skills/memory-md/SKILL.md
Maintains concise repository MEMORY.md notes for gotchas, stale memory corrections, and durable user preferences. Use at the start of repository conversations, when the user mentions MEMORY.md, when an error should be remembered to avoid repeating it, or when MEMORY.md content may be wrong.
npx skillsauth add narumiruna/agent-skills 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.
Use MEMORY.md as a concise repository-local memory file. It is not automatically loaded, so check for it explicitly at the start of repository conversations and whenever prior project context may matter.
MEMORY.md exists and skim it for relevant context before planning or editing.MEMORY.md as normal. Do not invent entries or assume the file exists.MEMORY.md entry is wrong, stale, or contradicted by current evidence, correct that entry instead of adding a conflicting note.MEMORY.md, including credentials, tokens, API keys, cookies, private endpoints, proprietary/internal-only details, or sensitive personal data.## GOTCHA and ## TASTE.## GOTCHA for traps, failure modes, commands that behave unexpectedly, and verified recovery steps.## TASTE for durable project or user preferences that shape future edits.For gotchas, capture the failure and the fix:
- Symptom: <what went wrong>. Cause: <why>. Fix: <specific future action>.
For taste, capture the preference and its practical effect:
- Prefer <choice> when <context>; avoid <alternative> because <reason>.
GOTCHA: command failed because a tool needed UV_CACHE_DIR=/tmp/uv-cache; record the symptom, cause, and future command pattern.TASTE: the user prefers thin skills with only SKILL.md unless supporting files solve a concrete problem.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.