菜单
这个仓库中的 skills
SkillsMP 已收集 WeaveMindAI/weft 中的 72 个 Skill。打开任一 Skill 可查看来源和详情。
WeaveMindAI/weft已展示 32 / 72 个已收集 Skill。
COMMAND, not reference: Grow the program one stage at a time against a real input, seeded runs and frozen examples included. Run this when the user asks for this step by name, optionally naming the stage to grow or an example name to rerun. The sixteen…
原文语言：英语
Read 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.
原文语言：英语
COMMAND, not reference: Grow the program one stage at a time against a real input, seeded runs and frozen examples included. Run this when the user asks for this step by name, optionally naming the stage to grow or an example to check. The sixteen `weft-`…
原文语言：英语
Read 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.
原文语言：英语
Writes 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…
原文语言：英语
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 step with agency, an unguarded path to something that matters. Dispatched by Tangle when the program…
原文语言：英语
Deep post-mortem digging into a weft execution. Dispatched with a color 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…
原文语言：英语
Read 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.
原文语言：英语
Writes 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…
原文语言：英语
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 step with agency, an unguarded path to something that matters. Dispatched by Tangle when the program…
原文语言：英语
Deep post-mortem digging into a weft execution. Dispatched with a color 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…
原文语言：英语
Read 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.
原文语言：英语
Read 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.
原文语言：英语
Read 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.
原文语言：英语
Read 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.
原文语言：英语
Read 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.
原文语言：英语
Read 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.
原文语言：英语
Load full codebase context before we design a feature
原文语言：英语
Write the agreed design to a plan file in ~/.codex/plans/
原文语言：英语
Fully implement the agreed plan in one long autonomous session
原文语言：英语
One wide-net review round over the whole uncommitted diff, then clean reshape fixes
原文语言：英语
Paranoid red-team pass over the fixes made during review, re-verifying each one
原文语言：英语
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.
原文语言：英语
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.
原文语言：英语
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.
原文语言：英语
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.
原文语言：英语
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.
原文语言：英语
Research 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.
原文语言：英语
Writing 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…
原文语言：英语
Writing 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…
原文语言：英语
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.
原文语言：英语
Writing 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…
原文语言：英语