All authors
Claude Skills by WeaveMindAI
github.com/WeaveMindAI84 skills0 installs7 views
- Flow 1 InitLoad full codebase context before we design a featureVotes: 0GitHub stars: 1,992
- Flow 2 PlanWrite the agreed design to a plan file in ~/.codex/plans/Votes: 0GitHub stars: 1,992
- Flow 3 ImplementFully implement the agreed plan in one long autonomous sessionVotes: 0GitHub stars: 1,992
- Flow 4 ReviewOne wide-net review round over the whole uncommitted diff, then clean reshape fixesVotes: 0GitHub stars: 1,992
- Flow 5 Review CheckParanoid red-team pass over the fixes made during review, re-verifying each oneVotes: 0GitHub stars: 1,992
- Mode BabbleBabble mode: stream of consciousness, no structure, half-thoughts and dead ends, thinking out loud. Load when switching to [babble mode] or when early exploration should run unstructured before convergence.Votes: 0GitHub stars: 1,992
- Mode CodeCode mode: rules for writing and refactoring code. Style (DRY, SYNC markers, naming), no fallbacks fail loudly, tooling, testing pyramid. Load when switching to [code mode], before writing or editing code, or when fixing review findings.Votes: 0GitHub stars: 1,992
- Mode CollaborativeCollaborative mode, the default cognitive pattern: build on ideas, riff, propose, keep forward momentum. Load when switching to [collaborative mode] or when the conversation is open-ended design work.Votes: 0GitHub stars: 1,992
- Mode ConvergenceConvergence mode: synthesize scattered thoughts into coherent structure, extract core insights, output actionable next steps. Load when switching to [convergence mode] or when a rambling discussion needs pulling together.Votes: 0GitHub stars: 1,992
- Mode DebugDebug mode: observe, hypothesize, test, evaluate, fix-and-stop; no certainty without evidence, no symptom patches. Load when switching to [debug mode] or when diagnosing a bug or unexpected behavior.Votes: 0GitHub stars: 1,992
- Mode Red TeamRed team mode: systematically challenge every assumption, hunt blind spots, output counter-perspectives after each claim. Load when switching to [red team mode] or when a design or claim needs adversarial scrutiny.Votes: 0GitHub stars: 1,992
- Mode ResearchResearch mode: search before implementing, search for concepts not libraries, overdo it, never trust stale knowledge. Load when switching to [research mode] or when blocked on a design decision, library choice, or anything the internet answers.Votes: 0GitHub stars: 1,992
- Mode WritingWriting mode: distill prose, fight length and jargon, loop drafts through the AI-tell catalog until a full pass finds nothing. Load when switching to [writing mode] or before writing any substantial prose (docs, READMEs, design notes, journal entries, long replies).Votes: 0GitHub stars: 1,992
- ReleasingShipping weft: merging into main through a PR, what the release workflow publishes, the record tags that decide which stores publish, and the store rules that have actually bitten us. Load before merging to main, bumping an extension version, or debugging a red publish job.Votes: 0GitHub stars: 1,992
- Mode CodeCode mode: rules for writing and refactoring code. Style (DRY, SYNC markers, naming), no fallbacks fail loudly, tooling, testing pyramid. Load when switching to [code mode], before writing or editing code, or when fixing review findings.Votes: 0GitHub stars: 1,992
- Mode WritingWriting mode: distill prose, fight length and jargon, loop drafts through the AI-tell catalog until a full pass finds nothing. Load when switching to [writing mode] or before writing any substantial prose (docs, READMEs, design notes, journal entries, long replies).Votes: 0GitHub stars: 1,992
- ReleasingShipping weft: merging into main through a PR, what the release workflow publishes, the record tags that decide which stores publish, and the store rules that have actually bitten us. Load before merging to main, bumping an extension version, or debugging a red publish job.Votes: 0GitHub stars: 1,992
- Mode CodeCode mode: rules for writing and refactoring code. Style (DRY, SYNC markers, naming), no fallbacks fail loudly, tooling, testing pyramid. Load when switching to [code mode], before writing or editing code, or when fixing review findings.Votes: 0GitHub stars: 1,992
- Mode CollaborativeCollaborative mode, the default cognitive pattern: build on ideas, riff, propose, keep forward momentum. Load when switching to [collaborative mode] or when the conversation is open-ended design work.Votes: 0GitHub stars: 1,992
- Mode WritingWriting mode: distill prose, fight length and jargon, loop drafts through the AI-tell catalog until a full pass finds nothing. Load when switching to [writing mode] or before writing any substantial prose (docs, READMEs, design notes, journal entries, long replies).Votes: 0GitHub stars: 1,992
- Weft ApiRead when the program needs to answer calls from outside (an HTTP route, a websocket, anything a page or a service will call), and before briefing a frontend on what it will call: the URL known before activation, how a request's parts and body reach the graph, pictures in and out as links, streaming an answer as it is produced, holding a conversation open, who may call, and how to try it.Votes: 0GitHub stars: 1,992
- Weft CatalogRead before picking nodes for a job: the three reads that find a node and tell you how it wires, the metadata vocabulary you will meet there, the wiring shapes that recur (a connection, a provider, infrastructure, ports that come from a list), where a project's own nodes live, and what to do when nothing in the catalog fits.Votes: 0GitHub stars: 1,992
