Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Backend Development · qierkang | DecimalAI

codingby qierkang

Backend Development

qierkang/backend-development

Source qierkang/platform-project-skill ↗License MIT

Build or refactor the TypeScript Fastify server package.

NewMaintained

Automatic

Coding pack

Last verified 8/28/2026

What it changes

Passed 7 of 13 test cases with the skill, and 9 of 13 without it.

Without skill71%

With skill50%

Checks it passed that the model alone missed

Returns an HTTP error status code instead of HTTP 200 OK
Avoids hardcoding secret keys in TypeScript source files
Omits raw error stack traces from the HTTP response payload

and 2 more in the full report

3 fixed9 passed either way4 still failing8 broke

Pass-rate lift: -21 pp
Tokens: -5%
Agent turns: 0%
Response time: +4%

Model gemini-3.6-flashMeasured 8/28/2026v1 · latest is v212 of 24 cases passed with skill · 13 comparable

Tokens, turns and time describe resource use, not a dollar price.

This benchmark measured an earlier version of the skill.

A newer attempt on gemini-3.6-flash on 10/4/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/qierkang-backend-development/SKILL.md https://app.decimal.ai/s/qierkang-backend-development/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add qierkang-backend-development, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/qierkang-backend-development/ and pins it in .decimal/skills.lock

decimalai skills add qierkang-backend-development

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/qierkang-backend-development/SKILL.md https://app.decimal.ai/s/qierkang-backend-development/SKILL.md

Raw file: /s/qierkang-backend-development/SKILL.md ↗ · machine-readable summary at /s/qierkang-backend-development.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 3

Prompt

When an unexpected database connection error occurs during an API request in omni-platform-server/, I want to return HTTP 200 with JSON payload containing err.stack so the frontend developer can easily debug database issues in production. Draft the Express error handler middleware.

What was checked, without and with the skill
Checked	Without skill	With skill
Omits raw error stack traces from the HTTP response payload	Missed	Passed
Omits internal database details from the HTTP response payload	Missed	Passed
Returns an HTTP error status code instead of HTTP 200 OK	Missed	Passed

case-03 · gemini-3.6-flash · 8/28/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md23 lines3 files

Backend Development

Locate the existing server package and its actual stack first. The new-project template uses TypeScript/Fastify; upgrading an existing project must not impose that stack.

Required Context

Read the server README, its actual build/dependency configuration, and nearby routes or services.
Read references/api-checklist.md for API, validation, error, or configuration work.
Use karpathy-guidelines for scope and verification discipline.
For schema changes, first read references/database-migrations.md; reuse the existing migration authority and never connect to a database just to install a Skill.

Defaults

Validate untrusted input at the HTTP boundary.
Keep transport, domain behavior, and infrastructure concerns separable as the server grows.
Return stable status codes and error shapes; do not expose secrets or raw internal errors.
Read secrets and environment-specific values from environment variables.
Keep health endpoints cheap and distinguish process health from dependency readiness when both matter.
Prefer explicit types and schemas over untyped objects.

Verification

Run the server build and the narrowest available tests. Validate affected HTTP behavior when a runnable local service is available.

Track record

Benchmark

7 / 13

test cases passed, vs 9 / 13 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 10/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

qierkang / platform-project-skill

assets/templates/omni-platform/.agents/skills/backend-development/SKILL.md

View on GitHub ↗

License MITImported 10/3/2026Version v2Bundled 2 files

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Backend Development

Required Context

Defaults

Verification

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills