reactive-comment
Triage inbound journalist source queries and draft a response only when the user's expertise is a real fit. Runs each query through proven source-request lenses (4-gate fit triage, credential-standing test, deadline read, BLUF/inverted-pyramid drafting), kills weak fits, asks for missing proof, and never auto-sends.
Profile →npx skills add elvisun/newsjack --skill reactive-comment --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
The Reactive Comment skill triages inbound journalist source queries and drafts a response only when the user's expertise is a real fit. It processes the query through four gates (credential → specs → outlet → strategic value), checks credential standing, reads the deadline, and applies BLUF/inverted-pyramid drafting. If any gate fails, it kills the fit; if proof is missing, it asks for exact missing proof and never auto-sends.
How it works
- It takes one inbound journalist query plus the user's profile. It first runs the query through the 4-Gate fit triage to verify credentials, specs, outlet quality, and potential value. If any gate fails, it Kill; if all pass, it then uses the credential-standing test to confirm who would speak, why they’re credentialed, and the relationship. It applies the deadline-reality read to assess timeliness and window. If the fit passes all lenses, it drafts using BLUF/inverted-pyramid principles to produce a 3-5 sentence body (150 words or fewer) with one substantive claim and an offer to go on record, followed by the profile's contact_block verbatim. It must also indicate the source of every claim (profile proof point, journalist byline, or USER MUST CONFIRM). If information is missing, it returns Ask for proof.
When to use it
Use when a user wants to know whether to respond to a HARO, Source of Sources, Qwoted, Featured, Help A B2B Writer, JournoRequest, or similar source request and wants to know whether to respond or wants a response drafted.
What it can touch
The skill uses tools/inputs described in the workflow: it references profile fields (name, title, company, expertise_areas, proof_points, do_not_comment_on, contact_block), and query fields (source, journalist_name, journalist_outlet, query_text, deadline_iso, requirements, query_url, received_at_iso). It Drafts only if all fit lenses pass and does not auto-send.
Caveats
The process enforces first-hand expertise; it will not draft if the profile lacks required standing or if any vetoes are triggered (do_not_comment_on, outlets_to_skip, cap exceeded, deadline passed, or fabrication risk). It requires exact missing proof to be provided when Ask for proof is chosen.
# Reactive Comment You are the **Reactive Comment** gate inside newsjack.sh. The user gives you one inbound journalist query plus their expertise profile. Your job is to decide whether they should respond. If the fit is real, draft a tight reply for manual review. If the fit is weak, kill it. If proof is missing, ask for exactly what you need. You are the opposite of AI tools that spray automated expert replies into journalist inboxes. You are the friction. You kill more queries than you draft. ## Your Voice - Cut but never cruel. "This is not your fight" beats "bad pitch." - Specific over general. Name the mismatch: title, topic, proof point, deadline, outlet, cap, or source-platform rule. - No hedging. Default to Kill; a draft is earned, not assumed. - No LinkedIn positivity. A tier-one outlet does not rescue a bad fit. - Protect the user from their own appetite for coverage. ## Doctrine If `skills/ETHICS.md` and `skills/WHY-NOT-SPAM.md` exist in this repo, follow them. Either way, hold the line: this skill answers a query *only* when the user has first-hand expertise. Answering outside their field burns the journalist (they cite the user's credentials and look foolish when an un
- Your Voice
- Doctrine
- The Triage & Draft Toolkit — how to decide and draft
- Fit lenses — decide whether to respond at all
- Draft lenses — how to write the winning answer (only once fit passes)
- Inputs
- Decision
- Flow
- Step 1 - Decay (deadline-reality read)
- Step 2 - Anti-Spray Cap (selective, not exhaustive)
- Step 3 - Fit (4-Gate + standing + ethics)
- Step 4 - Draft Only When Earned (BLUF + skeleton)
- Step 5 - Pre-Ship Check
- Quality Bar
What does the reactive-comment skill do?
Triage inbound journalist source queries and draft a response only when the user's expertise is a real fit. Runs each query through proven source-request lenses (4-gate fit triage, credential-standing test, deadline read, BLUF/inverted-pyramid drafting), kills weak fits, asks for missing proof, and never auto-sends.
How do I install it?
Run `npx skills add elvisun/newsjack --skill reactive-comment --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From elvisun/newsjack, a repository with 620 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.