CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

scope-check

Scope creep check — current scope versus the original plan. Flags additions, quantifies bloat, recommends cuts. 'Any scope creep?' Finishing a game from its brief is /cut's.

Quality

91%

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

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.

An exceptionally well-engineered procedural skill: concrete commands and paths, a canonical verdict table, and thoughtful guardrails against misleading 0% computations. The only deductions are mild redundancy in the NOT ASSESSED rationale across three phases and a borderline-long inline report template.

Suggestions

State the NOT ASSESSED rationale once (Phase 4) and have Phases 3 and 5 reference it in one line each — the same hazard is currently explained three times.

Consider moving the Phase 3 report template to a references/report-template.md file to keep SKILL.md as a lean overview, since the template accounts for roughly a third of the body.

DimensionReasoningScore

Conciseness

The body is dense with skill-specific judgment — file paths, thresholds, commands, and a report template — with no generic-knowledge padding. However, the NOT ASSESSED rationale is explained three times in different words (Phase 3 blockquote, Phase 4 bullets, Phase 5 closing parenthetical), which goes slightly beyond the "minor trim" bar for a 5.

4 / 5

Actionability

Guidance is fully executable: exact paths ("design/gdd/[feature].md", "production/sprints/sprint-003.md"), concrete commands ("git log --oneline --since=[start-date]", Grep pattern "^#" with offset/limit reading), a complete report template with table schemas, numeric verdict thresholds, and per-verdict next steps. This is copy-paste-ready guidance for an instruction-only skill.

5 / 5

Workflow Clarity

Five clearly sequenced phases with explicit validation checkpoints: Phase 1 stops when the baseline is absent, Phase 4's NOT ASSESSED check gates the verdict before the table is applied, and Phase 5 gives feedback loops (what would fix an unreadable side, why not to re-run). The skill is read-only, so the destructive/batch validation cap does not apply.

5 / 5

Progressive Disclosure

A single-file skill with no bundle, organized into well-labeled phases — appropriate since nothing here needs splitting into references. At ~156 lines with a full report template inlined it exceeds the under-50-line simple-skill exception, leaving minor organization room (the template could live in a reference file), which fits the good-structure anchor at 4.

4 / 5

Total

18

/

20

Passed

Description

92%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 tight, exemplary description: it states the comparison the skill performs, enumerates three concrete actions, includes a quoted natural trigger phrase, and draws an explicit boundary against a sibling skill. Its only weakness is minor — a few natural synonym variations (de-scope, over scope) are absent.

DimensionReasoningScore

Specificity

"Flags additions, quantifies bloat, recommends cuts" lists multiple concrete actions that comprehensively cover the skill's purpose alongside the "current scope versus the original plan" comparison framing. There is no meaningful coverage gap, so it matches the comprehensive anchor rather than the minor-gaps anchor at 4.

5 / 5

Completeness

The what is explicit ("Flags additions, quantifies bloat, recommends cuts") and the when is given as a concrete trigger phrase — "'Any scope creep?'" — which serves as equivalent explicit trigger guidance to a "Use when..." clause. Both are answered clearly and concretely, matching the top anchor.

5 / 5

Trigger Term Quality

Natural terms are present — "scope creep" (twice, including the quoted user phrase "Any scope creep?"), "bloat", "additions", "cuts" — giving good keyword coverage. A few natural variations users might say ("de-scope", "over scope", "feature bloat") are missing, so it falls short of the comprehensive anchor at 5.

4 / 5

Distinctiveness Conflict Risk

"Scope creep check" carves out a clear niche with distinct triggers, and the closing sentence "Finishing a game from its brief is /cut's" explicitly disambiguates against the closest sibling skill. Minimal conflict risk.

5 / 5

Total

19

/

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/scope-check/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.