkillsMP a collecté 16 skills depuis jon-devlapaz/socratink. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 16 skills collectés sur 16.
Catch Socratink Brain live-implementation (CURRENT STATE, Active notes, live-repo SRC) up to the sibling product repository HEAD. Use when tandem is mismatch, after a product land, or when the user asks to update Brain to socratink, pin CURRENT STATE, or sync…
Langue du texte source : anglais
Interface safely with the Socratink Brain from the Socratink application repo: orient ontology to the live codebase, retrieve task-scoped canon, trace provenance, mine conversation/experiment histories into Learning Events, reconcile new evidence, and…
Langue du texte source : anglais
Audit Socratink idea-to-PR work that moved the learner-facing product needle. Mines Socratink chat snapshots and product git/PRs for real wins and failures, then names skills, tools, and harnesses to reuse. Use when the user is tired of back-and-forth, asks…
Langue du texte source : anglais
Apply a Martin Fowler-derived perspective to software architecture, refactoring, delivery, technical leadership, or AI-assisted development. Use only when the user explicitly asks for Martin Fowler's perspective, asks "what would Fowler think?", requests a…
Langue du texte source : anglais
Apply an evidence-grounded simulation of Steve Jobs's public product reasoning to product taste, artifact reviews, portfolio focus, platform boundaries, pivots, and creative-team decisions. Built from 92 distinct public URLs and distills 5 mental models and 7…
Langue du texte source : anglais
Design engineering principles for making interfaces feel polished. Use when building UI components, implementing animations or hover states, or doing any visual detail work. Triggers on UI polish, "feels off", stagger animations, enter animations, theme…
Langue du texte source : anglais
Puts real design variations of one project file on the user's own localhost, behind a small card that flips them with the arrow keys, then keeps listening for their verdict. Use when the user wants design variations, alternatives, or directions to choose…
Langue du texte source : anglais
An evidence-grounded Andrej Karpathy perspective for technical reasoning, product and research decisions, learning strategy, AI engineering, and evaluating agent autonomy. Built from 92 distinct public URLs across first-party writing, interviews, talks,…
Langue du texte source : anglais
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews…
Langue du texte source : anglais
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
Langue du texte source : anglais
Locate and read the generated Braintrust Obsidian vault when work needs documented Braintrust behavior for tracing, observation, annotation, evaluations, deployment, SDKs, or administration. Report the snapshot and its upstream gaps; make no changes.
Langue du texte source : anglais
Interface with the sibling flue-obsidian-wiki vault for Flue harness documentation while developing Socratink agents. Use when authoring or changing Flue agents, hooks, skills, tools, routing, sandboxes, sessions, SDK clients, CLI usage, or when the user…
Langue du texte source : anglais
Tink CLI for repository-owned Agent Skills. Use when the user asks to initialize Tink; inspect GitHub skill sources; add, list, check, lock, verify, sync, refresh, or remove project skills; manage grouped skillsets; use the home library or catalog; harvest…
Langue du texte source : anglais
Apply Sal Khan's public thinking framework and explanatory style: mastery learning, teacher amplification, durable access, and evidence-aware educational AI. Use when the user explicitly asks for “Sal Khan's perspective,” “what would Sal Khan think,” “Sal…
Langue du texte source : anglais
Scout existing agent skills with evidence before creating one. Use when the user wants the best-supported skill for a workflow, to compare candidates against supplied evidence, or to verify one known skill or repository.
Langue du texte source : anglais
Triangulate a claim through faithful, steel, and stress reads, then identify its crux and evidence-sensitive convergence. Use when the user asks to pressure-test an interpretation, expose the crux between plausible readings, ground a supposedly fixed…
Langue du texte source : anglais