CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

soak-test

Soak test protocol for extended play — what to observe and log for slow leaks, fatigue, late-appearing edge cases.

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/soak-test/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

The content is a highly actionable, well-sequenced protocol generator: concrete thresholds, engine-specific monitoring steps, a complete output template, and explicit decision and verdict rules with feedback loops. Its only real weaknesses are moderate redundancy in the unit-handling and NOT-ASSESSED rationale (repeated in three places) and the fact that a 330-line self-contained body could offload the protocol template to a reference file for better progressive disclosure.

DimensionReasoningScore

Conciseness

The body is mostly efficient — checkpoint schedules, thresholds, and the template all earn their tokens — but the unit-agnostic/NOT-SOURCEABLE rationale is repeated across Phase 4, the Phase 5 checklist, and the Verdict note, and the opening paragraph defines what a soak test is, a concept that could be tightened or trimmed.

3 / 5

Actionability

Guidance is fully concrete and executable: exact checkpoint tables per duration, engine-specific tool names and counters to record, explicit alert thresholds ("> 20% from T+0", "monotonicity across 3+ checkpoints"), a complete fill-in protocol template, and an exact output path with post-write instructions covering all common engines and focus modes.

5 / 5

Workflow Clarity

Phases 1-6 are clearly sequenced (parse args → load context → checkpoints → generate → write → follow-up) with explicit checkpoints: fallback paths for missing project.yaml keys, an approval gate before the single file write, verdict decision rules including NOT ASSESSED handling, and a feedback loop (FAIL → fix → re-run /smoke-check, regression soak after memory fixes).

5 / 5

Progressive Disclosure

The body is well-organized into numbered phases with clear headers and no nested references, and the inlined protocol template is justified as the per-run deliverable; at ~330 lines with no bundle files, however, the ~130-line protocol template and engine-specific monitoring guidance could arguably live in reference files, leaving minor organization gaps.

4 / 5

Total

17

/

20

Passed

Description

66%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.

The description is specific and appropriately concise, clearly naming the domain and the concrete observables (slow leaks, fatigue, late-appearing edge cases) with natural trigger keywords. Its main gap is the absence of any "Use when..." trigger guidance, which limits completeness and makes the activation boundary rely on inference. Distinctiveness within a game-QA skill suite is good but not explicitly delineated from adjacent test types.

Suggestions

Add an explicit trigger clause, e.g. "Use when running extended-play QA before a release gate, after fixing a memory or stability issue, or when the user mentions soak tests, endurance tests, or long-session stability."

Name the concrete deliverable and actions in the description, e.g. "Generates a timed observation protocol (production/qa/soak-test-*.md) covering memory, stability, and fun-fatigue checkpoints" so the "what" is fully explicit.

Include the synonym "endurance test" (already used in the body) in the description to widen natural trigger coverage.

DimensionReasoningScore

Specificity

"what to observe and log for slow leaks, fatigue, late-appearing edge cases" enumerates concrete observables and a clear deliverable (a soak test protocol), which is noticeably above the 1-2-action midpoint; however it does not list several distinct actions (e.g., generating the protocol file, post-session analysis), leaving minor coverage gaps.

4 / 5

Completeness

The "what" is clear (generates a soak test observation/logging protocol for extended play), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3; the "when" is only weakly implied by the topic keywords.

3 / 5

Trigger Term Quality

"soak test", "extended play", "slow leaks", "fatigue", "late-appearing edge cases" are natural phrases a user would say, but common synonyms such as "endurance test", "memory leak", or "long session" are missing, so coverage is good rather than comprehensive.

4 / 5

Distinctiveness Conflict Risk

"Soak test" is a distinctive QA niche term unlikely to trigger sibling skills like smoke checks or single-feature playtests, but the description does not draw that boundary explicitly, leaving minor overlap risk with closely related QA skills.

4 / 5

Total

15

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository

Donchitos/Claude-Code-Game-Studios

Path

.claude/skills/soak-test/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.