CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

testland/gameplay-recording-replay

Use when a game needs recorded play sessions as regression tests, netcode replays for spectators or esports, or reproducible bug repros for cert. Replays sessions bit-for-bit and checks the end state, via Unity InputEventTrace, Unreal's Replay System or deterministic Godot input replay.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Overview
Quality
Evals
Security
Files

Quality

Content

85%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-engineered workflow skill: dense with non-inferable engine facts, an explicit validated multi-step process, and exemplary progressive disclosure that pushes all working code into a single clearly-signaled reference file. The only weaknesses are minor token waste from repeated inline URLs and restating the Unity/Unreal determinism contract, and the body's reliance on the reference file for executable code.

DimensionReasoningScore

Conciseness

Nearly all content is non-obvious, engine-specific fact delivered in compact tables (determinism lock-downs, capture-level contracts, anti-patterns), but the same Unity InputEventTrace URL is inlined about five times and the Unity-vs-Unreal determinism split is restated three times (Step 2 table, the prose after it, and Limitations), so minor trimming is possible. Not 3, because there is almost no explanation of concepts Claude would already know.

4 / 5

Actionability

Gives concrete, real commands and APIs (DemoRec/DemoPlay/DemoStop, InputEventTrace, NetworkReplayStreamer), exact storage paths, a specific hash-comparison CI loop, and points to a verified one-level-deep reference file containing full copy-paste code for all three engines. Not 5, because the body itself contains no code blocks — executability depends on the referenced file.

4 / 5

Workflow Clarity

A clear 4-step sequence (determinism → capture level → record/replay + CI assertion → drift fail-safe) with explicit validation checkpoints ("Mismatch → CI fails the build", CI rejecting replays with replay_format < current_format), feedback paths (re-record vs fail the build), a fully worked Unity example, and an anti-patterns error-recovery table.

5 / 5

Progressive Disclosure

The body is a well-organized cross-engine decision surface, and the bulk record/replay/CI code is correctly split into references/engine-record-replay-apis.md (verified to exist, one level deep, pointing no further), signaled clearly at each point of use with when-to-consult context. Navigation is easy with consistent sectioning.

5 / 5

Total

18

/

20

Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: it states a concrete, differentiated capability set with explicit 'Use when' triggers covering regression tests, spectator/esports replays, and cert bug repros, anchored by named per-engine APIs. Third-person, appropriately concise, and unlikely to fire for the wrong skill.

DimensionReasoningScore

Specificity

Lists several concrete actions ("Replays sessions bit-for-bit", "checks the end state") and names the exact engine APIs (Unity InputEventTrace, Unreal's Replay System, deterministic Godot input replay), but the recording action itself is only implied by "recorded play sessions" rather than explicitly enumerated, so it falls just short of comprehensive coverage.

4 / 5

Completeness

Explicitly answers both: what ("Replays sessions bit-for-bit and checks the end state, via Unity InputEventTrace, Unreal's Replay System or deterministic Godot input replay") and when ("Use when a game needs recorded play sessions as regression tests, netcode replays for spectators or esports, or reproducible bug repros for cert") with concrete trigger phrases. Not 4, because the 'when' clause is already explicit and specific rather than vague.

5 / 5

Trigger Term Quality

Good coverage of natural user phrases — "regression tests", "netcode replays", "spectators or esports", "bug repros", "cert", plus engine names — though a few natural variants like "playthrough", "session recording", or "speedrun" are missing.

4 / 5

Distinctiveness Conflict Risk

Clear niche — engine-specific gameplay replay/recording for regression testing, spectator/esports features, and cert repro artefacts — with distinct trigger phrases; minimal conflict risk with adjacent testing skills since the triggers are tied to replays and recorded sessions.

5 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

On this page