long-form-content
Skill37 starsChanged 37 days agoMITView on GitHub
Use when writing a researched article, blog post, or long-form piece. Covers building an argument, researching and citing, structure, and writing something with a point rather than a survey. Trigger on "write a blog post about", "turn my research into an article", "write an essay arguing that". Do not use for polishing an existing draft — see the editing skill; for developer docs, see the technical-documentation skill.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- Xipher-Labs/walter-ostheir own version, first seen May 21, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- Xipher-Labs/walter-os★ 8same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository137 other files it gives its agents.
- agent-instructionsSkill
- agent-memorySkill
- hooksSkill
- plugin-developmentSkill
- skill-authoringSkill
- skill-reviewSkill
- slash-commandsSkill
- subagentsSkill
- agent-designSkill
- context-engineeringSkill
- fine-tuningSkill
- llm-cost-optimizationSkill
- llm-evaluationSkill
- llm-integrationSkill
- mcp-serverSkill
- ml-pipelineSkill
- model-selectionSkill
- prompt-engineeringSkill
- ragSkill
- structured-outputSkill
- api-designSkill
- background-jobsSkill
- cachingSkill
- djangoSkill
- event-driven-architectureSkill
- fastapiSkill
- graphqlSkill
- microservicesSkill
- nestjsSkill
- realtime-websocketsSkill
- spring-bootSkill
- competitive-analysisSkill
- lead-researchSkill
- product-analysisSkill
- resumeSkill
- user-researchSkill
- database-performanceSkill
- data-modelingSkill
- data-qualitySkill
- pandasSkill
- postgresSkill
- sparkSkill
- brand-guidelinesSkill
- generative-artSkill
- themingSkill
- ui-reviewSkill
- visual-designSkill
- architecture-decisionsSkill
- bug-fix-protocolSkill
- cli-developmentSkill
- code-reviewSkill
- debuggingSkill
- design-patternsSkill
- domain-modelingSkill
- git-workflowSkill
- legacy-modernizationSkill
- refactoringSkill
- repository-explorationSkill
- simple-designSkill
- system-designSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Write a long piece that makes an argument, supported by research, that a reader finishes.
≈ “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
Long-Form Content
Purpose
Write a long piece that makes an argument, supported by research, that a reader finishes. The failure mode is a survey of a topic that says nothing — comprehensive, balanced, and pointless.
When to Use
- Writing a researched article or a substantial blog post.
- Turning a body of research into a readable piece.
- An essay that argues for something.
- Content that must be accurate and sourced.
Capabilities
- Argument construction.
- Research and source evaluation.
- Structure: opening, development, conclusion.
- Citation and evidence.
- Editing for length and force.
Inputs
- The topic and, more importantly, the claim.
- The audience and what they already believe.
- The research available, and how good it is.
Outputs
- A piece with a defensible thesis.
- Claims supported by sources that were actually read.
- A structure a reader can follow.
Workflow
- Find the claim — What are you actually asserting? A piece "about" a topic is a survey. A piece arguing that something is true, or that a common belief is wrong, is an article. If you cannot state the claim in one sentence, do not start writing.
- Research to test the claim, not to support it — Look for the strongest counterargument first. If it holds, the claim was wrong and you have saved yourself two thousand words.
- Open with the claim or with the tension — Not with a definition, not with history, and never with "since the dawn of time". The first paragraph decides whether the piece is read.
- Develop with evidence — Each section advances the argument. A section that is merely interesting but does not advance it should be cut, however good it is.
- Cite what you actually read — Not the abstract, not what someone else said the paper said.
- Edit for force — The first draft is 30% too long. Cut the hedging, the throat-clearing, and the paragraph you are proud of that does not advance the argument.
Best Practices
- A piece with no claim is a survey, and surveys are not read. The reader's implicit question is "what do you think, and why should I believe you?"
- Steelman the counterargument. A piece that only engages with the weakest opposing view convinces nobody who did not already agree.
- The opening paragraph carries a disproportionate share of the work. If it does not create tension or state a claim, the reader leaves.
- Hedging weakens prose. "It could be argued that in some cases X may perhaps be true" asserts nothing. Say X, or do not.
- Cut your favourite paragraph if it does not advance the argument. This is the hardest editing rule and the most valuable.
- Cite primary sources. A statistic that has been passed through three blog posts is usually wrong by the time it reaches you.
Examples
Openings:
WEAK — a definition and a throat-clear. Nobody reads paragraph two.
Microservices are an architectural approach in which an application is
composed of small, independently deployable services. Since the term was
popularized in the mid-2010s, many organizations have adopted this pattern.
In this article we will explore the advantages and disadvantages of
microservices architecture.
STRONG — a claim and a tension, in two sentences.
Most teams that adopt microservices end up with a distributed monolith: all
the operational cost of a distributed system, and none of the independent
deployability that justified it. The failure is almost always the same one,
and it happens before a single service is written.The second opening makes a claim, implies the article has a specific answer, and gives the reader a reason to continue.
Research that tests the claim rather than decorating it:
Claim: "Microservices adoption usually produces a distributed monolith."
Before writing, look for what would falsify this:
- Are there large-scale surveys? (Yes: several state-of-DevOps style reports.
Read them. Note that they measure adoption, not outcome — so they do not
settle the question.)
- Who argues the opposite, and what is their best case? (Teams with genuine
independent deployability. Read their accounts. Their common factor:
they split around data ownership, not around entities.)
- Is there a definitional problem? (Yes — "distributed monolith" has no
agreed definition. Define it explicitly, or the claim is unfalsifiable
and therefore uninteresting.)
This research changed the piece: the claim became "teams that split by entity
rather than by data ownership produce a distributed monolith", which is
sharper, more defensible, and actually useful.Notes
- Researching to test a claim rather than to support it is the difference between an argument and a rationalization, and readers can tell.
- The 30% rule holds remarkably well: nearly every first draft improves by cutting a third, and almost none improve by adding.
- A piece that changes its own claim during research is a piece that was worth writing. One that ends where it started usually did not need the research.
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.

