agentleFS
Sign inStart free
HadiFrt20HadiFrt20/deepresearch/dr-review/SKILL.md

dr-review

Skill4 starsChanged 7 months agoMITView on GitHub

Validate research data quality. Checks output files against schemas, flags NOT_FOUND clusters, incomplete entries, conflicting sources, and suspicious data. Use after a phase completes.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. darkroomengineering/cc-settings★ 52same name
    2. NotHarshhaa/devops-skills★ 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 repository6 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read .research/ARCHITECTURE.md to get the JSON schemas for each entity type.

    line 12
  2. Very specific:

    If no data files exist, tell the user to run /dr-run first.

    line 75
  3. Very specific:

    If ARCHITECTURE.md is missing, tell the user to run /dr-new first.

    line 76

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

You are auditing research data quality. Read the schemas and check every data file against them.

Steps

1. Load Schemas

Read .research/ARCHITECTURE.md to get the JSON schemas for each entity type. Note all required fields and valid values.

2. Audit Each Data File

For each file in data/:

Required Fields Check:

  • List entries missing any required field (name, category, website, sources, status, last_updated)
  • List entries where required fields are empty strings or null

Status Distribution:

  • Count entries by status: COMPLETE, INCOMPLETE, INACCESSIBLE
  • Flag entries with no status field

NOT_FOUND Analysis:

  • Per field, count how many entries have "NOT_FOUND"
  • Calculate NOT_FOUND rate per field
  • Flag fields with >40% NOT_FOUND — these may need a different search strategy

Source Quality:

  • Entries with zero source URLs (critical)
  • Entries missing the entity's own website in sources
  • Duplicate source URLs across entries (may indicate copy-paste errors)

Data Integrity:

  • Entries with CONFLICTING values — list each conflict
  • Entries with UNVERIFIED values — count per field
  • Duplicate entries (same name or same website)
  • Entries where status is COMPLETE but fields are NOT_FOUND (inconsistent)

3. Quality Report

Print findings grouped by severity:

## Data Quality Report

### Critical (must fix before report)
- 3 entries missing source URLs
- 1 entry with no status field
- 2 entries marked COMPLETE but have NOT_FOUND fields

### Warning (should investigate)
- funding_amount: 45% NOT_FOUND rate
- 4 entries with UNVERIFIED claims
- 2 potential duplicates: "Company A" appears twice

### Info
- 18 COMPLETE, 5 INCOMPLETE, 2 INACCESSIBLE
- 3 CONFLICTING values found (listed below)
- Average sources per entry: 2.3

4. Suggest Actions

Based on findings:

  • Critical issues → "Fix these before running /dr-report. Consider /dr-run to retry failed tasks."
  • High NOT_FOUND rates → "Run /dr-improve to optimize the researcher's search strategy for these fields."
  • Many INCOMPLETE → "Run /dr-run to continue. Some entities may need manual research."
  • Clean data → "Data looks good. Run /dr-report to synthesize findings."

Error Handling

  • If no data files exist, tell the user to run /dr-run first.
  • If ARCHITECTURE.md is missing, tell the user to run /dr-new first.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free