agentleFS
SrltasSrltas/claude-skills/weekly-report/SKILL.md

weekly-report

Skill0 starsChanged 13 days agoMITView on GitHub

Turn a list of Jira issue keys into one short Korean line per issue for the weekly-report sheet (개조식, 명사형 종결), fetched with jira-fetch. Summarizes what each issue is, not its progress.

49 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use agency-clients, cross-post-video and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • posteverywhereSkill

    agency-clients

    Work safely across several clients or brands in PostEverywhere. Use when the user manages social media for more than one client, brand or business, mentions a client by name, asks to switch clients, or when the connected accounts belong to different companies.

    Also in 3 projects that use this

  • posteverywhereSkill

    cross-post-video

    Post one video to several platforms with PostEverywhere, with the right title and caption for each. Use when the user wants to share a video, Reel, Short or TikTok across TikTok, Instagram Reels, YouTube Shorts, LinkedIn and Facebook Reels, or asks to "post this video everywhere".

    Also in 3 projects that use this

  • CodeWithSulemanSkill

    approval-workflow

    Manage human-in-the-loop approval workflows for sensitive actions like payments, emails to new contacts, social media posts, and other actions requiring human oversight.

    Also in 3 projects that use this

  • flintfromthebasementSkill

    write-blog-post

    Write or edit a long-form blog post in a specific author's voice, then run it through six editorial passes (substance, structure, human voice, de-AI scrub, house style + O'Reilly word list, fresh-context critic) before delivering. Handles drafting from a brief, filling an outline, editing a draft, refreshing an old post, and applying revision notes. Use when the user wants a blog post that sounds like a real person wrote it, not a one-shot generation.

    Also in 3 projects that use this

  • +8 more from posteverywhere

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 25 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read each <KEY>.md and compress it.

    line 35
  2. Very specific:

    No em-dash (—): use commas, colons, parentheses.

    line 51
  3. Distinctive:

    Do not invent a line for an issue you could not read, and do not guess from the key alone.

    line 63

“Common” is measured: kept by at least 6 in 10 of the 25 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Weekly-report lines from JIRA issues

Compress each issue into one line for the weekly-report spreadsheet: one line per cell, in the order the keys were given. Draft only, nothing is posted anywhere.

Step 0: Prereq

The jira-fetch skill, installed next to this one (this skill calls its helper). Its constraints apply: only publicly readable projects (CBRD, TOOLS, APIS, ...) can be read; internal-only projects such as CUBRIDQA fail with HTTP 401.

Step 1: Parse the keys

From $ARGUMENTS, take every PROJECT-NUMBER. Accept commas or spaces, a pasted issue URL, and lower case (apis-1111 -> APIS-1111). Drop duplicates and keep the order given: the report rows should match what the user typed.

Step 2: Fetch all of them in one call

bash ${CLAUDE_SKILL_DIR}/../jira-fetch/assets/fetch_jira.sh APIS-1111 TOOLS-4324 ...

The helper takes many keys at once, so call it once for the whole list. It writes ./jira/<KEY>.md (title as # heading, then the description). Skip any key whose .md already exists: do not re-fetch. A key that cannot be read is simply reported as missing, and the rest still succeed.

Step 3: Write one line per issue

Read each <KEY>.md and compress it. The line answers "what is this issue", not "what did I do" or "what is its status".

APIS-1088 JDBC 구버전 PROTOCOL 호환성 코드 제거
TOOLS-4888 CMT 단위 테스트 라이브러리 Java 8 지원 버전으로 업그레이드

Rules:

  • Form: <KEY> <요약>, key first, one space, then the summary. No trailing period (it goes in a cell).
  • 명사형 종결: end on a noun form ("추가", "제거", "업그레이드", "검토"), the usual weekly-report register.
  • Length: around 60 characters, 80 at the very most.
  • Content: 대상 + 무엇을 하는가. One thread only.
  • Never list the description's steps, checklists, sub-items, or affected files. Those belong in the issue, not the report line.
  • Do not just copy the title. Titles are often vague ([JDBC] PROTOCOL 호환성 제거 관련): use the description to make the line concrete. If the title is already specific and complete, reusing its substance is fine.
  • Drop the [AREA] bracket from the title; the key already identifies the area.
  • No em-dash (—): use commas, colons, parentheses.

Step 4: Output

Print the lines as one plain block in input order, nothing else interleaved, so the user can copy it straight into the sheet.

Then, if any key could not be read, list those separately with the reason and what would unblock them:

읽지 못함: CUBRIDQA-1509 (내부 전용 프로젝트, 내용을 알려주시면 그 줄만 채웁니다)

Do not invent a line for an issue you could not read, and do not guess from the key alone.

Notes

  • This skill keeps no history, so the same issue produces the same line every week. If the user wants the line to reflect only the latest change, they should say what changed and it goes into that line.
  • Progress and status are out of scope by design: the line describes the issue. If the user asks for status too, get it from them rather than assuming.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.