krishnaik06/deep-agents-with-langchain/report-writer

Claude Code and agent skill by krishnaik06/deep-agents-with-langchain

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Report writing skill that should be applied AFTER answering any user query. Whenever the deep agent produces a final answer, use this skill to also write a structured markdown report of the interaction (question, approach, findings, answer, sources) and save it as a file using the write_file tool. Use for every substantive answer, and especially when the user asks for a report, summary document, or saved output.

Install

npx vskill@latest install krishnaik06/deep-agents-with-langchain/report-writer

SKILL.md

Report Writer Skill

This is a post-answer skill: after you finish answering ANY substantive user query, generate a structured report of what was asked, what you did, and what you concluded — and save it to a file with the write_file tool.

When to Use

  • ALWAYS after producing a final answer to a substantive question
  • When the user explicitly asks for a report, summary document, or saved output
  • After research tasks, code generation tasks, or multi-step workflows
  • Skip only for trivial exchanges (greetings, clarifying questions)

Supporting Files (read these for deeper context)

  • instructions.md — the exact report template, file-naming rules, and writing standards
  • examples.md — sample reports showing the expected quality and structure

Core Workflow

  1. Answer the user's question first, as normal (possibly using other skills).
  2. Read instructions.md in this skill folder for the report template.
  3. Fill in the template: title, date, question, approach, key findings, answer, sources.
  4. Save the report with write_file to /reports/<topic-slug>-report.md.
  5. Tell the user the report was saved and where.

Quick Standards

  • Reports are markdown files saved under /reports/
  • File name: kebab-case topic slug + -report.md (e.g., /reports/lambda-cost-report.md)
  • Always include: Question, Approach, Key Findings, Answer, Sources/Tools Used
  • Keep the report self-contained — readable without the chat transcript
  • Be factual; do not add claims to the report that were not in your answer

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
59
Repository forks
41
7-day trend score
20

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/krishnaik06/deep-agents-with-langchain/report-writer/badge)](https://verified-skill.com/skills/krishnaik06/deep-agents-with-langchain/report-writer)

Something wrong with this skill or its page? Tell us.