brief-my-writer
Skill0 starsChanged 4 months agoMITView on GitHub
Turn one blueprint node into a complete content brief: the revenue argument, the buyer's own words that must appear, the proof to cite, the internal links, the schema, and what the piece will not say. Refuses to brief a node whose SERP has never been checked.
In this repository26 other files it gives its agents.
- beat-my-competitorsSkill
- can-i-actually-rankSkill
- check-before-i-publishSkill
- explain-this-numberSkill
- find-my-quick-winsSkill
- follow-the-moneySkill
- get-cited-elsewhereSkill
- get-mentioned-by-aiSkill
- know-my-buyerSkill
- make-it-sound-humanSkill
- make-me-quotableSkill
- map-my-siteSkill
- pick-my-battlesSkill
- put-it-on-autopilotSkill
- rainmakerSkill
- revive-old-pagesSkill
- say-it-their-waySkill
- show-me-progressSkill
- show-up-in-communitiesSkill
- spread-one-piece-everywhereSkill
- stop-losing-visitorsSkill
- unblock-my-money-pagesSkill
- what-actually-workedSkill
- what-changed-in-searchSkill
- what-to-target-nextSkill
- write-the-pageSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 22
Run rainmaker context --check first.
- Very specific: line 30
Only the data/ files listed in this skill's Consumes table.
- Very specific: line 32
If strategy.json.context_hash does not match the current hash of context/business.md, say exactly:
- Very specific: line 38
If context/business.md carries confidence: stub, continue, and stamp every output with: "Built on a stub context.
- Distinctive: line 74
Never brief a node the gate refused.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
brief-my-writer
Context load
Run rainmaker context --check first. It prints what exists, what is stale, and exits 1 if anything this skill requires is missing.
Then read, in this order:
context/business.mdin full. If absent, stop: "No business context. Runrainmaker audit, then theknow-my-buyerskill."context/voice.mdif this skill writes prose. If absent, stop and say so.context/glossary.mdif this skill names products, features or competitors.data/strategy.jsonif this skill reads or writes strategy.- Only the
data/files listed in this skill's Consumes table. Never crawl or call an API the core already covers.
If strategy.json.context_hash does not match the current hash of context/business.md, say exactly:
"Business context was edited after the strategy was written. Re-run know-my-buyer, or run rainmaker context --sync to accept the prose as authoritative."
Then stop.
If context/business.md carries confidence: stub, continue, and stamp every output with: "Built on a stub context. Nothing in it came from a buyer. Run know-my-buyer to replace it."
Consumes
| File | Why | If missing |
data/blueprint.json node | parent, cluster, tier, SERP verdict | run map-my-site first |
data/strategy.json | pain points, proof, buyer language | run know-my-buyer first |
context/voice.md | tone the brief must specify for the writer | required, see context load |
data/snapshots/<latest>/crawl.json | candidate internal link sources | run rainmaker audit |
Produces
briefs/<slug>.md.
Concurrency
Batch mode fans out one agent per brief, maximum 5. This is one of the three permitted fan-out points in the system.
Refuses when
The target node's serp_verdict is unchecked, KILL, or CONDITIONAL with no recorded resolution. Call src/blueprint/gates.ts canBrief(node) and print its reason verbatim rather than re-deriving the same judgment by eye.
Procedure
- Confirm
canBrief(node)allows it. If not, stop and print the reason, naming the exact command that unblocks it (rainmaker serp, thencan-i-actually-rank). - State the node id, its parent path, its cluster and pain point ids, its tier, and the revenue argument in one sentence: why this page's tier and score justify the effort.
- State the target query, current position if any, and the format the SERP capture says Google rewards, with the competing URLs.
- Pull the buyer's own words from
strategy.json.pain_points[].buyer_languagethat must appear in the piece, quoted exactly. - Cite proof ids with their source URLs. A brief citing no proof fails preflight; do not write one anyway and hope the writer finds proof later.
- Name 3 or more internal link sources from
crawl.json, matched to the node'slinks_upandlinks_acrossin the blueprint, with the target URL each should link from. - State the chosen schema type, the named author and their first-hand evidence, and 3 to 7 standalone claim sentences for extractability.
- Copy the "What we will not say" section relevant to this topic from
business.mdverbatim.
Decision rules
- Never brief a node the gate refused. There is no override; a node without a resolved verdict gets a resolved verdict before it gets a brief.
- A brief with zero proof ids is incomplete, not lenient. Say so and stop rather than shipping it.
- Internal links must be real URLs from
crawl.jsonor real planned nodes fromblueprint.json, never invented paths.
Output
## Brief: <node.path>
Cluster: <id> Pain points: <ids> Tier: <n> Revenue argument: <one sentence>
Target query: <q> Current position: <n or "none"> Rewarded format: <format>
Competing: <url>, <url>
Must include, verbatim: "<buyer language>"
Proof to cite: <id>: <claim> (<source url>)
Internal links: from <url> to this page, from <url> to this page, from <url> to this page
Schema: <type> Author: <name>, <first-hand evidence>
Standalone claims: <sentence>, <sentence>, <sentence>
Will not say: <text from business.md>Done when
canBrief passed or the skill stopped with its reason, the brief cites 3 or more internal link sources, at least one proof id, and the exact buyer-language quotes to include.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

