worklog
Skill0 starsChanged 12 days agoMITView on GitHub
Record issue work (a CUBRID Jira or Hibernate HHH key) as a Markdown note in the public work-docs repo, filled from the session (background, cause, change, verification, result) and committed. For work without an issue, use note. Triggers on phrases like '작업 기록 남겨줘', 'worklog 작성', '이 이슈 문서로 정리해서 커밋'.
- Sends data out
14 other projects use a version of this.
Adopted by
Most recently taken up by
- JibranMachiavelli/claude-worklogtheir own version, first seen Nov 8, 2026
- antass/antass-skillstheir own version, first seen Nov 1, 2026
- Vinay-R/vibe-engineering-templatetheir own version, first seen Nov 1, 2026
- rynbol/claude-skillstheir own version, first seen Oct 13, 2026
- BespokeWoodcraftStudio/claude-worklog-skilltheir own version, first seen Oct 11, 2026
- dgilford/ai-science-toolkittheir own version, first seen Oct 1, 2026
Other versions14 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 14
- revfactory/skills★ 160same name
- dgilford/ai-science-toolkit★ 82same name
- tae0y/python-project-template★ 14same name
- antass/antass-skills★ 1same name
- BespokeWoodcraftStudio/claude-worklog-skill★ 1same name
- bpappin/skills★ 1same name
- f-ewald/claude-skills★ 1same name
- ingeun92/claude-code-configs★ 1same name
- renicsemenov/claude-code-skills★ 1same name
- Hyosun-byte/worklog★ 0same name
4 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository22 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- blogSkill
- ci-checkSkill
- cmt-manualSkill
- commitSkill
- cubrid-manualSkill
- hhh-dialect-verify-reportSkill
- hhh-dialect-verifySkill
- java-formatSkill
- jdbc-ctp-verify-reportSkill
- jira-draftSkill
- jira-fetchSkill
- noteSkill
- pr-draftSkill
- pr-reviewSkill
- reportSkill
- review-triageSkill
- self-reviewSkill
- skill-createSkill
- submodule-bumpSkill
- tutorSkill
- weekly-reportSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 12 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 53
This repo is PUBLIC: do not include credentials, internal hostnames, local absolute paths, or internal-only analysis.
“Common” is measured: kept by at least 6 in 10 of the 12 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Record work as a Markdown note (work-docs)
Publish a per-issue work record to your public work-docs repo, so the reasoning behind a change is shareable and linkable from PRs. This complements (does not replace) the internal master DOCX: deep internal analysis stays in the DOCX; a clear, public-safe summary goes here.
Step 0: Prereqs
- The docs repo cloned locally at
${WORK_DOCS_REPO:-$HOME/Devel/work-docs}, with itsoriginset to your public repo (e.g.github.com/Srltas/work-docs). Override the path withWORK_DOCS_REPO(the legacyWORKLOG_DOCS_REPOalso works). Shared with thenoteskill. - Optional: the jira-fetch skill, to pull issue context (CBRD only; Hibernate HHH is Atlassian Cloud, not supported by that tool).
Step 1: Identify the record
From $ARGUMENTS: an issue key (<PROJECT>-<N>, e.g. CBRD-1234, TOOLS-4888, APIS-1079, CUBRIDQA-123, HHH-20527) or a topic slug, plus an optional short slug. Write the note in Korean regardless of the project. The project prefix only decides the folder/file name (see Step 3).
Step 2: Gather context (optional)
For a CUBRID Jira Server issue (CBRD, TOOLS, APIS, CUBRIDQA), pull its summary/description with jira-fetch to seed the note:
bash ${CLAUDE_SKILL_DIR}/../jira-fetch/assets/fetch_jira.sh -o /tmp/jira <KEY>(HHH is Atlassian Cloud, which jira-fetch does not support, so write its context from the session instead.) Also use the current session's work (the change, the verification numbers) as the substance.
Step 3: Scaffold the file
bash ${CLAUDE_SKILL_DIR}/assets/new_worklog.sh <ISSUE-KEY|topic> [slug]Creates <KEY>/<KEY>-<slug>.md from the template (refuses to overwrite an existing one) and prints the local path plus the public GitHub URL it will have.
Step 4: Fill it in
Edit the created file, completing each section (요약, 배경/이슈, 원인 분석 AS-IS, 변경/해결 TO-BE, 검증 with real numbers, 결과/영향, 참고 links). Detailed but easy to skim:
## 요약first, in one line (무엇을 했고 결과가 뭔지).- 배경·결론은 2~3문장 짧은 서술, 원인·변경·검증·결과의 나열은 개조식 불릿.
- before/after·수치는 표로, 코드·SQL·로그는 코드블록으로 (문장으로 풀지 않기).
- 한 불릿에는 한 사실만:
현재 → 목표를 한 문장에 욱여넣지 말고 표의 두 열로. 클래스·파일 이름을 넷 넘게 쉼표로 잇지 말고, 표로 분리하거나 기준 + 개수로 압축한다 (예: "Wrapper를 구현하는 7개 클래스"). - 흐름·구조·관계·시퀀스는 Mermaid 다이어그램(GitHub가 자동 렌더하는
mermaid코드블록)으로 적극 표현:flowchart(처리·분기 흐름),sequenceDiagram(호출/상호작용),erDiagram(스키마·테이블 관계),classDiagram/stateDiagram(구조·상태 전이). 이해를 돕는 곳에만, 노드는 간결하게(대략 10개 이하). 노드가 4개를 넘으면flowchart TB(세로)가 폭에 맞아 읽기 좋다.- 복잡한 도식은 커밋 전에 한 번 렌더해 눈으로 확인한다(문법 오류·어색한 배치 예방). 예:
.mmd로 저장 후curl -sf -X POST "${KROKI_URL:-https://kroki.io}/mermaid/png" -H 'Content-Type: text/plain' --data-binary @diagram.mmd -o /tmp/d.png로 렌더해 이미지를 확인하고, 이상하면 고친 뒤 다시 렌더한다. 최종 문서에는mermaid코드블록을 그대로 둔다(GitHub가 자동 렌더).
- 복잡한 도식은 커밋 전에 한 번 렌더해 눈으로 확인한다(문법 오류·어색한 배치 예방). 예:
- em-dash(
—)는 쓰지 않는다. 쉼표·콜론·괄호·마침표로 대체.
This repo is PUBLIC: do not include credentials, internal hostnames, local absolute paths, or internal-only analysis. Anything sensitive stays in the master DOCX; link to the JIRA/PR instead.
Step 5: Commit (never push)
REPO="${WORK_DOCS_REPO:-$HOME/Devel/work-docs}"
git -C "$REPO" add "<folder>/<name>.md"
git -C "$REPO" commit -m "docs(<key>): <short summary>"Give the user the local path and the public URL. Pushing is the user's responsibility.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

