Ready to supercharge your AI agents?

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

Create Changeset — measured AI agent skill | DecimalAI

ledgerhq/create-changeset

NewSkillScoreMaintained

Create changesets for the ledger-live monorepo using @changesets/cli. Use when the user asks to add a changeset, prepare a release, or document package changes for a PR.

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-create-changeset/SKILL.md

decimalai skills pull ledgerhq-create-changeset --out .claude/skills/

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

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

Raw file: /s/ledgerhq-create-changeset/SKILL.md ↗ · machine-readable summary at /s/ledgerhq-create-changeset.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

—-43% tokens0% turns86% of whole cases pass with skill (19/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-8%	0%
case-02	✗→✓	▲ Improved	-6%	0%
case-03	✗→✓	▲ Improved	14%	0%
case-04	✗→✓	▲ Improved	-74%	0%
case-05	✗→✓	▲ Improved	-48%	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/create-changeset/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

Create Changeset

Create a .changeset/<adjective-noun-verb>.md file (human-readable random identifier, matching @changesets/cli convention) with this format:

markdown
---
"package-name": minor
---

Short description of the change

Package Names

Package names must match exactly what's in each package.json:

| App / Lib | Package name | |-----------|-------------| | Mobile app | live-mobile | | Desktop app | ledger-live-desktop | | Common lib | @ledgerhq/live-common | | Coin modules | @ledgerhq/coin-<name> (e.g. @ledgerhq/coin-sui) | | Other libs | Check the lib's package.json name field |

Impact Levels

| Level | When to use | |-------|-------------| | minor | New features, bug fixes, non-breaking changes | | major | Breaking changes (rare, requires discussion) | | patch | Internal-only changes, dependency bumps |

Description

One line, concise but descriptive
Format: <verb> <what> or conventional commit style
Examples:
Add portfolio analytics dashboard with performance metrics
Fix transaction signing issue on mobile
Flush mobile content card click analytics before opening links

Want to see if ledgerhq/create-changeset 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.