Repository inventory

spillwavesolutions/project-memory

Skills indexed from this repository, with install-style signals scoped to the repo.
1 skills48 GitHub stars0 weekly installsGitHubOwner profile

Overview

This skill sets up and maintains a structured project memory system under docs/project_notes/. It creates and curates four focused memory files (bugs.md, decisions.md, key_facts.md, issues.md) and configures CLAUDE.md and AGENTS.md so AI tools remain memory-aware. The goal is to preserve solutions, architectural decisions, key facts, and work history across sessions and tools.

How this skill works

On first run the skill creates docs/project_notes/ and populates it from provided templates for bugs, decisions, key facts, and issues. It then inserts a "Project Memory System" section into CLAUDE.md and (optionally) AGENTS.md describing protocols for searching, updating, and using those files. During development the skill searches memory files before proposing changes and adds or updates entries when asked (bug fixes, ADRs, config facts, ticket logs).

When to use it

  • Starting a new project that will accumulate institutional knowledge
  • When you want AI agents to check past decisions and fixes before proposing changes
  • Log a bug fix, add an architectural decision, or record key configuration details
  • Before making architectural changes or major refactors
  • When multiple developers or multiple AI tools are working on the repo

Best practices

  • Keep entries concise (1–3 lines for descriptions) and always include dates
  • Prefer bullet lists over tables for simplicity and editability
  • Include URLs to tickets, docs, and dashboards for traceability
  • Search docs/project_notes/ before making proposals or applying fixes
  • Manually archive or prune old entries on a regular cadence (no automated deletion)

Example use cases

  • User reports a recurring error — search bugs.md, apply a known fix, or add a new entry with root cause and prevention
  • Propose tooling change — check decisions.md for existing ADRs and either follow or document a new ADR explaining trade-offs
  • After completing a ticket — append a dated entry to issues.md with ticket ID, status, URL, and short notes
  • Update deployment details — add or revise entries in key_facts.md for service accounts, ports, and connection strings

FAQ

No. The templates and guidelines explicitly advise against storing sensitive credentials; key_facts.md should list non-sensitive configuration and reference secure secret stores.

What if AGENTS.md is not present?

The skill will ask whether to create AGENTS.md. If created, it receives the same Project Memory System section so multi-tool workflows remain consistent.

1 skills

More from this maintainer
Other repositories and skills published under the same GitHub owner.
Skills library
Jump back to the full directory or explore grouped topics.
Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational