agent-ecosystem

agent-ecosystem/agent-skill-implementation

Skill Claude CodeCodex

Benchmark skill for testing how platforms handle references to skills that don't exist. Use when asked to probe missing dependency behavior.

agent-ecosystem/agent-skill-implementation

Skill Claude CodeCodex

This skill has no description field. The client implementation guide says platforms should skip such skills ("a description is essential for disclosure") and log the error. This skill tests whether platforms actually skip it, load it anyway, or fail some other way.

agent-ecosystem/agent-skill-implementation

Skill Claude CodeCodex

Benchmark skill for testing directory recognition and naming divergence. Use when asked to probe directory handling.

agent-ecosystem/agent-skill-implementation

Skill Claude CodeCodex

Benchmark skill for testing how platforms handle nonstandard frontmatter fields. Use when asked to probe nonstandard fields.

agent-ecosystem/agent-skill-implementation

Skill Claude CodeCodex

Benchmark skill whose name exceeds the 64-character limit. Use when asked to probe overlong name handling.

agent-ecosystem/agent-skill-implementation

Skill Claude CodeCodex

Benchmark skill for testing whether bundled scripts are executable. Use when asked to probe script execution behavior.

agent-ecosystem/agent-skill-implementation

Skill Claude CodeCodex

First of a pair of benchmark skills for testing cross-skill resource shadowing. Both skills have a references/API.md file with different content. Use when asked to probe resource shadowing.

agent-ecosystem/agent-skill-implementation

Skill Claude CodeCodex

Second of a pair of benchmark skills for testing cross-skill resource shadowing. Both skills have a references/API.md file with different content. Use when asked to probe resource shadowing.

agent-ecosystem/agent-skill-implementation

Skill Claude CodeCodex

Benchmark skill placed OUTSIDE any recognized skills directory, in the project tree. Use when asked to probe stray skill discovery.

agent-ecosystem/agent-skill-implementation

Skill Claude CodeCodex

Benchmark skill for testing path traversal boundary enforcement. Use when asked to probe path traversal.

agent-ecosystem/agent-skill-implementation

Skill Claude CodeCodex

Benchmark skill whose description stays under the spec's 1024-character limit when counted in Unicode code points but runs past it when counted in UTF-16 code units or UTF-8 bytes. Use when asked to probe description length units. The head marker MAGPIE-OBSIDIAN-1240 sits near the start and a tail marker sits at the…

agent-ecosystem/agent-skill-implementation

Skill Claude CodeCodex

Benchmark skill whose description stays under the spec's 1024-character limit when counted in characters but runs past it when counted in UTF-8 bytes. Use when asked to probe description length units. The head marker GANNET-PYRITE-1130 sits near the start of this description and a tail marker sits at the very end.…

agent-ecosystem/agent-skill-implementation

Skill Claude CodeCodex

Control beacon for the multi-root collision check, installed only under the AGENTS-root beacon path with no colliding name. Use when asked to probe the agents-root beacon.

agent-ecosystem/agent-skill-implementation

Skill Claude CodeCodex

Benchmark skill for testing collision precedence between two scanned project roots. This is the AGENTS-root variant. Use when asked to probe multi-root collisions.

agent-ecosystem/agent-skill-implementation

Skill Claude Code

Control beacon for the multi-root collision check, installed only under the CLAUDE-root beacon path with no colliding name. Use when asked to probe the claude-root beacon.

agent-ecosystem/agent-skill-implementation

Skill Claude Code

Twin of probe-allowed-tools whose allowed-tools value is a bare lowercase shell tool name, as some platforms spell it. Use when asked to probe allowed-tools lowercase naming.

agent-ecosystem/agent-skill-implementation

Skill Claude Code

Twin of probe-allowed-tools whose allowed-tools value is the bare tool name shell, as some platforms spell it. Use when asked to probe allowed-tools shell naming.

agent-ecosystem/agent-skill-implementation

Skill Claude CodeCodex

Benchmark skill with an unusually large and varied set of bundled files, for testing how platforms enumerate them at activation. Use when asked to probe bundled file enumeration.

agent-ecosystem/agent-skill-implementation

Skill Claude CodeCodex

Length-unit probe ascii-sixty-four. Benchmark skill whose name is an ASCII name of exactly 64 characters, the spec's cap, so it should be listed on every platform that counts in any unit. Use when asked to probe name length units.

agent-ecosystem/agent-skill-implementation

Skill Claude CodeCodex

Length-unit probe greek-sixteen. Benchmark skill whose name is a short name of lowercase Greek letters (16 code points, 16 UTF-16 units, 26 UTF-8 bytes), under the cap in every unit, so it is listed unless the platform rejects non-ASCII names outright. Use when asked to probe name length units.

agent-ecosystem/agent-skill-implementation

Skill Claude CodeCodex

Length-unit probe math-forty. Benchmark skill whose name is a name of lowercase mathematical bold letters from the astral plane (40 code points, 74 UTF-16 units, 142 UTF-8 bytes), under the cap in code points but over it in UTF-16 units and bytes. Use when asked to probe name length units.