agentleFS
peterbamuhigirepeterbamuhigire/proposal-skills/skills/writing-content/blog-writer/SKILL.md

blog-writer

Skill11 starsChanged 16 days agoMITView on GitHub

Use when drafting, revising, or finalising a publishable blog post, article, guide, case study, or thought-leadership piece; use blog-idea-generator when only topic discovery is required.

33 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use aminer-data-search, auto-target-tracker and 10 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.
  • dav-niu474Skill

    aminer-data-search

    使用 AMiner 开放平台 API 进行学术数据查询与分析。当用户需要查询学者信息、论文详情、机构数据、期刊内容或专利信息时使用此 skill。 触发场景:提到 AMiner、学术数据查询、查论文/学者/机构/期刊/专利、学术问答搜索、引用分析、科研机构分析、学者画像、论文引用链、期刊投稿分析等。 支持 6 大组合工作流(学者全景分析、论文深度挖掘、机构研究力分析、期刊论文监控、学术智能问答、专利链分析)以及 28 个独立 API 的直接调用。 即使用户只说"帮我查一下 XXX 学者"或"找找关于 XXX 的论文",也应主动使用此 skill。

    Also in 4 projects that use this

  • dav-niu474Skill

    auto-target-tracker

    自动目标进度追踪器。在对话中检测到目标相关图片(笔记、进度、截图、记录)时,自动调用 VLM 识别关键信息并记录到目标日记。适用于学习管理、健身追踪、工作进度、习惯养成、创作记录等所有目标管理场景。

    Also in 4 projects that use this

  • Liang-MHSkill

    stock_analysis

    获取 A 股、基金和港股的实时行情和技术分析数据

    Also in 4 projects that use this

  • +9 more from dav-niu474

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 31 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use blog-idea-generator when the task ends at topic options, angles, or a content backlog.

    line 24
  2. Distinctive:

    Do not write source-dependent claims when the evidence pack is missing or unverifiable.

    line 25
  3. Distinctive:

    Read and search are required.

    line 50
  4. Distinctive:

    Stop when a load-bearing claim, quotation, case, or personal experience cannot be supported.

    line 70

“Common” is measured: kept by at least 6 in 10 of the 31 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

Blog Writer

Acknowledgement: Shared by Peter Bamuhigire, techguypeter.com, +256 784 464178.

Turn an approved content brief and evidence set into an authored article with a clear reader promise, defensible claims, and publication-ready structure.

<!-- dual-compat-start -->

Use When

  • Draft or substantially revise a blog post, article, tutorial, opinion piece, case study, or long-form guide.
  • Convert an approved topic and evidence pack into publishable content.

Do Not Use When

  • Use blog-idea-generator when the task ends at topic options, angles, or a content backlog.
  • Do not write source-dependent claims when the evidence pack is missing or unverifiable.

Inputs

ArtefactSource/providerRequired?Missing-input behaviour
Content brief, audience, and publication goalClient or content leadYesStop and return the minimum questions needed to establish the reader promise.
Approved angle and evidence packblog-idea-generator, research, or subject expertYes for factual contentNarrow the article or flag claims as not assessed; do not invent citations or experience.
Voice, length, SEO, and publication constraintsBrand or editorConditionalState assumptions and avoid claiming brand or search compliance.

Outputs

ArtefactConsumerAcceptance condition
Publication-ready articleEditor and intended readerThe opening earns attention, the body fulfils one reader promise, claims are sourced or qualified, and the ending gives a useful next step.

Evidence Produced

EvidenceConsumerAcceptance condition
Claim and source checkEditorEvery load-bearing factual claim maps to a source or an explicit qualification.
Editorial quality checkPublisherStructure, voice, links, metadata, and unresolved edits are recorded.

Capability Contract

Read and search are required. Editing is allowed for authorised drafting and revision. Network research, publishing, image licensing, paid promotion, external messages, and claims of personal experience require explicit authority and evidence.

Degraded Mode

Fallback: when research, subject expertise, brand guidance, or publishing tools are unavailable, return the narrowest useful qualified draft, mark source and publication checks not assessed, and do not invent facts, quotes, experience, or SEO results.

Decision Rules

Condition or choiceActionFailure or risk avoided
Reader needs a practical sequenceUse a guide or tutorial structure with tested stepsDecorative advice with no usable path
Claim depends on data or current factsVerify and cite it at the point of claimConfident wrongness
Topic is opinion-ledState the thesis, evidence, countercase, and limitsViewpoint-free filler
Only ideas are requestedRoute to blog-idea-generatorPremature long-form drafting

Workflow

  1. Confirm the audience, reader promise, angle, evidence, voice, and publication constraints.
  2. Select a structure that matches the reader's job and outline only sections that advance it.
  3. Draft with specific evidence, authored reasoning, varied rhythm, and explicit hard cases.
  4. Stop when a load-bearing claim, quotation, case, or personal experience cannot be supported.
  5. Recover by verifying, qualifying, removing, or reframing the affected passage.
  6. Edit for logic, voice, scanning, links, metadata, and the anti-slop gate before handoff.

Quality Standards

  • The article makes one defensible promise and fulfils it without padded sections or search-engine mimicry.
  • Sources, examples, counterarguments, edge cases, and the writer's actual point of view are visible.

Anti-Patterns

  • Opening with a generic statement about a changing world. Fix: begin with the reader's concrete problem, tension, or evidence.
  • Adding statistics without a source. Fix: cite a verified source or remove the number.
  • Writing five interchangeable sections to reach a word count. Fix: keep only sections that advance the reader promise.
  • Presenting borrowed experience as personal. Fix: attribute the case or label it as an example.
  • Optimising keywords before the argument works. Fix: establish substance and reader usefulness first.

Worked Example

For an article on tender pricing, lead with the mismatch between proposed staff-days and fee totals, show a small traceable calculation, explain the evaluator risk, cover the case of reimbursables, and end with a pre-submission reconciliation check. Do not pad it with generic claims about competitive markets.

References

  • Comprehensive blog-writing guide
  • Editorial standards
  • Writing craft
  • Blog idea generator
  • Anti-slop guardrail
<!-- dual-compat-end -->

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.