Skills in this repository
SkillsMP has collected 207 skills from WeaveMindAI/weft. Open a skill to review its source and details.
WeaveMindAI/weftShowing 40 of 207 collected skills.
Read 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…
Read 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…
Read 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…
Read 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…
Read 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…
Read 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…
Code 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.
Read 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…
Read 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…
Read 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…
Read 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…
Read 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…
Read 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…
Read 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…
Writing mode: distill prose, fight length and jargon, loop drafts through the AI-tell catalog until a pass finds nothing but polish. Load when switching to [writing mode] or before writing any substantial prose (docs, READMEs, design notes, journal entries,…
Writing mode: distill prose, fight length and jargon, loop drafts through the AI-tell catalog until a pass finds nothing but polish. Load when switching to [writing mode] or before writing any substantial prose (docs, READMEs, design notes, journal entries,…
Writing mode: distill prose, fight length and jargon, loop drafts through the AI-tell catalog until a pass finds nothing but polish. Load when switching to [writing mode] or before writing any substantial prose (docs, READMEs, design notes, journal entries,…
Attacks 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 node with agency, an unguarded path to something that matters. Dispatched by Tangle when the program…
COMMAND, not reference: Validate and build the weft program, fix diagnostics until clean. Run this when the user asks for this step by name. The `weft-` reference skills beside it are things you read; this is a procedure you carry out.
COMMAND, not reference: Inspect the last run and chase the failure to one node. Run this when the user asks for this step by name, optionally naming a run id. The `weft-` reference skills beside it are things you read; this is a procedure you carry out.
Validate and build the weft program, fix diagnostics until clean
Inspect the last run and chase the failure to one node
Attacks 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 node with agency, an unguarded path to something that matters. Dispatched by Tangle when the program…
Gives the project's site its look and its motion. Loaded by the frontend-builder before it writes any page; works in design-lab/, a standalone app with every page mocked on realistic data, calls no backend, and hands over the tokens, components and motion the…
Deploy the program to a cloud install, through the deployer
Walk the user through setting up and running a node's live test
Expert entry: have a specific node built, or take the hand and write it yourself
Gives the project's site its look and its motion. Started by Tangle in the same breath as the frontend-builder; works in design-lab/, a standalone app with every page mocked on realistic data, calls no backend, and hands over the tokens, components and motion…
Read 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…
Debug 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.
COMMAND, not reference: Deploy the program to a cloud install, through the deployer. Run this when the user asks for this step by name, naming the target and optionally what to do. The `weft-` reference skills beside it are things you read; this is a…
COMMAND, not reference: Walk the user through setting up and running a node's live test. Run this when the user asks for this step by name, optionally naming the node type or package name. The `weft-` reference skills beside it are things you read; this is a…
COMMAND, not reference: Expert entry: have a specific node built, or take the hand and write it yourself. Run this when the user asks for this step by name, optionally naming what the node should do, in plain words. The `weft-` reference skills beside it are…
Load full codebase context before we design a feature
Write the agreed design to a plan file in ~/.codex/plans/
Fully implement the agreed plan in one long autonomous session
Babble 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.
Collaborative 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.
Convergence 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.
Red 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.