Ready to supercharge your AI agents?

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

Get Started Free →

Shared Skills — measured AI agent skill | DecimalAI

rshankras/shared

NewSkillScoreMaintained

Platform-agnostic skills including skill creation templates and best practices. Use when creating new skills or improving existing ones.

agent-toolingby rshankras

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

Automatic

AI Engineer pack

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

pip install decimalai

2 · Get the skill — writes .claude/skills/rshankras-shared/SKILL.md

decimalai skills pull rshankras-shared --out .claude/skills/

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

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

Raw file: /s/rshankras-shared/SKILL.md ↗ · machine-readable summary at /s/rshankras-shared.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 2h ago

Yes — +36% lift-24% tokens0% turns68% of whole cases pass with skill (15/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-11	✗→✓	▲ Improved	-5%	0%
case-16	✗→✓	▲ Improved	-58%	0%
case-17	✗→✓	▲ Improved	-57%	0%
case-18	✗→✓	▲ Improved	-60%	0%
case-19	✗→✓	▲ Improved	-55%	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

rshankras / claude-code-apple-skills

skills/shared/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

Shared Skills

Platform-agnostic skills that work across iOS, macOS, and other Apple platforms. This category provides foundational tools for extending Claude Code's capabilities.

When This Skill Activates

Use this skill when the user:

Wants to create a new Claude Code skill
Asks about skill structure or organization
Wants to improve or refactor existing skills
Needs help with skill modularization
Asks about skill best practices or templates

Available Modules

Read relevant module files based on the user's needs:

skill-creator/

Templates and guidance for creating well-structured Claude Code skills.

Skill structure and organization patterns
YAML front matter configuration
Modularization strategies
Templates for simple and complex skills
Best practices and common pitfalls

How to Use

Identify user's need from their question
Read relevant module files from subdirectories
Apply the guidance to their specific context
Provide examples from existing skills when helpful

Example Workflow

User wants to create a new skill:

Read skill-creator/SKILL.md for the full creation process
Determine skill complexity (simple vs modularized)
Guide through front matter, structure, and content
Reference existing skills as examples

Want to see if rshankras/shared 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.