Ready to supercharge your AI agents?

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

Get Started Free →

Fix CI — measured AI agent skill | DecimalAI

ledgerhq/fix-ci

NewSkillScoreMaintained

Find failing CI jobs, inspect logs, and apply focused fixes

DevOpsby ledgerhq

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/ledgerhq-fix-ci/SKILL.md

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

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

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

Raw file: /s/ledgerhq-fix-ci/SKILL.md ↗ · machine-readable summary at /s/ledgerhq-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 6h ago

—-26% tokens0% turns64% of whole cases pass with skill (14/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-06	✗→✓	▲ Improved	-36%	0%
case-18	✗→✓	▲ Improved	-47%	0%
case-21	✗→✓	▲ Improved	-46%	0%
case-05	✓→✗	▼ Worse	-37%	0%
case-13	✓→✗	▼ Worse	-45%	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

ledgerhq / ledger-live

.agents/skills/fix-ci/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

Fix CI

Trigger

Branch CI is failing and needs a fast, iterative path to green checks.

Workflow

Identify the latest run for the current branch.
Inspect failed jobs and extract the first actionable error.
Apply the smallest safe fix.
Re-run CI and repeat until green.

Guardrails

Fix one actionable failure at a time.
Prefer minimal, low-risk changes before broader refactors.

Output

Primary failing job and root error
Fixes applied in iteration order
Current CI status and next action

Want to see if ledgerhq/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.