OpenParable
Skip to content
← Back to skills

Log Daily

Productivity
log-daily

Log Daily is an Agent Skill for productivity published in the majiayu000/claude-skill-registry repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Log conversation activity to today's daily note on demand. Use when wrapping up work, capturing decisions, or documenting session outcomes.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/majiayu000/claude-skill-registry/blob/HEAD/skills/productivity/log-daily/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/log-daily, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

<daily_note_location> Default Path: "~/Documents/obsidian_vault/vault/publish/7 - Daily Notes/{YYYY}/{MM}/{DD}.md" If not exists create a note for today </daily_note_location>

<when_to_use>

  • End of a work session (before closing Claude)
  • After completing a significant piece of work
  • When important decisions were made that should be recorded
  • When the user explicitly requests logging
  • Mid-session when switching contexts

NOT needed when:

  • Just chatting without meaningful work output
  • Quick questions with no decisions or outcomes </when_to_use>

<log_format>

---

## Session Log - [TIME]

**Focus:** [1-2 sentence summary of main work]

### Completed
- [Concrete outcome 1]
- [Concrete outcome 2]

### Decisions Made
- [Decision]: [Why]

### Next Steps
- [ ] [Follow-up task if any]

---

</log_format>

<quality_guidelines> Good entries:

  • "Created YouTube analytics inbox item with 3 integration options"
  • "Refactored authentication to use JWT instead of sessions"
  • "Decision: Use Postgres over SQLite (need concurrent writes)"

Bad entries:

  • "Worked on stuff"
  • "Had a conversation about the project"
  • "Did some research"

Be specific. Capture what was DONE, not what was discussed.

Why this matters: Vault-analyst reads these logs to find patterns. Vague entries = weak pattern detection. Specific entries = actionable automation recommendations. </quality_guidelines>

<example_output>

Local LLM integration for cost optimization

Completed

  • Overhauled inbox-processor with local_classify integration
  • Created keep-warm launchd agent for Ollama (4-min interval)
  • Tested classification accuracy on inbox items (~66%)

Decisions Made

  • Hybrid local/cloud pattern: Local does mechanical work, Claude does judgment
  • 4-minute keep-warm interval: Prevents cold start without wasting resources

Next Steps

  • Monitor token savings over next week
  • Apply pattern to slop-detector skill

</example_output>