Skip to main content
skill CX Codex

log-work — Claude Code skill: work log and installation

The skill records a concise account of completed work in WORKLOG/YYYYMMDD.md, with references to files that hold more detail. Use it to keep a dated project log for people and AI agents.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add pchalasani/claude-code-tools --skill log-work -a claude-code
Open on GitHub

What log-work does

log-work creates WORKLOG/YYYYMMDD.md using the current date. When that file already exists, it adds a top-level section headed by an HH:MM timestamp and a short topic. The entry captures the work segment and points to documents or code for further context.

A section can include the current session ID, text or Markdown files read or created, results, and changed code files. Choose the items that fit the task. Existing entries stay in place as the skill adds another section to the same daily log.

What it helps with

  • record a completed work segment in a Markdown log
  • append an entry to the log for the current date
  • link a concise update to files with more detail
  • note which code files changed during a task

Example prompts for the agent

  • Log the work completed so far in WORKLOG/YYYYMMDD.md and link to the relevant files.
  • Record the text files you read or created, then summarize the outcome.
  • Add a timestamped section to the current work log with a short topic.

How to install log-work

1Skills CLI (Vercel)

npx skills add pchalasani/claude-code-tools --skill log-work -a claude-code

2Manually: put the files in place

~/.claude/skills/log-work/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/log-work/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about log-work

How do I install log-work in Claude Code?

Run npx skills add pchalasani/claude-code-tools --skill log-work -a claude-code. The skill file is at ~/.claude/skills/log-work/SKILL.md.

What does log-work do?

It writes a brief account of completed work to WORKLOG/YYYYMMDD.md, adding a timestamped section. Entries can point to files with more detail.

What can a work log entry contain?

It can list the session ID, text or Markdown files read or created, results, and code files changed. Include the details that apply to the task.

Source text

SKILL.md · MIT
---
name: log-work
description: >-
  Log the work segment that you did after the last work log until now in a log
  file at WORKLOG/YYYYMMDD.md where YYYYMMDD is based on today's date. The
  intent of this worklog is not to be exhaustive and super detailed. It is
  meant more as a very concise description plus, importantly, REFERENCES to
  more detailed documents such as code files or markdown documents, etc. This
  allows humans as well as AI agents to only refer to these additional
  documents if they want details. This is the progressive disclosure
  principle.
---


# log-work

1. create the file WORKLOG/YYYYMMDD.md if it doesn't already exist.
2. if the file exists, append a new TOP-LEVEL markdown section to it.
3. When you add a section, follow this format for the section header, so it has
   HH:MM timestamp followed by suitable concise topic

```markdown
# 13:45 Added feature xyz
```

In the log section include a CONCISE set of items such as the following
(Not all may apply to all situations, use your judgement):

- the session_id of the current session
- any text/md file(s) you CREATED and their purpose
- any text/md file(s) you READ as part of the current task
- short description of what you just did, including any results you got 
- which code files were created/changed



© pchalasani · MIT · pchalasani/claude-code-tools

Similar skills

SKILL.md skills catalog →

From the same set15

remove-ai-patterns Detects and removes generative writing cliches using the avoid-ai-writing catalog. Useful when drafting copy that needs a natural tone without synthetic phrasing. CX Codex +1 ★ 2,021repo stars agent-style This skill guides formal technical writing in English. Invoke it by name when drafting or revising a paper, README, proposal, or design document. CX Codex +1 ★ 2,021repo stars socratic-quiz The skill walks you through a topic with one question at a time instead of handing over the answer. Useful when you want to actually understand something, not just read it. CX Codex +1 ★ 2,021repo stars make-issue-spec Generates a markdown task specification and implementation plan in issues/. Adds the file to Git staging if permissions allow. CX Codex +1 ★ 2,021repo stars code-walk-thru The skill makes the agent open files in your editor one at a time, at the exact line, so you can follow a code walkthrough or review its changes. CX Codex +1 ★ 2,021repo stars voice-update Speaks a short audio summary of completed tasks using pocket-tts. Useful when monitoring background runs without watching the screen. CX Codex +1 ★ 2,021repo stars tmux-cli This skill lets an agent work with CLI agents and scripts in other tmux panes. Use it for shell commands, exit-code checks, and pane-to-pane communication. CX Codex +1 ★ 2,021repo stars msg This skill hands your agent a msg CLI for talking to other Claude and Claude sessions, reading incoming messages and coordinating across tmux panes. CX Codex +1 ★ 2,021repo stars

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor