memory-mining
Skill11 starsChanged 6 days agoMITView on GitHub
Protocol for querying Memory Core prior art; use when diagnosing regression/validation symptoms, proposing architectural claims/roadmaps/external comparisons, or starting an implementation or PR review.
In this repository39 other files it gives its agents.
- architecture-pre-flightSkill
- blocked-task-stateSkill
- blog-postSkill
- context-recoverySkill
- create-skillSkill
- design-sweepSkill
- epic-createSkill
- epic-resolutionSkill
- epic-reviewSkill
- goal-scopingSkill
- guide-authoringSkill
- hostile-content-quarantineSkill
- ideation-sandboxSkill
- identity-firewallSkill
- industry-friction-radarSkill
- lane-intentSkill
- lead-roleSkill
- neo-app-authoringSkill
- neo-identity-updateSkill
- neural-linkSkill
- overviewSkill
- peer-namingSkill
- peer-roleSkill
- post-review-pickupSkill
- pr-reviewSkill
- pull-requestSkill
- release-notesSkill
- self-repairSkill
- session-sunsetSkill
- structural-pre-flightSkill
- tech-debt-radarSkill
- ticket-createSkill
- ticket-intakeSkill
- ticket-triageSkill
- turn-memory-pre-flightSkill
- unit-testSkill
- update-roadmapSkill
- video-createSkill
- whitebox-e2eSkill
The file
Files
Memory Mining Skill
If you are diagnosing a regression symptom ("used to work", "suddenly broken", surprise validation/schema/additionalProperties failures), proposing a non-trivial architectural claim/roadmap/external comparison, or starting an implementation or PR-review (3–10-call prior-art sweep), you MUST immediately use the view_file tool to read and strictly adhere to .agents/skills/memory-mining/references/memory-mining-protocol.md before running git log, grep, the first design sentence, or a review verdict. Or, if you already have the payload in context, proceed directly to its directives.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.