Ready to supercharge your AI agents?

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

Public Plugin Packaging — measured AI agent skill | DecimalAI

agentlas-ai/public-plugin-packaging

SkillScore86Maintained

Use when packaging this meta-agent for public Codex plugin registration, Claude Code installation, GitHub release, one-line terminal install, or open-source distribution.

agent-toolingby agentlas-ai

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

Automatic

AI Engineer pack

decimalai skills pull agentlas-ai-public-plugin-packaging

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/agentlas-ai-public-plugin-packaging/SKILL.md

Raw file: /s/agentlas-ai-public-plugin-packaging/SKILL.md ↗ · machine-readable summary at /s/agentlas-ai-public-plugin-packaging.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

—-31% tokens0% turns86% of whole cases pass with skill (19/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-03	✗→✓	▲ Improved	3%	0%
case-02	✗→✓	▲ Improved	-22%	0%
case-01	✗→✓	▲ Improved	-50%	0%
case-07	✗→✓	▲ Improved	-62%	0%
case-09	✗→✓	▲ Improved	-42%	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

agentlas-ai / agentlas-os

skills/public-plugin-packaging/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v2

Skill contents

SKILL.md

Public Plugin Packaging

Procedure

Separate public operating-system files from private hosted service code.
Include README.md, LICENSE, SECURITY.md, AGENTS.md, agents/,

skills/, .agentlas/global-commands.json, schemas, templates, install scripts, runtime command files, and verification.

Keep private research, credentials, raw logs, and local paths out of the

package.

Run scripts/public_safety_check.sh.
Run runtime-specific plugin validation when available.

Output

Return release surface, install command, global_commands, validation commands, and blockers.

Want to see if agentlas-ai/public-plugin-packaging 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.