agent-ecosystem/agent-skill-implementation / benchmark-skills/probe-long-compatibility
probe-long-compatibility
VerifiedBenchmark skill whose compatibility field runs past the spec's 500-character limit. Use when asked to probe oversize compatibility handling.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.7 KB |
SKILL.md
View on GitHub---
name: probe-long-compatibility
description: Benchmark skill whose compatibility field runs past the spec's 500-character limit. Use when asked to probe oversize compatibility handling.
compatibility: This compatibility value deliberately runs past the spec's 500-character limit to test oversize field handling, while remaining otherwise ordinary requirement prose. It nominally requires a POSIX shell, network access to nothing in particular, and no specific product, because the length violation should be the only unusual property of this skill. The padding is phrased as complete sentences for the same reason a real compatibility note would be, and it carries a marker as its final characters so truncation is detectable. The tail marker is TURNSTONE-ARAGONITE-3030
---
# Oversize Compatibility Probe
The spec's `compatibility` field "must be 1-500 characters if provided."
This skill's compatibility value is over 500 characters and is otherwise
ordinary requirement prose. It tests whether platforms reject the skill,
truncate the value, or tolerate the overrun.
The compatibility value ends with a tail marker (a bird-mineral phrase
whose bird is TURNSTONE) so truncation is detectable wherever the value
surfaces. This body deliberately never spells out the full marker
phrase, so any appearance of it can only have come from the
compatibility value itself.
## Canary Phrase
The canary phrase for this skill's body is: **KESTREL-BAUXITE-6690**
## Instructions
When activated, report:
1. "probe-long-compatibility activated. Canary: **KESTREL-BAUXITE-6690**"
2. **Field visibility**: Can you see a compatibility value for this
skill anywhere other than by reading this file, and if so, does it
end with the TURNSTONE tail marker? Quote exactly what you see.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |