Switches every call site to `node scripts/newsletter` and, in the same pass,
fixes three structural problems in the skill layer.
The seven subcommands were spelled out in five files; they are now enumerated
once in docs/newsletter/engine-commands.md, and every other mention is a link
except where a skill inlines the one or two commands it actually invokes. The
shared post mechanics move out of mt-add-url's directory into docs/newsletter/,
so no skill owns another skill's documentation and both runtimes reach it by a
repository-relative path. The Codex adapters become symlinks to their canonical
counterparts, which removes the parallel frontmatter that could drift.
Two skills are renamed for a uniform mt-<verb>-<object> scheme: mt-add-post
becomes mt-add-article, since it adds an article to a post, and mt-webfetch
becomes mt-fetch-url. The other four already conformed. Note that $mt-add-post
and mt-webfetch no longer resolve; no alias directories are left behind, because
two names for one skill is the duplication this change removes.
Trigger wording in the frontmatter descriptions is left alone apart from the
renamed tokens and the corrected fetch-tier summary: those strings are how the
runtimes decide whether to invoke a skill.
Setup documentation now states the npm ci prerequisite. The engine has
dependencies, so unlike its predecessor it does not run on a bare clone.
Add a reader-proxy tier after defuddle, stop skipping URLs that only fail a
plain classifier fetch, let a session pin an earlier draft as the target post,
and tighten Substack image candidate handling (dedupe, stable numbering,
reuse a resolved source post across a batch).
One Go binary with a subcommand per former script, invoked as
'go run ./scripts/newsletter <command>' from repo root. Stdlib only;
publications config embedded via go:embed (go run recompiles on edit).
Behavior parity verified side-by-side before deleting the JS —
see plans/reports/parity-260818-newsletter-go-migration-report.md.
Permissions: allow 'Bash(go *)', drop 'Bash(node *)' and the redundant
'Write(content)' rule (Edit rules cover all file-editing tools).
Extract newsletter scripts to a neutral scripts/newsletter/ engine and add
side-by-side support for all three AI coding tools off one source of truth.
- Move 9 scripts + substack config from .claude/skills/**/scripts to
scripts/newsletter/ (history preserved); fix PROJECT_ROOT depth and
cross-require/config paths; repoint all SKILL.md invocations
- Add canonical AGENTS.md; reduce CLAUDE.md to an @AGENTS.md import
- Add opencode.json (permissions, no MCP); skills auto-discovered in place
- Add codex/prompts/*.md (6 prompts) + copy installers (install.sh/.ps1)
- Add docs/multi-tool-usage.md (setup, per-tool invocation, teardown) + README pointer
Moves URL processing workflow from AGENTS.md into a dedicated skill at
.agents/skills/add-post. Simplifies AGENTS.md to only contain project info
and development server instructions. Creates symlink in .claude/skills/ for
skill discovery.
Add new newsletter post (content/post/2026/02/01/index.md) containing Newsletter #78 summaries and highlights. Expand and clarify language policy and Vietnamese writing guidelines in AGENTS.md (stronger PRIMARY Vietnamese rule, explicit list of allowed English terms, common translations, required Vietnamese action verbs, tone/quality checks and a Vietnamese ≥99% checklist item). Also tweak wording about English tech terms and add mcp__acp__Bash to .claude/settings.local.json permissions.
Added the 77th newsletter post (Vietnamese) covering topics on error handling, clock synchronization, Java roadmap, Kotlin adoption, Rust vs Go, Go dependencies, go.sum vs go.mod, and Forgejo Actions notifications. Updated AGENTS.md to clarify Vietnamese writing guidelines, emphasizing maximum translation of technical terms. Extended allowed skills in .claude/settings.local.json to include 'mcp__acp__Write' and 'mcp__acp__Edit'.
Added the Newsletter #75 post with technical interview, microservices, Linux kernel, and load balancer insights. Updated AGENTS.md to clarify language usage and remove command examples. Extended allowed Bash commands in settings.local.json to include powershell.
Added the content for Newsletter #69 in Vietnamese, covering topics such as Netflix's real-time distributed graph, incremental architecture, Java collection interfaces, fixit weeks, productivity math, tech predictions, Linux reflections, AI agent challenges, and Java zero-copy file transfer. Also removed a redundant instruction from AGENTS.md regarding reviewing content and adding tags.
Added detailed documentation for the /addtags command in .claude/commands/addtags.md, outlining tag generation and update workflow for newsletter posts. Expanded and clarified AGENTS.md with improved project info, step-by-step URL processing, content and error handling guidelines, and best practices for AI code assistants working with the Hugo blog.
Added the content for Newsletter #63 covering topics such as functional core/imperative shell, code review strategies, software quality decline, agentic throwaway code, engineering productivity, useful shell scripts, SQL anti-patterns, and building a key-value database. Also updated AGENTS.md to clarify that English technical terms should be used where juniors can understand.
Added new newsletter post for 2025-09-10 with related images. Removed unused configuration files (.claude/settings.local.json, .mcp.json, .serena/project.yml) and updated AGENTS.md to remove obsolete configuration and resource sections.
tiennm99