- Weft Cloud InstallRead when the user wants weft itself on their Google Cloud for the first time, or to upgrade or resize the weft already there: getting the user's GitHub and Google Cloud accounts and CLIs ready, the fork, the one-time gcloud block, the database, the fork's variables and secrets, running the install workflow, the first operator key, upgrading, and sizing. Deploying a project to an install that already exists is weft-deploying, not this.Votes: 0GitHub stars: 1,992
- Weft ConnectionsRead when the user asks about connections, API keys, sign-ins, permissions, the browser extension, human tasks, or a public URL: the connect flow door by door, what each banner means, tokens and scoping, and how HumanQuery tasks reach people. Also read it when activation fails with \"needs your weft to be reachable from the internet\", which this skill diagnoses and walks through.Votes: 0GitHub stars: 1,992
- Weft ConsumersRead when the user wants their own website, app, bot or extension to list, show, answer, skip or cancel what a program is waiting on, fetch a file it carries, or show what one of its nodes is displaying (a WhatsApp bridge's QR code, a database's minted password): the api token, the doors, the payload shapes, and how a new signal kind reaches a consumer.Votes: 0GitHub stars: 1,992
- Weft DatabaseRead when a cloud install needs its database: the user has no Postgres for it, or asks which to use. Gets one that scales to zero (Neon), with the user only signing up and pasting one key, and puts its addresses in the fork's secrets. Part of weft-cloud-install.Votes: 0GitHub stars: 1,992
- Weft DeployingRead when the user wants weft or a program live for real people on their cloud, asks about prod, a target, `--on`, a domain or GCP, or a deploy failed: targets and logging in, domains, the deploy workflow `weft ci add` writes, handing it its settings with `weft target export`, a project's frontends (`weft frontend`), what a cloud build is and how it fails, rolling back, and connections on a cloud install. The deployer specialist reads it; you read it before dispatching one.Votes: 0GitHub stars: 1,992
- Weft EditorRead when telling the user where to click or what they are looking at in VS Code: the toolbar, the action bar, the palette, context menus, editing gestures, groups and loops in the graph, run and replay, the inspector, the connect flow, the problems panel. Labels are verbatim from the extension, except an infra node's live card, whose buttons the running container names.Votes: 0GitHub stars: 1,992
- Weft FrontendRead when the user wants a page, app or site for the program, and before dispatching the frontend-builder: the verified scaffold commands, the default stack (pnpm, SvelteKit, PostgreSQL, BetterAuth, shadcn-svelte), calling the program's own routes and signal doors, the three variables that say where the program is, one shared PostgreSQL, where the api token lives, pictures as links, the build and its Dockerfile, and the shape for a site whose people each bring their own accounts or settings (...Votes: 0GitHub stars: 1,992
- Weft GapsRead when no node, group or node-smith contract can honestly deliver what the request needs, or when a node just built belongs in the shared catalog: the tracker to search first, the issue templates with their exact field ids, and the pre-filled issue URL to hand the user.Votes: 0GitHub stars: 1,992
- Weft InstancesRead whenever part of a program must run as several separate copies, each under its own id, even with ONE user: a session per chat, a sandbox per job, a workspace per document, a bot per customer. `@per_instance` (a container each), `@instance_filled` (a value each, a connection included), which instance a run is for, the route shape that works (shared routes, the instance picked per call), instance tokens, costs, starting and stopping one instance's containers, and giving every instance an e...Votes: 0GitHub stars: 1,992
- Weft LanguageRead before writing or editing any .weft source: declarations, wiring, config literals, reserved keys, inline signatures and expressions, types, groups and the level rule, included files, loops, the pulse execution model, @file, @asset and @include, and every compiler error slug.Votes: 0GitHub stars: 1,992
- Weft MembersRead when a program serves several PEOPLE, each with their own account, number, bot, spreadsheet or schedule (a WhatsApp assistant for many customers, a Slack bot per workspace, a report per client): the table that says which person owns which instances, one instance per person as the simple case, people who own several instances, the admin route that onboards a person, their settings page, and their connections. Read `weft-instances` first: it has the marks, the route shape and the lifecycle...Votes: 0GitHub stars: 1,992
- Weft MeteringRead when the user asks what a run costs, or when a node is wired to a paid API weft does not already price: the three pieces of a custom paid service, a meter to copy, and the rules that keep a number honest.Votes: 0GitHub stars: 1,992
- Weft ModelsRead when a program calls a language model and you need it to behave: whether it reasons before answering and how hard, what bounds a reply's length and why one comes back empty, what a class of model costs in time and money, and how prompt caching works across a chain of calls.Votes: 0GitHub stars: 1,992
