Skills for Real Engineers. Straight from my .agents directory.
review
Agent skill fromnagisanzenin/engram
Clear due memory reviews with free recall — the two-minute habit that makes learning permanent. Use when reviews are due, or the user wants to review, practice, or "do my engram reviews".
How to install review
npx skills add nagisanzenin/engram# or add only this skill to Claude Code: copy the folder
skills/review/
# into
~/.claude/skills/review/ (all projects)
.claude/skills/review/ (one project)
1# /review — the retention loop23Read `skills/_shared/dialogue-grammar.md` (hard rules, confidence integrity, park-and-resume, and the rating map apply here verbatim). Set:45```bash6# Resolve the engine. RUN THIS BLOCK VERBATIM — do not substitute a path you guessed.7# Order: ZCode's plugin root first (ZCode exports the legacy CLAUDE_PLUGIN_ROOT too,8# so its own var must be checked before it), then OpenCode / Claude Code / Codex, dev9# clone (ENGRAM_ROOT — Pi's extension exports this), OpenClaw's extension dir, the10# Antigravity staging path, Pi's git-install path, the working tree ($PWD / git11# toplevel), and LAST the shared agent home (~/.agents/engram — the clone route for12# platforms that read ~/.agents; last so it can shadow nothing). First one exists wins.13for d in "$ZCODE_PLUGIN_ROOT" "$OPENCODE_PLUGIN_ROOT" "$CLAUDE_PLUGIN_ROOT" "$CODEX_PLUGIN_ROOT" "$ENGRAM_ROOT" \14 "${OPENCLAW_STATE_DIR:-$HOME/.openclaw}/extensions/engram" \15 "$HOME/.gemini/config/plugins/engram" \16 "$HOME/.pi/agent/git/github.com/nagisanzenin/engram" \17 "$PWD" "$(git rev-parse --show-toplevel 2>/dev/null)" \18 "$HOME/.agents/engram"; do19 [ -n "$d" ] && [ -f "$d/scripts/engram.py" ] && ENGRAM="$d/scripts/engram.py" && break20done21if [ -z "$ENGRAM" ]; then22 echo "engram: engine not found — set ENGRAM_ROOT to your engram checkout" >&223 return 2 2>/dev/null || exit 2 # FAIL CLOSED: proceeding runs `python3 ""`,24…
Excerpt shown under the repository's MIT license.
More skills in engram
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
