# Topic Scout > Find new topics worth covering and log them to a tracker, deduplicated and scored. Rotates through the beats in references/beats.md, walks the primary sources listed there, drops anything already covered or already expired, and records only the top few. Use for "find me something to post about today", "what should I cover this week", "any new topics", "fill the idea backlog", "update the topic tracker", and for a scheduled daily run. Researching and verifying an already-chosen topic is topic-brief instead — this skill is the step before that, deciding what to work on at all. - Skill: `chanuk0/topic-scout` (Agent Skill, multi-file: 6 files) - Install (CLI): `npx skillmds@latest add chanuk0/topic-scout` - Raw SKILL.md: https://api.skillmd.com/api/skills/chanuk0/topic-scout/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Product & Planning - Author: chanuk0 (https://skillmd.com/u/chanuk0) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/chanuk0/topic-scout --- # Topic Scout **Finds what to cover and writes it to your idea tracker.** Built to run once a day. Where it sits in the pipeline: ```text [this skill] scout → idea tracker ↓ a human picks one and promotes it production queue ↓ topic-brief (verify → one-page brief) ↓ blog-post / carousel-post ``` **This skill never writes to the production queue.** It reads the queue only to check for duplicates. A human promoting an idea is the gate; if the model skips that gate, unverified topics end up in the production queue. ## The five ways this fails (all five are defended below) 1. **Suggests something already covered** → don't skip the three-layer duplicate check. 2. **Suggests something already over** → a candidate whose deadline you couldn't confirm does not get recorded. 3. **Mines the same beat every day** → follow the rotation from `axis.py`. Don't pick by feel. 4. **Invents something plausible with no source** → no primary-source URL, no record. 5. **Ranks by intuition** → score only with the rubric in `references/scoring.md`. ## Reference routing | When | Document | | --- | --- | | Which sources to open for each beat | `references/beats.md` | | How to score, and what disqualifies a candidate | `references/scoring.md` | | Tracker fields and how to write a row | `references/tracker.md` | | Today's beats and their sources | `python scripts/axis.py --today` | | Duplicate check | `python scripts/dedup.py` | ## Procedure — once per run ### 1. Pick the beats ```bash python scripts/axis.py --today ``` Prints the beats to mine today and the source rows for each. **Mine only those beats.** Do not swap a beat because another one "looks more interesting today" — once the rotation breaks, you are back to one beat forever within a few days. If the user names a beat, override with `--beat ""` and leave the rotation state alone. ### 2. Load existing state (for the duplicate check) Pull the **names of every row** from both lists — your production queue and your idea tracker. `references/tracker.md` has the field names. - Production queue — **every row**, whatever its status. A row sitting at "candidate" is still a topic you already have. - Idea tracker — every row. Re-suggesting yesterday's suggestion is the most common way this skill wastes a run. ### 3. Collect — walk the primary sources Open the sources for each of today's beats **from the top down**. In each one you are looking for exactly one thing: **something live right now that gives your audience real money, time, or access.** - Fetch the page. If the body doesn't come back because the page renders client-side, reopen it with a browser tool rather than giving up. - If walking the sources isn't enough, search — but put **the beat name plus the current month** in the query. Do not run queries that leave the beat. - **Do not scrape sites behind a login.** It breaks their terms and the data is unreliable. Gather 3–5 candidates per beat, 10–15 total. Don't filter yet. ### 4. Filter — most candidates die here Apply in order. Log the reason for each rejection; don't record rejected candidates. | # | Rejected when | Why | | --- | --- | --- | | F1 | No primary-source URL | Nothing can be verified | | F2 | Already closed, expired, or fully subscribed | The worst possible accident | | F3 | Already in the queue or tracker (`dedup.py`) | Duplicate | | F4 | Audience doesn't match yours | Not your readers | | F5 | Benefit can't be expressed as an amount or a time saved | No number for the hook | | F6 | Geographically narrower than your audience | Reach doesn't justify it | Always run F3 through the script: ```bash python scripts/dedup.py --existing existing.json "candidate one" "candidate two" ``` Drop anything marked `duplicate`. Keep anything marked `similar`, **noting what it is similar to** — the next round of a recurring thing is a new topic, not a duplicate. ### 5. Score Use only the rubric in `references/scoring.md`: beat base score plus adjustments. **Never raise a score because a deadline is close.** Urgency belongs in the deadline field, where it breaks ties; it is not a ranking input. `scoring.md` explains why. ### 6. Record Write **only the top 3–5** to the idea tracker. Write all ten and nobody reads any of them. Follow the row format in `references/tracker.md` exactly. ## Reporting Leave only this in chat. Don't paste candidate write-ups — the tracker is the record. ```text [scout YYYY-MM-DD] beats: recorded N: (score) / (score) / (score) rejected M: F1 a · F2 b · F3 c ... blocked sources: ``` ## Never - Create or edit rows in the production queue (read-only from here) - Fill in an amount, date, or eligibility rule that isn't in the primary source - Scrape pages behind a login wall - Write hooks, scripts, or outlines here (that's `blog-post` / `carousel-post`) - Write a full brief (that's `topic-brief` — scouting stops at a one-line summary)