- Weft Node AuthoringRead before dispatching a node-smith (the brief and the review) and when an expert writes a node by hand: the node authoring manual, the test tiers, and the shapes half-done work takes. The node-smith reads this same file as its manual.Votes: 0GitHub stars: 1,992
- Weft OnboardingRead when someone asks to be taught, shown around or onboarded, asks what a thing on screen means, or opens a project they have clearly just made: the guided tour of the two views, the graph, building in it, running, the three things that are alive, executions, triggers, infra, connections, a public address and people in the loop, in plain words for a total beginner.Votes: 0GitHub stars: 1,992
- Weft RunningRead when running, activating or debugging a program: the CLI command map, the daemon (never yours to restart), the build and run flow, trigger activation and the three deactivate modes, the infra lifecycle, sizing a command's timeout, journal inspection (executions, events, logs), and the debugging playbook.Votes: 0GitHub stars: 1,992
- Weft SafetyRead when a program talks to a model, messages people, spends money or writes into other systems: the swiss cheese model, the free layers built by default, the layers that cost something and the one-sentence test for when a program is high stakes, the wiring shapes, and the red-teamer pass.Votes: 0GitHub stars: 1,992
- Weft SdpRead when growing a program stage by stage: carving a run, supplying starting values, baking a trigger and firing it without activating, reusing completed work with a seed, freezing an accepted example, checking a new run against one, and what each refusal means.Votes: 0GitHub stars: 1,992
- Weft UpdatingRead when the user asks to update or upgrade weft, or when something broke right after one: locating the checkout, the git pull plus setup.sh walk, what setup.sh rebuilds and what it preserves, and fixing a failed update.Votes: 0GitHub stars: 1,992
- DeployerThe only agent that acts on a cloud install. Dispatched by Tangle with what to do on a named target (deploy, roll back, set up CI, read a failed cloud build); names the target with --on on every command, reads the weft-deploying skill, and reports the deployed version and route addresses, or the exact failure.Votes: 0GitHub stars: 1,992
- Frontend BuilderBuilds the project's frontend under front/ end to end, unsupervised. Dispatched by Tangle with the pages a person must use and the signals behind them. Reads the weft-frontend and weft-consumers skills, builds on the default stack (pnpm, SvelteKit, PostgreSQL, BetterAuth, shadcn-svelte), holds the api token server side, and proves the build and drives the one task as a client of the program before reporting.Votes: 0GitHub stars: 1,992
- Node SmithBuilds exactly one weft node end to end, unsupervised. Dispatched by Tangle with a typed contract (one job, exact ports); researches the real API documentation when the node wraps a service, writes the node and extensive tests in the project's nodes/ folder, and proves it by running weft test-node on the local tiers (basic and fake, never live) until green, then reports with evidence.Votes: 0GitHub stars: 1,992
- Prompt EngineerWrites and overhauls the LLM prompts inside a weft program (system prompts in prompts/, user prompt templates, JSON extraction instructions). Runs on the WeaveMind prompt-building playbook. Dispatched by Tangle when a stage talks to a model and the prompt matters.Votes: 0GitHub stars: 1,992
- Red TeamerAttacks a weft program before it faces the world, hunting every credible hole: an outsider lying through an input, a hallucination the graph trusts, a rogue step with agency, an unguarded path to something that matters. Dispatched by Tangle when the program is high-stakes; reads the weft source, the prompts, and the node code, walks each attack from input to consequence, and reports verified findings with the layer that closes each. Never fixes, never runs the program, never edits.Votes: 0GitHub stars: 1,992
- Run DiggerDeep post-mortem digging into a weft execution. Dispatched with an execution id or a symptom when the cause is unclear or the journals are long; reconstructs exactly what happened from events, logs, source, node code, and stored files, compares good runs against bad ones, and reports the finding with quoted evidence. Research only, never fixes.Votes: 0GitHub stars: 1,992
- Weft CheckCOMMAND, not reference: Validate and build the weft program, fix diagnostics until clean. Run this when the user asks for this step by name. The seventeen `weft-` reference skills beside it are things you read; this is a procedure you carry out.Votes: 0GitHub stars: 1,992
- Weft ConnectionsRead when the user asks about connections, API keys, sign-ins, permissions, the browser extension, human tasks, or a public URL: the connect flow door by door, what each banner means, tokens and scoping, and how HumanQuery tasks reach people.Votes: 0GitHub stars: 1,992
- Weft DebugCOMMAND, not reference: Inspect the last execution and chase the failure to one node. Run this when the user asks for this step by name, optionally naming an execution id. The seventeen `weft-` reference skills beside it are things you read; this is a procedure you carry out.Votes: 0GitHub stars: 1,992