Report Writing Skills for AI Agents
Report Writing skills cover the work of turning evidence into a document someone can act on. That means skills for scoping the question a report is allowed to answer, recording what you looked at and what it actually shows, structuring findings so a reader in a hurry still gets the answer and the "so what", moving from "here is a number" to "here is what it means", writing recommendations a decision-maker can act on rather than facts they merely know, and running accuracy and sign-off before the report leaves the building. The ranked list below is ordered by observed search demand, with skills that match this topic directly placed first and a cap on how many come from any single publisher. Read the descriptions to find the sub-topic you are weakest on, then pick the one skill that covers it rather than stacking several that overlap.
5 to start with18 top options
Start with these.
A report is an evidence document: scope the question, gather, structure findings, recommend, then make it checkable.
These are the closest matches for this work. Start with the first one and open it to install.
- Rank 01View Agent SkillDirect
notion-research-documentation
OfficialResearch across Notion and synthesize into structured documentation; use when gathering info from multiple Notion sources to produce briefs, comparisons, or reports with citations.
- Rank 02View Agent SkillDirect
technical-writing
House style and rules for writing technical documents such as specs, design docs, plans, and reports, covering structure, truth/sourcing, and banned constructions. It directly governs report drafting with evidence and structure.
12,920 · popularity - Rank 03View Agent SkillDirect
reviewing-technical-prose
Reviews, rewrites, and edits technical prose with severity mapping, findings format, and a delivery checklist, preserving content exactly. It directly supports the review facet of report writing.
12,600 · popularity - Rank 04View Agent SkillDirect
internal-comms
OfficialA set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
- Rank 05View Agent SkillDirect
writing-postmortems
Writes postmortems, incident reports, and root-cause analyses with blameless framing, evidence-only timelines, contributing factors, and owned action items. It directly covers a report type with structure and evidence discipline.
12,379 · popularity
Explore 13 more Agent Skills
- Rank 09View Agent SkillPossible
researchwrite
A proposal-first research writing pipeline that composes, revises, and audits research proposals and plans with evidence tables, argument maps, and section contracts. It supports structured report-like writing but is scoped to research prop
10,277 · popularity - Rank 10View Agent SkillPossible
firecrawl-research-papers
Finds and synthesizes research papers into sourced literature reviews using Firecrawl's paper index. It produces a report-like synthesis with citations but is scoped to academic literature, not general reports.
33,101 · popularity - Rank 11View Agent SkillPossible
firecrawl-workflows
Runs outcome-focused Firecrawl workflows that produce deliverables such as research reports, literature reviews, and audits. It can produce report deliverables but is a workflow router, not report-writing guidance.
32,186 · popularity - Rank 12View Agent SkillPossible
nature-polishing
Polishes, translates, or tightens existing academic prose while preserving facts and evidence boundaries, with journal-specific routing. It supports the review/evidence facets of report writing but is scoped to academic manuscripts.
15,558 · popularity - Rank 13View Agent SkillPossible
github-issue-creator
OfficialConvert raw notes, error logs, voice dictation, or screenshots into crisp GitHub-flavored markdown issue reports. Use when the user pastes bug info, error messages, or informal descriptions and wants a structured GitHub issue. Supports images/GIFs for visual evidence.
- Rank 14View Agent SkillPossible
security-best-practices
OfficialPerform language and framework specific security best-practice reviews and suggest improvements. Trigger only when the user explicitly requests security best practices guidance, a security review/report, or secure-by-default coding help. Trigger only for supported languages (python, javascript/typescript, go). Do not trigger for general code review, debugging, or non-security tasks.
- Rank 15View Agent SkillPossible
writing-issues
Writes tracker items (epics, stories, bugs, spikes) with outcome, acceptance checks, evidence, and owners. It structures written artifacts but is scoped to issue trackers, not reports.
12,380 · popularity - Rank 16View Agent SkillPossible54,457 · popularity
caveman-evidence-review
Notable - Rank 17View Agent SkillPossible
lark-workflow-standup-report
Notable日程待办摘要：编排 calendar +agenda 和 task +get-my-tasks，生成指定日期的日程与未完成任务摘要。适用于了解今天/明天/本周的安排。
747,014 · popularity - Rank 18View Agent SkillPossible
verification-before-completion
Enforces running verification commands and confirming output before claiming work is complete. It supports the review/evidence discipline of report work but is about code completion claims, not report drafting.
230,035 · popularity - Rank 19View Agent SkillPossible
docx
OfficialUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.
- Rank 20View Agent SkillPossible
writing-guidelines
OfficialReview docs/prose for Writing Guidelines compliance. Use when asked to "review my docs", "check writing style", "audit prose", "review docs voice and tone", or "check this page against the writing handbook".
- Rank 21View Agent SkillPossible
discernment-nudge
Official> After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.
What this topic covers
Each sub-topic groups Agent Skills for a specific situation.
- Scope
- What question this report is allowed to answer.
- Evidence
- What you looked at, and what it actually shows.
- Structure
- A reader in a hurry still gets the answer and the "so what".
- Analysis
- The move from "here is a number" to "here is what it means".
- Recommendations
- What a decision-maker should do, not just know.
- Review
- Accuracy and sign-off before it leaves the building.
Frequently asked questions
- How is this list ordered?
- It is ranked by observed search demand. Direct matches to the Report Writing topic come first, and no single publisher can take more than a capped share of the list.
- Which sub-topic should I start with?
- Start with the stage where your reports currently break down: scope, evidence, structure, analysis, recommendations, or review. Each sub-topic is a distinct step, so a skill that fixes scoping will not fix weak recommendations.
- Can one skill cover the whole report process?
- The topic spans six sub-topics, from scoping the question through review and sign-off. Some skills target a single stage, so check the description against the stage you need before choosing.
- What separates a report from a summary?
- A report is an evidence document: it scopes the question, gathers and structures findings, recommends, and stays checkable. A summary only restates what was found.
How to install an Agent Skill
Start with the first skill on this page. Claude Code reads a SKILL.md once it is in the skills directory:
- Claude Code — copy the SKILL.md for notion-research-documentation into ~/.claude/skills/notion-research-documentation/ for yourself, or .claude/skills/notion-research-documentation/ to share it with a project.
- From the registry — run npx skills add openai/skills@notion-research-documentation.
- Or download notion-research-documentation from its source and place that SKILL.md in the directory above.
How to choose Check the source and the skill’s own instructions before you install. Official and Notable describe where a skill comes from.