andreadellacorte avatar

Groove Utilities Memory Log Daily

End of day memory logging for the Groove workflow system. It writes a structured markdown file to `.groove/memory/daily/` with sections for completed work, git activity, task status, learnings, and carry-forward items. The skill pulls from actual artifacts like completed tasks and git diffs rather than letting you handwave what you did. If you try to log something vague or a task lacks details, it'll ask you to clarify before writing. Designed to append to files that might already exist from morning standup, so your daily bookends stay in one place. Honest take: this is the kind of forced reflection that feels annoying until you need to remember what you actually accomplished three weeks ago.

skills.sh installs
582
GitHub stars
6
last updated
Aug 21, 2026

Install

$ npx -y skills add andreadellacorte/groove --skill groove-utilities-memory-log-daily --agent claude-code

Installs into .claude/skills of the current project.

Files

groove-utilities-memory-log-daily

Outcome

.groove/memory/daily/YYYY-MM-DD.md is created or updated with a structured end entry. The file may already exist from daily start (start-of-day structure); if so, append the closeout sections. The file is written so that the next daily start can verify yesterday had an end.

Acceptance Criteria

  • File exists at .groove/memory/daily/YYYY-MM-DD.md after command completes
  • "Done today" section contains granular multi-level bullets sourced from completed tasks and git diff
  • Git section summarises commits and changed files for the day
  • Tasks section shows task summary by status
  • Learnings section is populated (not blank)
  • Open/Next section captures carry-forward items
  • If file already exists, content is updated/appended rather than overwritten

Constraints

Sponsors

Details

Repository
github.com/andreadellacorte/groove
First seen
Jun 3, 2026

More from andreadellacorte/groove

All 45

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs