Ready to supercharge your AI agents?

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

Fix CI — measured AI agent skill | DecimalAI

mariasolos/fix-ci

NewSkillScoreMaintained

Fetches failed and errored test details from CircleCI job test URLs using the CircleCI API v2. Use when the user provides a CircleCI tests URL and asks for errors, failures, test results, or help fixing CI.

DevOpsby mariasolos

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

Automatic

DevOps & SRE pack

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

pip install decimalai

2 · Get the skill — writes .claude/skills/mariasolos-fix-ci/SKILL.md

decimalai skills pull mariasolos-fix-ci --out .claude/skills/

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

curl -fsSL --create-dirs -o .claude/skills/mariasolos-fix-ci/SKILL.md https://app.decimal.ai/s/mariasolos-fix-ci/SKILL.md

Raw file: /s/mariasolos-fix-ci/SKILL.md ↗ · machine-readable summary at /s/mariasolos-fix-ci.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 5h ago

—-35% tokens0% turns82% of whole cases pass with skill (18/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-04	✗→✓	▲ Improved	-9%	0%
case-05	✗→✓	▲ Improved	40%	0%
case-06	✗→✓	▲ Improved	-54%	0%
case-08	✗→✓	▲ Improved	-41%	0%
case-11	✗→✓	▲ Improved	-18%	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

mariasolos / dotfiles

.pi/agent/skills/fix-ci/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1Bundled 1 file · scripts

Skill contents

scripts/

SKILL.md

Fix CI

Use this skill to turn a CircleCI web tests URL like:

text
https://app.circle.example.com/pipelines/github/example-org/example-repo/19060/workflows/887679f9-1f30-43a6-a600-7292d29b3edc/jobs/215974/tests

into API calls to CircleCI v2 and summarize failing/erroring tests.

Requirements

Make sure that the following environment variables are set in your environment. If not, raise an error.

CIRCLECI_TOKEN
CIRCLECI_API_BASE

For such test run [ -n "${CIRCLECI_TOKEN}" ] && echo "ENV OK" || echo "ERROR: MISSING ENV VAR"

Usage

From this skill directory:

bash
python3 scripts/circleci_errors.py '<circleci-tests-url>'

Useful options:

bash
python3 scripts/circleci_errors.py '<url>' --all        # print all tests, not just failed/error tests
python3 scripts/circleci_errors.py '<url>' --json       # emit normalized JSON
python3 scripts/circleci_errors.py '<url>' --base-url https://circle.example.com/api/v2

Workflow

Parse the CircleCI web URL.
Derive the project slug (github/org/repo from app URLs, accepted by CircleCI Server; public cloud also accepts gh/org/repo for cloud URLs).
Call GET /api/v2/project/{project-slug}/{job-number}/tests, following pagination.
Report tests whose result is failure, failed, error, or errored, including class/name/file/message/source where available.

If authentication fails, ask the user to provide/export a valid CircleCI token with permission to read the project/job.

Want to see if mariasolos/fix-ci 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.