worklog
- Repo stars 14
- Author updated Live
- Author repo python-project-template
- Domain
- Productivity
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @tae0y · no license declared
- Token usage
- Lean
- Setup complexity
- Guided setup
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Shell exec
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: worklog
description: Update worklog files by moving tasks between todo/doing/done states. Use when recording task pro…
category: productivity
runtime: no special runtime
---
# worklog output preview
## PART A: Task fit
- Use case: Update worklog files by moving tasks between todo/doing/done states. Use when recording task progress, starting new work, or marking tasks complete. Requires explicit arguments: worklog [done|doing|todo] [description]..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Worklog Files / Arguments / What to Read (by command)” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Update worklog files by moving tasks between todo/doing/done states. Use when recording task progress, starting new work, or marking tasks complete. Requires explicit arguments: worklog [done|doing|todo] [description].”.
- **02** When the source has headings, the agent prioritizes “Worklog Files / Arguments / What to Read (by command)” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options.The source does not require a stable slash command. After installation, invoke the skill by name and describe the task.
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files, run shell commands.
Start with a small task and check whether the result follows “Worklog Files / Arguments / What to Read (by command)”. Inspect diffs, logs, previews, or tests before expanding scope.
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: worklog
description: Update worklog files by moving tasks between todo/doing/done states. Use when recording task pro…
category: productivity
source: tae0y/python-project-template
---
# worklog
## When to use
- Update worklog files by moving tasks between todo/doing/done states. Use when recording task progress, starting new wo…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Worklog Files / Arguments / What to Read (by command)” and keep inference separate from source facts.
- read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies.The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "worklog" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Worklog Files / Arguments / What to Read (by command)
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files, run shell commands | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}Worklog
Update task state in worklog files. Requires explicit arguments.
Worklog Files
localdocs/worklog.todo.md— backloglocaldocs/worklog.doing.md— in progresslocaldocs/worklog.done.md— completed (grouped by date, append-only)
worklog is for current phase/session execution tracking.
For future items not yet included in an approved plan, use localdocs/backlog.<topic>.md.
Arguments
$ARGUMENTS must be: [state] [description]
done [description]— mark task completedoing [description]— start working on a tasktodo [description]— add to backlog
If no arguments, stop and output:
Error: worklog requires explicit arguments.
Usage: worklog [done|doing|todo] [description]
Examples:
worklog done config/settings.py setup complete
worklog doing collectors/data_go_kr.py implementation
worklog todo parsers/xml_parser.py implementationWhat to Read (by command)
done: Read worklog.doing.md only — to find and remove the matching item.
doing: Read worklog.todo.md only — to find and remove the matching item.
todo: No need to read any file — just append.
Never read worklog.done.md — it is append-only and grows over time.
Update Rules
done [description]
- Read
worklog.doing.md; find matching item (keyword match, not exact) - Remove the item from doing
- Append to
worklog.done.mdunder today's date section (## YYYY-MM-DD), creating the section if absent - If no match in doing, append directly to done without removing anything
doing [description]
- Read
worklog.todo.md; find matching item - Remove the item from todo
- Append to
worklog.doing.md - If no match in todo, append directly to doing
todo [description]
- Append item to end of
worklog.todo.md
Writing Style
- Concise bullet points — focus on what was done, not how
- Use filenames and concrete task names over vague descriptions
- No tables or heavy formatting
- Done items must be under a date section (
## YYYY-MM-DD)
Output
Worklog updated:
- [action taken]: [description]
Decide Fit First
Design Intent
How To Use It
Boundaries And Review