agentleFS
agiea-brainagiea-brain/agency-skills/skills/tapajyoti-das/content-brief/SKILL.md

content-brief

Skill1 starsChanged 17 days agoMITView on GitHub

Use this skill when a topic has been chosen and a writer needs to produce something that sounds like the firm rather than like anyone. Produces a brief they can work from without three follow-up questions: the reader in a line, the angle as a claim, the firm's actual position with sources, the structure marked for priority, the usable evidence, and what to avoid. Also use for "brief this for the writer", "what's the angle", "write the content brief", "hand this topic off".

21 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use competitor-gap, serp-analysis and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • DarynaRodriguezSkill

    competitor-gap

    Finds the terms rivals rank for and the site does not, confirms who the real organic competitors are, and returns a gap table split into terms to win, terms underperforming, and terms to concede.

    Also in 4 projects that use this

  • opencueSkill

    serp-analysis

    Use when the user asks to "analyze SERPs"; reviews ranking factors, features, intent, AI Overviews, and snippets. SERP分析/搜索结果

    Also in 3 projects that use this

  • akii-technologies-ltdSkill

    internal-linking

    Analyze and improve internal linking strategy. Use when the user asks about "internal links", "link structure", "site architecture", "link strategy", "orphan pages", "link equity", "page authority distribution", "anchor text", "topical clusters", "siloing", or wants to improve how pages connect.

    Also in 3 projects that use this

  • akii-technologies-ltdSkill

    keyword-clustering

    Cluster and organize keywords into topical groups for SEO. Use when the user asks to "cluster keywords", "group keywords", "organize keywords", "keyword mapping", "topic clusters", "keyword grouping", "build a content plan", "pillar pages", "topical authority", "semantic clustering", or pastes a list of keywords.

    Also in 4 projects that use this

  • silvainfmSkill

    schema-markup

    When the user wants to add, fix, or optimize schema markup and structured data on their site. Also use when the user mentions "schema markup," "structured data," "JSON-LD," "rich snippets," "schema.org," "FAQ schema," "product schema," "review schema," or "breadcrumb schema." For broader SEO issues, see seo-audit.

    Also in 6 projects that use this

  • indranilbanerjeeSkill

    keyword-research

    Research keywords via the connected data source: intent, gaps. Grouping → keyword-cluster. \"what keywords should we target\"

    Also in 7 projects that use this

The file

We split this skill into the rules it gives an agent

11 rules. 0 are common, 11 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 19 edited versions we read keep these.

  • 11

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the firm has no position, say so and offer two or three candidate angles for the owner to choose between.

    line 22
  2. Distinctive:

    Write the reader in one line: who they are, what they already believe about this topic, and what they are trying to do.

    line 24
  3. Distinctive:

    MUST find the firm's existing position before setting an angle.

    line 48
  4. Distinctive:

    MUST write the angle as a claim, not a subject.

    line 49
  5. Distinctive:

    MUST attach a source to the firm's stated position.

    line 50
  6. Distinctive:

    MUST mark which sections carry the argument.

    line 51
  7. Distinctive:

    MUST flag evidence that needs client approval.

    line 52
  8. Distinctive:

    MUST name what an already-published piece covers.

    line 53
  9. Distinctive:

    NEVER invent the firm's position.

    line 54
  10. Distinctive:

    NEVER list evidence that cannot be confirmed.

    line 55
  11. Distinctive:

    NEVER write the piece. This is the brief.

    line 56

“Common” is measured: kept by at least 6 in 10 of the 19 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Applies once the topic is decided and before anyone drafts. Produces the brief, not the piece.

The play

  1. Find what the firm genuinely thinks about this topic before setting an angle. Past calls, posts, client work, anything the founder has said out loud. This is the step that decides whether the piece is worth publishing, because the firm's real position is the only thing in the piece a competitor cannot also write.
  2. If the firm has no position, say so and offer two or three candidate angles for the owner to choose between. An invented point of view gets published, gets challenged, and then has to be walked back in public.
  3. Write the reader in one line: who they are, what they already believe about this topic, and what they are trying to do. Not a persona document. One line a writer can hold in their head while drafting.
  4. Set the angle as a claim, not a subject. "Why retainers break at fifteen clients" is an angle. "Agency scaling" is a topic, and handing a writer a topic is how a brief produces a survey of everything anyone has said.
  5. State the firm's position in two or three sentences, with the source attached. If it came from a call or a post, name it so the writer can go read the original rather than paraphrasing a paraphrase.
  6. Build the structure as sections with one line each on what the section does. Mark which sections carry the argument and which are supporting, so a writer cutting for length cuts the padding and not the point.
  7. List the evidence actually available: results, client examples, data the firm holds. Mark anything that needs client approval before use. A writer who discovers at draft stage that the best example cannot be named rewrites the whole middle.
  8. List what to avoid: claims the firm cannot make, positioning it has moved away from, words it does not use, and what an existing published piece already covers.
  9. Draft the opening line or two in the firm's voice. The open is where drafts go generic, and giving the writer a starting note is cheaper than editing a generic one later.

What good looks like

  • First thing I check that most people skip: whether the brief contains a position somebody could disagree with. If it does not, whatever gets drafted will default to what is already on the public internet, and that is average by definition.
  • The mediocre version: a topic, a word count and a keyword, with the thinking left to whoever writes it. The writer is then being asked to invent the firm's point of view, which is not their job and not something they can do.
  • I know it is right when the writer does not come back asking what we think. If they have to ask, the brief did not contain the one thing only we could supply.
  • Second test: the position has a source attached, a specific call or post, so the writer reads the original instead of a paraphrase of a paraphrase.
  • Red flag: the angle could have been written by somebody who has never spoken to a client. That is the test, and most briefs fail it.

Rules

  • MUST find the firm's existing position before setting an angle.
  • MUST write the angle as a claim, not a subject.
  • MUST attach a source to the firm's stated position.
  • MUST mark which sections carry the argument.
  • MUST flag evidence that needs client approval.
  • MUST name what an already-published piece covers.
  • NEVER invent the firm's position. Leave it open and offer options.
  • NEVER list evidence that cannot be confirmed.
  • NEVER write the piece. This is the brief.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.