agentleFS
pauloribeiro16pauloribeiro16/my-skills/service-verify/SKILL.md

service-verify

Skill1 starsChanged 6 months agoMITView on GitHub

Use before and after any service-dependent work. Verifies correct endpoint/port configuration, detects hardcoded connection strings, and ensures env-based config. Critical for data integrity.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before running data loading scripts

    line 12
  2. Distinctive:

    After editing any file with service connections

    line 13
  3. Distinctive:

    Before validation of results

    line 14
  4. Distinctive:

    When troubleshooting connection issues

    line 15
  5. Distinctive:

    When data seems wrong or missing

    line 16
  6. Distinctive:

    If found → FAIL → Fix immediately

    line 38
  7. Distinctive:

    Check that all service connections read from:

    line 42

≈ “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

Service Verify Skill

Ensures service connections use correct endpoints and detects hardcoded connection bugs.

When to Activate

  • Before running data loading scripts
  • After editing any file with service connections
  • Before validation of results
  • When troubleshooting connection issues
  • When data seems wrong or missing

Endpoint Rules (CRITICAL)

Each service has a specific endpoint configuration. Verify the correct ports/protocols for your project.

ServiceExpected EndpointEnvironment VariablePurpose
[Main DB][endpoint][DB_URI]This project
[External][endpoint][EXT_URI]External reference (if applicable)

Any hardcoded endpoint strings in source/config files = BUG

Verification Steps

Step 1 — Check for Hardcoded Endpoints

# Should return NOTHING — adapt patterns to your project's known bad ports/uris
grep -r "[known_bad_pattern]" [source_dirs]/

If found → FAIL → Fix immediately

Step 2 — Verify Connection Config

Check that all service connections read from:

  • Environment variables (.env), OR
  • Project config files (e.g., config.yaml), OR
  • A config loader module

Never hardcode:

  • protocol://localhost:port
  • Specific port numbers as literal strings
  • Connection credentials in source code

Step 3 — Test Connection

# Verify can connect to correct endpoint
python -c "
import os
uri = os.getenv('SERVICE_URI', 'protocol://localhost:default_port')
print(f'Testing {uri}')
# Adapt connection logic to your service type
result = connect(uri, ...)
print(f'Connection: {'OK' if result else 'FAIL'}')
"

Step 4 — Verify Data Loaded (if applicable)

# Quick count check for expected data
python -c "
import os
conn = connect(os.getenv('SERVICE_URI'))
count = conn.query('SELECT count(*) FROM records').single()[0]
print(f'Records: {count}')
conn.close()
"

Common Bug Patterns

❌ WRONG

driver = Driver("protocol://localhost:port", ...)
uri = "http://localhost:custom_port"

✅ CORRECT

import os
driver = Driver(
    os.getenv("SERVICE_URI", "protocol://localhost:default_port"),
    auth=(os.getenv("SERVICE_USER", "user"), os.getenv("SERVICE_PASSWORD"))
)

Output Format

## Service Verification

### Endpoint Check
grep -r "[known_bad_pattern]" [source_dirs]/ → [PASS/FAIL]
Found: [list files if any]

### Connection Test
URI: [what was used]
Result: [OK/FAIL]

### Data Check (if applicable)
Records: [count]
[Other relevant counts]

**Verdict:** [PASS/FAIL]

If FAIL

  1. Identify files with hardcoded endpoints
  2. Fix to use environment variables
  3. Re-run verification
  4. Report what was fixed

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.