OpenParable
Skip to content
← Back to skills

Work Logger

Productivity
work-logger

Work Logger is an Agent Skill for productivity published in the syi0808/screenize repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Document completed work with vector database indexing. Use `/log-work` after completing any significant task (feature, bug fix, refactoring, configuration change) to record what was done, decisions made, and files changed.

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/syi0808/screenize/blob/HEAD/.claude/skills/work-logger/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/work-logger, 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.

WORK LOGGING PROTOCOL

Index completed work for future context retrieval via semantic search.

When to use: Execute /log-work after every meaningful work unit (features, bugs, refactors, config changes).

Step 1: Generate Template

uv run .claude/skills/work-logger/scripts/create_template.py \
  --description "short-description" \
  --type feature|bugfix|refactor|docs|config

Output: private-docs/work-logs/YYYY-MM-DD-short-description.md

Step 2: Populate Log

Edit the generated file:

  • Metadata: Fill tags (YAML array) and files_changed
  • Content: Complete summary, Title, and all sections
  • Quality: Ensure self-contained, searchable text

Step 3: Index to Vector DB

uv run .claude/skills/sqlite-vectordb/scripts/add_entry.py \
  --file "private-docs/work-logs/YYYY-MM-DD-short-description.md" \
  --summary "One-line summary" \
  --tags "tag1,tag2"
  • Language: All indexed data (summary, tags) MUST be in English for vector DB compatibility
  • Integrity: Logs must be understandable in isolation with verified filenames/paths
  • Context: Use project conventions from CLAUDE.md
  • Completeness: Include decisions made and rationale

Valid usage:

# Step 1: Generate
uv run .claude/skills/work-logger/scripts/create_template.py \
  --description "add-user-auth" --type feature

# Step 2: Edit private-docs/work-logs/2026-01-16-add-user-auth.md

# Step 3: Index
uv run .claude/skills/sqlite-vectordb/scripts/add_entry.py \
  --file "private-docs/work-logs/2026-01-16-add-user-auth.md" \
  --summary "Implemented OAuth2 user authentication" \
  --tags "auth,oauth,security"