Extract bounded, source-linked context from large files or many inputs. Use when context is too large, files are oversized, or a task needs concise excerpts.
中文简介正在准备中。当前显示原文说明。
RasputinKaiser/Self-Improvement-Plugin82026年10月6日 更新
免费在 GitHub 公开
sips-memory-fabric
Search, inspect, and record SIPS-owned Memory Fabric lessons. Use when a task needs prior lessons, recurring-fix memory, recall health, scoped historical context, or when a just-fixed bump or error should be recorded.
中文简介正在准备中。当前显示原文说明。
查看安装方法包含的文件（4）
- SKILL.md1.9 KB
- agents/openai.yaml299 B
- assets/icon-large.svg525 B
- assets/icon-small.svg525 B
SKILL.md（原文）
安装前可以查看交给 AI 代理的指令内容。
SIPS Memory Fabric
Use homebase_recall with the user's query and current repo root. Treat Memory Fabric as a SIPS-owned subsystem for recall, lesson capture, memory health, and future tooling.
Do not present recall as current proof. If a memory-derived fact is likely to drift, verify it with local files or runtime checks before using it as evidence.
When recall finds a relevant fix, cite the remembered boundary in the final answer and run the live command that proves the current repo still matches it.
After fixing any bump (failed command, wrong path, retry chain), record it immediately: run python3 scripts/memory_fabric_cli.py record from the SIPS plugin root with the symptom, the working fix, and repo scope (or memory_fabric_record on the codex-memory-fabric MCP when that host exposes it), then confirm it surfaces via homebase_recall. Unrecorded fixes recur across sessions.
SIPS 0.6 evidence workflow
Use the shared adaptation controller for structured investigations and bounded probes.
Prefer current v2 contracts and joint-prerequisite composition before new helpers.
Use additive counterexamples; preserve raw episodes when proposing procedures.
Policy trials are declarative proposals, never changes to evaluation or activation.
See docs/sips-06.md for request shapes, supported schemas, and research limits.
Research methods (0.7)
Use assumptions to expose conditional support and contradictions. Unverified evidence references do not establish truth; recompute after retraction. Manual teaching does not establish high confidence. See method API and command protocol.
评价
还没有评价。欢迎分享你的使用感受。
评论
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
同一仓库的技能
Inspect SIPS Homebase status, manifest wiring, routes, host visibility, and MCP freshness. Use when asked for SIPS status, command center, host audit, plugin visibility, or whether Homebase is fresh.
中文简介正在准备中。当前显示原文说明。
RasputinKaiser/Self-Improvement-Plugin82026年10月6日 更新
Route a task through SIPS commands, agents, scripts, MCP tools, or bounded delegation. Use when asked to route, split, fan out, escalate, or choose the right SIPS path.
中文简介正在准备中。当前显示原文说明。
RasputinKaiser/Self-Improvement-Plugin82026年10月6日 更新
Turn failures, logs, symptoms, or flaky behavior into a compact repro and verification plan. Use when debugging needs a reproducible failure path.
中文简介正在准备中。当前显示原文说明。
RasputinKaiser/Self-Improvement-Plugin82026年10月6日 更新
Capture and develop a reusable skill, tool repair, or behavior improvement noticed while completing a task. Use when instructions are stale, a recurring workflow deserves a skill, or a tool contract fails in practice.
中文简介正在准备中。当前显示原文说明。
RasputinKaiser/Self-Improvement-Plugin82026年10月6日 更新
Plan browser, app, screenshot, or UI checks before visual claims. Use when a task includes app shots, visual QA, generated assets, or runtime UI proof.
中文简介正在准备中。当前显示原文说明。
RasputinKaiser/Self-Improvement-Plugin82026年10月6日 更新