Ready to supercharge your AI agents?

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

Get Started Free →

Skill: api/contract-update · velcrafting | DecimalAI

codingby velcrafting

Skill: api/contract-update

velcrafting/contract-update

Source velcrafting/codex-skills ↗License Not recorded

Update request/response API contracts and client wiring without business logic.

SkillScore64Maintained

Automatic

Coding pack

Last verified 8/3/2026

What it changes

Passed 13 of 21 test cases with the skill, and 8 of 21 without it.

Without skill36%

With skill64%

Checks it passed that the model alone missed

Logs change_type as additive.
Logs change_type as versioned or breaking.
Includes endpoints_affected in the telemetry log.

and 5 more in the full report

7 fixed7 passed either way7 still failing1 broke

Pass-rate lift: +27 pp
Tokens: -13%
Agent turns: 0%
Response time: -30%

Model gemini-3.6-flashMeasured 8/3/2026v114 of 22 cases passed with skill · 21 comparable

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-contract-update/SKILL.md https://app.decimal.ai/s/velcrafting-contract-update/SKILL.md

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

decimalai skills add velcrafting-contract-update

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 7

Prompt

Provide the telemetry log object after publishing a breaking payload restructuring on the versioned endpoint `POST /v2/orders`.

What was checked, without and with the skill
Checked	Without skill	With skill
Logs change_type as versioned or breaking.	Missed	Passed

case-18 · 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.md70 linessingle file

Skill: api/contract-update

Purpose

Update API request/response contracts in a controlled, explicit way so that:

producers and consumers remain aligned
breaking changes are intentional and visible
schema drift is prevented

This skill owns shape, not behavior.

Inputs

Endpoint or event identifier
Old vs new contract (fields added/removed/changed)
Compatibility requirement:
- backward-compatible
- versioned
- breaking (explicit)
Repo profile (preferred): <repo>/REPO_PROFILE.json

Outputs

Updated contract definition(s):
- OpenAPI / schema / types / DTOs (repo-specific)
Client wiring updates if co-located
Compatibility notes in code comments or docs (if repo standard)

Non-goals

Implementing backend behavior
Implementing frontend UI logic
Persistence changes

Workflow

Locate canonical contract source (schema/types/spec).

Track record

Benchmark

13 / 21

test cases passed, vs 8 / 21 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/api/contract-update/SKILL.md

View on GitHub ↗

Imported 8/1/2026Version v1

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: api/contract-update

Purpose

Inputs

Outputs

Non-goals

Workflow

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills