- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add bitjaru/styleseed --skill ss-learn -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add bitjaru/styleseed --skill ss-learn -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add bitjaru/styleseed --skill ss-learn -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add bitjaru/styleseed --skill ss-learn -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/bitjaru/styleseed/tree/HEAD/extensions/learning/skills/ss-learn來自發布者
ss-learn turns a specific human-approved correction into a generalized candidate rule. It
does not train a model, scrape a repository, or upload telemetry. The CLI is local-only. An
optional plugin MCP bridge can expose one exact package to its connected client/model only after a
separate one-time human grant.
Read references/privacy-contract.md before using this skill.
null or not-run; never infer.STYLESEED.md instead.After explicit user approval:
node <installed-ss-learn>/scripts/learning.mjs init --project-root .
This creates .styleseed/learning/config.json with sharing disabled and all raw-material
collection disabled. It performs no network request.
Use references/candidate.schema.json. Generalize the lesson:
Do not include project names, URLs, paths, emails, source snippets, prompts, screenshots, colors, font names, or component names. Then capture it:
node <installed-ss-learn>/scripts/learning.mjs capture \
--project-root . \
--input /path/to/candidate.json
The CLI validates maintained context IDs, exact fields, privacy patterns, and evidence honesty.
It writes an immutable draft ID under .styleseed/learning/candidates/.
Show the full candidate to the user. Only after their explicit accept/reject decision run:
node <installed-ss-learn>/scripts/learning.mjs review \
--project-root . \
--id <candidate-id> \
--decision accepted \
--reviewer <local-alias> \
--reason "<why this generalizes>" \
--attestation APPROVE_LOCAL_REVIEW
Use --decision rejected for a counterexample. Never accept on the user's behalf. A candidate is
content-addressed and receives one final local decision; revise the source lesson and capture a new
candidate instead of rewriting an accepted or rejected record.
Only an accepted candidate can be packaged. Show the sanitized payload and ask separately whether
the user approves export for team-registry or community-candidate:
node <installed-ss-learn>/scripts/learning.mjs prepare-share \
--project-root . \
--id <candidate-id> \
--purpose team-registry \
--attestation APPROVE_LOCAL_EXPORT
This writes .styleseed/learning/share/<id>.<purpose>.json. It strips reviewer identity and local
paths, binds the payload to the engine revision, and records a content hash. It does not send
the file anywhere.
Only when the user separately approves exposing the prepared package to the connected MCP client and its model, run:
node <installed-ss-learn>/scripts/learning.mjs grant-mcp-read \
--project-root . \
--package .styleseed/learning/share/<package.json> \
--attestation APPROVE_MCP_READ
The grant is bound to the package hash and accepted local review. The MCP bridge consumes it before returning the package, so retries fail closed. This is client/model exposure even though the MCP server itself performs no network request. Never describe it as remaining local after consumption.
A share package is evidence, not a StyleSeed rule. Central or team promotion requires multiple independent projects, counterexamples, accessibility and grammar regression checks, benchmark evidence, and named maintainer approval. Never edit core rules automatically from local learning.
Report separately:
Capture a human-approved UI design lesson as a privacy-minimized local StyleSeed candidate, review it, and prepare an opt-in share package without transmitting project code, prompts, screenshots, or b
---name: ss-learndescription: Capture a human-approved UI design lesson as a privacy-minimized local StyleSeed candidate, review it, and…---# extensions/learning/skills/ss-learn/SKILL.md總覽
Capture a human-approved UI design lesson as a privacy-minimized local StyleSeed candidate, review it, and prepare an opt-in share package without transmitting project code, prompts, screenshots, or brand data. Use when a person asks StyleSeed to remember, learn from, generalize, review, or prepare a reusable rule from an accepted design correction.
常見問題
從發布者下載 extensions/learning/skills/ss-learn/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/bitjaru/styleseed。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。