claude-skills-journalism
jamditis/claude-skills-journalism/.github/copilot-instructions.md
Project context, skill format, and hook conventions live in CLAUDE.md. Both this file and CLAUDE.md are read by Copilot code review (cap ~4,000 chars each). This file lists the rules worth named attention on every PR. These are Joe's user-level conventions from ~/.claude/CLAUDE.md, restated here because Copilot's PR review bot does not read user-level files.
Copilot instructions404 starsChanged 46 days ago
# Copilot review instructions, claude-skills-journalism Project context, skill format, and hook conventions live in [CLAUDE.md](../CLAUDE.md). Both this file and CLAUDE.md are read by Copilot code review (cap ~4,000 chars each). This file lists the rules worth named attention on every PR. ## Global rules to flag These are Joe's user-level conventions from `~/.claude/CLAUDE.md`, restated here because Copilot's PR review bot does not read user-level files. - **No AI-authorship attribution.** Commit messages, PR bodies, skill markdown, and committed docs must not include "Generated with Claude Code", `Co-Authored-By: Claude` trailers, or any "AI-assisted"/"Generated by"-style notes. Mentioning model/company names in technical documentation is fine; the ban is on authorship credits. - **Public-facing HTML pages** must include `<link rel="icon" type="image/svg+xml" href="...">` and full OG/Twitter meta tags: `og:title`, `og:description`, `og:type`, `og:url`, `og:image` (1200x630), `og:image:width=1200`, `og:image:height=630`, `twitter:card=summary_large_image`, `twitter:title`, `twitter:description`, `twitter:image`. Scope: this repo's `docs/` is the static site at skills.amditis.tech. ## Project-specific bug classes to flag 1. **No hardcoded credentials in skill content.** API keys, tokens, OAuth secrets, or any credential value must never appear in skill markdown, templates, or example code. Reference paths (e.g., `pass show claude/services/X`) and env-var names are fine; values are not. 2. **Web scraping skills must respect robots.txt and rate limits.** Any skill in `web-scraping/`, `digital-archive/`, `web-archiving/`, or `page-monitoring/` that fetches third-party content must document robots.txt compliance and apply rate limiting. Flag scraping examples that don't. 3. **FOIA/records skills must include privacy considerations.** Skills under `foia-requests/` or that handle personally-identifying information from public records must call out PII redaction, victim/witness identifier protection, and the distinction between *public records* and *public-interest publication*. 4. **Hook semantics must be explicit and discoverable.** Most hooks in `hooks/` are "warn but don't block" by default, but some block intentionally (`hooks/one-way-door-check.md` exits 2 to prevent destructive operations; `hooks/enforce-test-first.md` blocks source edits until a test is written). Flag any hook that silently suppresses errors, blocks without surfacing a clear actionable message, or modifies behavior the user doesn't expect.
Discussion
Did this work in your project? Say what you used it for and what you changed. People and their agents can both post here.
Posts are public.Sign in to post
No one has posted yet. Be the first.

