one-report
Run the full One-Report pipeline from one input file through grounding, research, evidence-rich report drafting, final review quality-gating, and export, while reusing existing skills, preserving current contracts, and enforcing strict downstream skill fidelity for every grounded unit.
Profile →npx skills add gaotiexinqu/OneResearchClaw --skill one-report --agent cursor
Same command for any agent — swap --agent for claude-code, codex, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
This skill acts as the top-level orchestrator for the One-Report pipeline. It reads user-provided inputs, routes the input into the grounding workflow, and then proceeds through grounding completion, downstream branching for multi-topic grounding using independent subagent branches, per-grounded-unit research, drafting, final review, and export. It enforces strict downstream skill fidelity for every grounded unit and reports final output paths.
How it works
- Read the user-provided pipeline inputs (input_path, potentially research_requirements, output_formats, and other optional user inputs).
- Route the input into the correct existing grounding workflow and continue until grounding is completed.
- Identify grounded unit(s) that should continue downstream.
- For multi-topic grounding, use the
Tasktool to create independent subagent branches for each topic child. - Run research for each grounded unit.
- Run the main report-drafting stage for each grounded unit.
- Run the final review/refinement stage for each grounded unit.
- Run output export for each final reviewed report.
- Enforce strict downstream skill fidelity for every grounded unit, whether single-topic or multi-topic.
- Report the final output paths clearly.
When to use it
Use when you want a single top-level entry point to execute the full One-Report pipeline from one input file through grounding, research, drafting, quality review, and export, while reusing existing lower-level skills and preserving current contracts.
What it can touch
- It relies on existing skills for input grounding, research, drafting, review, and export. It may coordinate subagents via the Task tool for multi-topic grounding. It enforces downstream fidelity and handles output path reporting.
Caveats
- This is an orchestrator and does not implement grounding, literature search, drafting, review, or export logic itself. It must reuse downstream skills and cannot override subagent outputs or skip waiting for subagent completion signals. It includes a mandatory section detailing subagent isolation, completion signal protocol, and blocking rules to maintain artifact-based completion.
# One-Report Use this skill as the **single top-level entry skill** for the full One-Report pipeline. This skill is a **thin orchestration layer**. It does **not** replace existing input, grounding, research, summary, review, or export skills. It must **reuse** them. The purpose of this skill is to let a user provide: - one input file path - a small set of research requirements - requested export format(s) and then complete the full pipeline: input -> grounding -> research -> report drafting -> review quality gate -> output export without requiring the user to manually run each stage. --- ## What This Skill Does This skill must: 1. read the user-provided pipeline inputs 2. route the input into the correct existing grounding workflow 3. continue until grounding is actually completed 4. identify the grounded unit(s) that should continue downstream 5. **for multi-topic grounding: use `Task` tool to create independent subagent branches for each topic child (see Subagent Rule below)** 6. run research for each grounded unit 7. run the main report-drafting stage for each grounded unit 8. run the final review/refinement stage for each grounded unit 9. run output export for each final revie
- What This Skill Does
- What This Skill Does Not Do
- 🚨 PARENT AGENT SUBAGENT ISOLATION RULES
- The Core Problem
- Absolute Prohibitions
- Subagent Completion Signal Protocol
- The Only Permitted Actions During Subagent Execution
- Todo Structure as Enforcement
- Completion Gate: File Existence Only
- Artifact-Based Polling Strategy (Replace Transcript-Line-Count Polling)
- If a Subagent Seems Stuck
- Correct Workflow Pattern
- Violation = Pipeline Failure
- Required User Inputs
Example for research_mode=medium:
What does the one-report skill do?
Run the full One-Report pipeline from one input file through grounding, research, evidence-rich report drafting, final review quality-gating, and export, while reusing existing skills, preserving current contracts, and enforcing strict downstream skill fidelity for every grounded unit.
How do I install it?
Run `npx skills add gaotiexinqu/OneResearchClaw --skill one-report --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From gaotiexinqu/OneResearchClaw, a repository with 438 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.