Ready to supercharge your AI agents?

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

Get Started Free →

Skill: backend/endpoint-scaffold · velcrafting | DecimalAI

codingby velcrafting

Skill: backend/endpoint-scaffold

velcrafting/endpoint-scaffold

Source velcrafting/codex-skills ↗License Not recorded

Create a validated, authorized backend endpoint with error mapping and tests.

NewMaintained

Automatic

Coding pack

Last verified 8/3/2026

What it changes

Passed 19 of 22 test cases with the skill, and 19 of 22 without it.

Without skill86%

With skill86%

Checks it passed that the model alone missed

Logs HTTP method, path, authorization type, and test outcome metadata
Recommends state machine modeling before proceeding with implementation

2 fixed17 passed either way1 still failing2 broke

Pass-rate lift: 0 pp
Tokens: +17%
Agent turns: 0%
Response time: -21%

Model gemini-3.6-flashMeasured 8/3/2026v119 of 22 cases passed with skill

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

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/velcrafting-endpoint-scaffold/SKILL.md https://app.decimal.ai/s/velcrafting-endpoint-scaffold/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add velcrafting-endpoint-scaffold, 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/velcrafting-endpoint-scaffold/ and pins it in .decimal/skills.lock

decimalai skills add velcrafting-endpoint-scaffold

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

curl -fsSL --create-dirs -o .claude/skills/velcrafting-endpoint-scaffold/SKILL.md https://app.decimal.ai/s/velcrafting-endpoint-scaffold/SKILL.md

Raw file: /s/velcrafting-endpoint-scaffold/SKILL.md ↗ · machine-readable summary at /s/velcrafting-endpoint-scaffold.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 2

Prompt

When completing the execution of an endpoint scaffolding action, what operational telemetry parameters should be recorded?

What was checked, without and with the skill
Checked	Without skill	With skill
Logs HTTP method, path, authorization type, and test outcome metadata	Missed	Passed

case-13 · gemini-3.6-flash · 8/3/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md98 linessingle file

Skill: backend/endpoint-scaffold

Purpose

Add or extend an API endpoint in a way that is:

validated (request + response shape)
authorized (authn/authz hooks enforced)
mapped to a stable error taxonomy
covered by tests

This skill is the default entry point for backend feature exposure.

Inputs

Endpoint intent (what it does, who calls it)
Contract surface (preferred):
- method + path
- request fields + types
- response shape + types
Authorization expectation:
- public / authenticated / role-based / resource-based
Error expectations:
- list of expected failure cases
Repo profile (preferred): <repo>/REPO_PROFILE.json

Outputs

New or updated endpoint handler/controller/router entry
Input validation (schema/types) consistent with repo patterns
Authorization enforcement consistent with repo patterns
Error mapping consistent with shared error taxonomy
Tests:
- unit tests for handler logic and validation OR
- integration tests at route boundary (preferred when available)

Non-goals

Implementing complex domain rules inside the handler (use backend/domain-logic-module)

Track record

Benchmark

19 / 22

test cases passed, vs 19 / 22 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 v4 — 8/1/2026

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

velcrafting / codex-skills

skills/backend/endpoint-scaffold/SKILL.md

View on GitHub ↗

Imported 8/1/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

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

Skill: backend/endpoint-scaffold

Purpose

Inputs

Outputs

Non-goals

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills