Name: Check Deep Research Status
Author: Skills Guide Bot

Automated summary

Checks the progress of the most recent deep research run by reading its artifact files and running an audit.

Strengths

Gives a single-command overview: phase, sources, claims, evidence, notes and report
Counts entries in the JSONL files (sources, claims, evidence) for precise quantitative tracking
Runs the dr_audit.py script in full mode and surfaces failures with their details
Automatically locates the latest run by sorting the directories under .deep-research/runs/

Limitations

Assumes the strict file layout (.deep-research/runs/, run.json, sources.jsonl, etc.) produced by the deep research plugin
Does not restart or fix the run: it is a read-only report
Relies on CLAUDE_PLUGIN_ROOT to locate the audit script

When to use it

Use it when you want to know where a current or recent deep research run stands and verify its integrity.

When not to use it

Do not use it to start a new research run, edit artifacts, or work outside an existing deep research plugin run.

Security analysis

Safe

Quality score80/100

The skill is a read-only status reporter: it locates a run directory, reads JSON/JSONL files, counts entries, and prints a summary. The only execution step is invoking a bundled local audit script with a user-determined run directory argument, with no network calls, no destructive filesystem operations, no secret handling, and no obfuscation. The referenced python script should be reviewed separately, but nothing in the instructions themselves is dangerous.

Findings

•Step 6 invokes `python3 ${CLAUDE_PLUGIN_ROOT}/scripts/dr_audit.py` even though no allowed-tools are declared; the script itself is not included in the skill, so its behavior cannot be verified from this file alone.
•Relies on resolving the most recent run directory by sorting directory names, which briefly reads local project state under `.deep-research/` — read-only, no exfiltration.

How this analysis is made

Examples

Check current run

What's the status of my deep research run? Show me the stage, source and claim counts, and whether the report is ready.

Verify audit

Run the audit on the latest deep research run and tell me if it passes or what failed.

Post-run review

Did the last deep research run finish cleanly? Summarize sources by type, claims by importance, and any notes or gaps.

name: status description: Check the progress of the current or most recent deep research run. Shows stage, source counts, claim counts, and any issues.

Check the status of the most recent deep research run.

Instructions

Find the latest run directory under .deep-research/runs/ (sort by directory name, most recent first).
Read run.json for the run metadata and current status.
Count entries in sources.jsonl, claims.jsonl, and evidence.jsonl.
List any notes files in the notes/ directory.
Check if report.md exists and has content.
Run a quick audit: python3 ${CLAUDE_PLUGIN_ROOT}/scripts/dr_audit.py --mode full --run-dir <run_dir>

Output

Provide a concise status summary:

Run ID: the run identifier
Topic: the research question
Status: current phase (planning/scouting/analyzing/synthesizing/complete)
Sources: count and breakdown by type
Claims: count and breakdown by importance and status
Evidence: edge count
Notes: number of source notes written
Report: exists/empty/missing
Audit: pass/fail with failure details if any

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/check-deep-research-status-ms47vps1/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/check-deep-research-status-ms47vps1' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/check-deep-research-status-ms47vps1/download' --output '.skill-downloads/check-deep-research-status-ms47vps1/SKILL.md.part' && mv '.skill-downloads/check-deep-research-status-ms47vps1/SKILL.md.part' '.skill-downloads/check-deep-research-status-ms47vps1/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code

test -f '.skill-downloads/check-deep-research-status-ms47vps1/SKILL.md' && test -s '.skill-downloads/check-deep-research-status-ms47vps1/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/status' && cp -R '.skill-downloads/check-deep-research-status-ms47vps1' '.claude/skills/status'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation

openskills install './.skill-downloads/check-deep-research-status-ms47vps1'

openskills read 'check-deep-research-status-ms47vps1'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/check-deep-research-status-ms47vps1/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills

Create Interactive Maps with kepler.gl

Data & AI

Create interactive map visualizations and export standalone HTML using the keplergl Python package. Use to plot geospatial data from DataFrames, GeoJSON, or CSV.

Claude CodeCursorCodexintermediateSafe 11,995

Skills Guide Bot