skills/zudoesa-articlify/SKILL.md
Convert conversation context into an esa article via the zudoesa-writer subagent. ONLY invoke when the user explicitly asks — NEVER proactively propose. Triggers: 'write esa article', 'esa記事', 'esaに書いて', 'articlify for esa', or /zudoesa-articlify. Gathers context, creates a writing brief, delegates to the writer subagent.
npx skillsauth add takazudo/claude-resources zudoesa-articlifyInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Convert the current conversation into an esa article by crafting a detailed writing brief and delegating to the zudoesa-writer subagent.
--conversationWhen $ARGUMENTS contains --conversation, the article must preserve the actual
conversation as-is. This means:
NEVER summarize the conversation. Reproduce the actual dialogue flow faithfully.
Keep casual utterances. Words like 「なるほど」「ふーん」「どう思う?」「OK」
「hum...」are meaningful conversational texture — they make the article sound natural and human. Removing them makes it look AI-auto-written.
Minimal rewriting only. Typo fixes and light formatting are OK. Do NOT
restructure, condense, or rephrase the user's words beyond that.
PRESERVE THE ORIGINAL LANGUAGE. DO NOT TRANSLATE. This is critical. If the
conversation was in English, keep it in English. If it was in Japanese, keep it
in Japanese. If it was mixed, keep both languages as-is. Translating the
conversation to Japanese destroys the original text — it is a total loss of the
source material the user wanted to preserve. The whole point of --conversation
is to capture the raw dialogue, and translation defeats that purpose. The
surrounding frontmatter title and any minimal scaffolding headings MAY be in
Japanese, but the conversation body itself must remain in its original language.
Include the brief in the writing prompt with explicit instruction:
"This is a conversation-style article with --conversation mode. Preserve the
dialogue verbatim IN THE ORIGINAL LANGUAGE. Only fix typos and apply vocabulary
rules. Do NOT summarize, restructure, or translate. If the conversation is in
English, the article body must remain in English."
Review the conversation history and identify:
If images were provided in the conversation (attached screenshots, diagrams, etc.):
Determine the article slug from the topic (e.g., 20260209-package-json-organization)
Create the image directory in the esa repo:
mkdir -p $HOME/repos/w/esa/doc/public/img/articles/YYYYMMDD-slug/
Copy each image to that directory with a descriptive filename:
cp /path/to/source/image.png $HOME/repos/w/esa/doc/public/img/articles/YYYYMMDD-slug/descriptive-name.png
Record the image paths for the writing brief. The markdown reference format is:

Create a detailed, self-contained prompt that the writer subagent can use without any conversation context. The brief must include:
The brief should be written so that someone with zero context could write the full article from it alone.
Use the Agent tool to spawn the zudoesa-writer subagent with run_in_background: true so the user is not blocked during writing:
Agent tool:
subagent_type: zudoesa-writer
run_in_background: true
prompt: [the detailed writing brief from Step 2]
The subagent will:
--conversation is specified)sidebar_position using the formula 999999999999 - YYYYMMDDHHMM (ensures newest articles appear first)After the subagent completes, read the created article file and verify that:
sidebar_position is present in the frontmatter999999999999 - YYYYMMDDHHMMIf sidebar_position is missing or incorrect, fix it directly. This is critical — without it, the article appears at the bottom of the sidebar instead of the top.
After the subagent completes, report:
development
Link Claude Code skill names mentioned in a CodeGrid article (data/{series}/{n}.md) to the author's public claude-resources repo, pinned to the latest commit hash so links don't rot. Use when: (1) user says 'linkify cc resources', 'link the skills', 'link skill names', or invokes /dev-linkify-cc-resources; (2) editing a CodeGrid article that mentions `/commits`, `/pr-complete`, `/skill-creator` or other Claude Code skills and they should point to claude-resources. Only links skills that actually exist in the public repo; skips hypothetical examples and code blocks.
development
Second opinion from Claude Opus on a plan or approach. Use when: (1) Planning phase of /big-plan needs a higher-quality review than /codex-2nd / /gco-2nd / /gcoc-2nd, (2) User says 'opus 2nd' or 'opus opinion', (3) Wanting Anthropic's larger model to critique a plan. Spawns a general-purpose Agent with model: opus that reads the plan file and returns structured feedback. Anthropic quota — not free.
tools
AI-based testing via subagent + a per-task test-flow skill. Use when the user wants to verify something that mechanical assertions can't fully capture — image recognition, visual size/position comparison, animation smoothness, multi-step manual flows that need AI judgment. Triggers: 'AI-based test', 'AI test', 'visual verify', 'image recognition test', 'manual operation test', 'human-eye check', 'verify visually', 'compare screenshots', 'looks the same', 'looks correct'. The skill's job is to (1) author a focused test-flow skill that captures the exact procedure + verdict criteria, then (2) dispatch a verification subagent via the Agent tool that loads BOTH the test-flow skill AND a browser-driving skill (/verify-ui primary, /headless-browser fallback) so the subagent has clear context and consistent verdicts. NEVER uses `claude -p` — subagent dispatch goes through the Agent tool exclusively.
development
End-of-workflow audit of touched GitHub issues, PRs, and branches via a Sonnet subagent. Use when: (1) /big-plan, /x-as-pr, or /x-wt-teams finishes its main work and needs to verify every touched resource is in the right state (closed when done, kept when ongoing, deleted when dead), (2) User says 'cleanup resources', 'audit cleanup', or 'check what should be closed', (3) A long workflow ends and the manager wants a structured paper trail of what it closed/kept/deleted. Auto-execute by default — the Sonnet agent proposes, the manager (you) executes safe actions and prints a final report.