rightmemory-onboarding-interview

Solid

Use when a user wants to initialize or onboard a RightMemory memory root, create reviewable MEMORY.md or MEMORY_*.md drafts, convert project/user context into RightMemory schema, or asks for an onboarding interview before writing memory files.

Code & Development 9 stars 2 forks Updated today Apache-2.0

Install

View on GitHub

Quality Score: 79/100

Stars 20%
33
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# RightMemory Onboarding Interview Run a short, evidence-aware interview that produces reviewable RightMemory drafts from durable project, user, environment, and agent-behavior context. ## Workflow 1. Read `skills/rightmemory-schema.md` and `MEMORY.example.md` when available. Treat the schema as authoritative and the example as illustrative, never as user facts. 2. Use the requested staging location, or `./tmp` by default. Do not overwrite a real memory root without explicit permission. 3. If the user asks what the interview covers, give a compact preview before starting. 4. Begin with the highest-yield question: > What projects, domains, or responsibilities should this memory cover, and what paths, links, docs, or servers can I inspect for each one? 5. Inspect supplied paths, repositories, docs, and links before asking follow-ups. Check durable sources such as READMEs, manifests, tests, API or integration docs, runbooks, and build or deployment files. Use bounded evidence collection only when permitted by the environment and project instructions. 6. Ask one practical follow-up at a time, and only when the answer cannot be inferred and would change future agent behavior. Focus on responsibility boundaries, project relationships, environments, integration surfaces, downstream callers, durable operating rules, and operationally relevant unknowns. 7. Stop when the evidence and answers support a useful draft. If the user rejects a question as unhelpful, skip that category...

Details

Author
RightL
Repository
RightL/RightMemory
Created
2 months ago
Last Updated
today
Language
Python
License
Apache-2.0

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

memory-onboard

Use this skill when the user types `/memory-onboard` (or asks "set up memory for this repo" / "onboard this repo to memory" / "what should be in lore for this repo?"). It runs a repo-aware onboarding interview that produces DRAFT lore records grounded in concrete repo signals (README, ADRs, recent commits, deprecation markers, in-flight migrations). Requires the memory-mcp MCP server to be configured. Uses these MCP tools: search_lore / get_lore / suggest_lore (core), and optionally report_conflict (when a candidate item contradicts existing lore) and record_absence (when the user confirms a topic has no team policy yet). All suggest_lore / report_conflict output lands as drafts — the human approves via `memory review` afterwards. record_absence markers self-expire (default 14 days) and don't need review.

0 Updated today
tmj-90
Code & Development Solid

memory-retriever

Use when the user explicitly chooses read-only RightMemory retrieval for relevant context from earlier work, preferences, project or domain knowledge, live Pursuits, or reusable agent guidance. This skill never submits updates or modifies RightMemory.

9 Updated today
RightL
AI & Automation Solid

memory-review

Interactive review of all memory/ files — keep, update, deprecate, or delete entries one by one. Use when the user wants to audit and prune accumulated memory — 'review my memory', 'clean up what you remember'. Do NOT use for: teaching a new fact (use learn), recalling something specific (read memory directly), or batch-promoting session insights (use recap).

20 Updated 5 days ago
onebrain-ai