CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

playtest-report

Structured playtest report template, or turn existing playtest notes into structured feedback.

Quality

75%

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/playtest-report/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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 body is a well-engineered instruction-only skill: fully concrete outputs, verbatim routing commands, and a tightly gated multi-phase workflow with fallbacks for every failure mode it anticipates. Its only real slack is mild wordiness in the director-review fallback prose and the lack of any bundle-file split for the inline template.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence — it delegates gate definitions and config defaults to external docs instead of restating them, and the bug-vs-pain-point distinction is non-obvious domain guidance that earns its tokens. Minor trimming opportunities remain (the Phase 3b fallback prose is slightly wordy, stray double blank lines), keeping it below the every-token-earns-its-place anchor.

4 / 5

Actionability

The skill is copy-paste ready: a complete blank-report template, verbatim user-facing messages ("Run /propagate-design-change [path]..."), an exact save path pattern (production/qa/playtests/playtest-[date]-[tester].md), and concrete Grep/Read mechanics (pattern ^# with offset/limit) for cross-referencing design docs. Both common modes (new/analyze) and the review-mode variants are concretely covered.

5 / 5

Workflow Clarity

Phases are explicitly sequenced (1 → 2A/2B → 3 → 3b → 4 → 5) with validation checkpoints throughout: argument/mode routing, a review-mode gate before spawning the director agent, an explicit permission gate before the file write, and COMPLETE verdicts with stop conditions. Error-recovery fallbacks are handled (no-argument case, missing game-concept.md, NOT ASSESSED verdict), matching the top anchor.

5 / 5

Progressive Disclosure

Good single-file structure with clearly signaled, one-level-deep references to project docs (e.g. "the spawned agent reads its own gate file; do not read it in the parent session"). The ~60-line inline template is arguably core content rather than misplaced bulk, but it could live in a separate asset, and the skill runs past 50 lines with minor organization gaps (duplicated heading spacing), so it sits just below the clear-split anchor 5.

4 / 5

Total

18

/

20

Passed

Description

53%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 communicates a clear, fairly distinct purpose in the game-development playtesting niche, but it answers only "what" and leaves "when" entirely implicit. Adding an explicit trigger clause with natural synonyms would lift both completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user mentions a playtest, playtesting session, or beta test, or wants to turn raw playtest/session notes into structured feedback."

Include natural synonyms users would actually say — "playtesting", "beta test feedback", "user testing", "QA session notes" — to broaden trigger-term coverage.

Optionally enumerate both capabilities ("generate a blank report template, structure raw notes into findings, and route them to design/balance/bug/polish actions") to raise specificity from 1-2 actions to several.

DimensionReasoningScore

Specificity

"Structured playtest report template, or turn existing playtest notes into structured feedback" names the domain and 1-2 concrete actions (generate template, structure notes) but stops there — it omits the routing, director review, and report-saving the skill actually performs. This matches the anchor for naming a domain with 1-2 concrete actions, not the several-action anchor above.

3 / 5

Completeness

The "what" is clear (structured template / structuring existing notes) but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Not score 2 because the "what" half is concrete, not vague.

3 / 5

Trigger Term Quality

"playtest" and "playtest notes" are natural terms a game developer would say, but common variations like "playtesting", "beta test", "user testing", or "session notes" are absent. Some relevant keywords with missing synonyms fits the middle anchor.

3 / 5

Distinctiveness Conflict Risk

"playtest" carves a clear niche that would rarely trigger the wrong skill, leaving only minor overlap risk with general feedback/reporting skills. Mostly distinct with minor overlap fits this anchor rather than the fully distinct anchor 5, since the description doesn't sharpen the boundary with explicit triggers.

4 / 5

Total

13

/

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/playtest-report/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.