Ready to supercharge your AI agents?

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

release-feed-api — measured AI agent skill | DecimalAI

learnprompt/release-feed-api

SkillScore68Maintained

Read a read-only release feed over HTTP, enforce an auditable request contract, and write redacted JSON and Markdown reports. Use when the task is to inspect releases from a REST endpoint without mutating upstream state.

DevOpsby learnprompt

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Coding pack

decimalai skills pull learnprompt-release-feed-api

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/learnprompt-release-feed-api/SKILL.md

Raw file: /s/learnprompt-release-feed-api/SKILL.md ↗ · machine-readable summary at /s/learnprompt-release-feed-api.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 3h ago

—-41% tokens0% turns68% of whole cases pass with skill (15/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-04	✗→✓	▲ Improved	-53%	0%
case-05	✗→✓	▲ Improved	-60%	0%
case-07	✗→✓	▲ Improved	-67%	0%
case-09	✗→✓	▲ Improved	22%	0%
case-10	✗→✓	▲ Improved	-70%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

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

learnprompt / learnprompt

research/articles/api-integration-skill-design/showcase/release-feed-api/fixture/.agents/skills/release-feed-api/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/3/2026Version v1Bundled 4 files · scripts

Skill contents

scripts/

references/

assets/

SKILL.md

release-feed-api

When to use

Use this skill when the user asks for a read-only release feed check, release summary report, or REST integration example that must keep credentials, retry policy, schema validation, and pagination explicit.

Required reading

references/api-contract.md

Workflow

Read the request contract.
Run:

bash node .agents/skills/release-feed-api/scripts/fetch-releases.mjs

Keep the generated reports if the fetch succeeds:

reports/releases.json
reports/releases.md

Run npm test.
Return only the JSON object requested by the caller schema.

Boundaries

Read the base URL and credential only from RELEASE_FEED_BASE_URL and RELEASE_FEED_TOKEN.
Reject any configured method other than GET before making a network request.
Paginate serially. Do not fan out concurrent page fetches.
If the server returns 429, obey Retry-After before retrying.
Retry 5xx responses only up to the configured limit, then fail with exit 43.
Do not print credential values or raw authorization headers into reports, logs, or final output.
Never edit source files outside reports/.

Want to see if learnprompt/release-feed-api would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.