skills/workflow-repository/maintaining-memory-md/SKILL.md
Read and maintain concise repository-root MEMORY.md notes for verified gotchas, durable user preferences, and established repository conventions. Use at repository-conversation start, when MEMORY.md is mentioned or may be stale, or when a qualifying memory emerges.
npx skillsauth add narumiruna/agent-skills maintaining-memory-mdInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Resolve the repository root and inspect MEMORY.md at the start of repository work and before non-trivial debugging, design, workflow, or skill maintenance. Missing memory is normal. Current repository evidence always overrides it.
Do not record transient status, task history, broad summaries, speculation, generic best practices, or secrets. Do not duplicate conventions already stated in AGENTS.md or authoritative documentation. If a convention should govern all contributors, recommend updating its authoritative owner unless that file is already within the user's requested scope; do not record it in MEMORY.md. Sanitize any reusable lesson involving credentials, tokens, private endpoints, proprietary data, or personal information.
MEMORY.md merely because it is absent.## GOTCHA
## TASTE
## CONVENTIONS
- Symptom: <failure>. Cause: <reason>. Fix: <future action>.
- Prefer <choice> when <context>; avoid <alternative> because <reason>.
- Use <pattern> for <context>; repository evidence: <concise evidence>.
After editing, reread the file to verify all three headings, placement, deduplication, and absence of sensitive or task-log content. Report the entry created or revised; do not claim memory was updated when writes were unavailable.
development
Score or compare one or more agent skills across trigger clarity, workflow actionability, safety boundaries, verification rigor, incremental knowledge value, and leanness. Use only when the user explicitly asks for ratings, numerical quality scores, rubric-based scorecards, or scored comparisons; use creating-agent-skills for unscored reviews or revisions.
development
Assess or improve an existing codebase's architecture when the user asks about module boundaries, coupling, scattered ownership, testability, change locality, deep modules, seams, or behavior-preserving structural refactoring. Use for cross-module design rather than ordinary diff review or a confirmed edge-case bug fix.
development
Perform read-only security audits, vulnerability assessments, or threat-focused reviews of diffs, pull requests, code paths, or explicitly scoped repositories when security is the primary objective or acceptance criterion. Use reviewing-code for ordinary review with baseline security coverage and hardening-code-paths for fixing confirmed findings.
development
Run iterative multi-reviewer panels over a code diff, verify their findings, apply explicitly authorized fixes, and re-review the updated change until it passes or reaches a stopping condition. Use when the user asks for a panel loop, multi-model code-review consensus, or a review-fix-re-review cycle.