help

Analyzes what is done and the users query and offers advice on what to do next. Use if user says what should I do next or what do I do now or I'm stuck or I don't know what to do

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/help/SKILL.md

Quality

Content

77%

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-sequenced, highly actionable read-only orientation workflow with concrete paths, status semantics, and an output template. Its main gaps are mild inferable-purpose padding and the absence of any progressive-disclosure structure despite the file's length.

Suggestions

Trim restated-purpose sentences (e.g. "This tells you what the user just finished..." and "This is the authoritative list...") since the step headings already convey intent.

Consider moving the large Step 7 output template and the Step 2 phase-mapping table into a referenced file (e.g. output-format.md) so the main SKILL.md stays a lean overview, improving progressive disclosure.

Collapse the overlap between Step 3 (session context) and Step 6 (in-progress work), which cover the same active.md signal, to remove redundancy.

Dimension	Reasoning	Score
Conciseness	The body is mostly operational directives, but it includes purpose restatements Claude could infer ("This is the authoritative list of all phases...", "This tells you what the user just finished or is stuck on — use it to personalize the output"), placing it at the mostly-efficient-but-could-be-tightened score-2 anchor rather than the lean score-3.	2 / 3
Actionability	It gives concrete, executable guidance for an instruction-only skill: specific paths (production/stage.txt, .claude/docs/workflow-catalog.yaml, production/sprint-status.yaml), glob patterns, explicit status field values, and a copy-paste output template with formatting rules, matching the score-3 anchor.	3 / 3
Workflow Clarity	Steps 1–9 are clearly sequenced with an explicit check order ("Check in this order"), enumerated special cases, and a Collaborative Protocol; this is a read-only analysis skill so the destructive/batch validation cap does not apply, reaching the score-3 clear-sequence anchor.	3 / 3
Progressive Disclosure	No bundle files exist and the entire procedure lives inline in one ~229-line file; sections are well organized, but there is no progressive disclosure (no one-level-deep references, no content split), and the >50-line simple-skill exemption for a score of 3 does not apply.	2 / 3
	Total	10 / 12 Passed

Description

82%

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 cleanly covers both what the skill does and when to use it, with natural trigger phrases and correct third-person voice. Its weakness is generic capability language and overlap with other orientation skills, which caps specificity and distinctiveness.

Suggestions

Replace abstract verbs with concrete capabilities, e.g. "Reads the workflow catalog and session state, detects the current phase, and lists the next required step and command."

Tighten distinctiveness by naming the pipeline scope up front, e.g. "For the game-dev phase workflow" so it does not collide with general /start or /gate-check skills.

Fix the grammatical awkwardness "the users query" → "the user's query" for readability.

Dimension	Reasoning	Score
Specificity	"Analyzes what is done and the users query and offers advice on what to do next" names the pipeline-status domain and a couple of actions, but the actions (analyzes, offers advice) are abstract rather than a list of concrete capabilities; it sits between the vague score-1 anchor and the multi-action score-3 anchor.	2 / 3
Completeness	It explicitly answers both what ("Analyzes...offers advice on what to do next") and when (an explicit "Use if user says..." clause), satisfying the score-3 anchor for both what AND when with explicit triggers.	3 / 3
Trigger Term Quality	"Use if user says what should I do next or what do I do now or I'm stuck or I don't know what to do" gives strong coverage of natural phrases a user would actually say when they need this skill, matching the score-3 anchor.	3 / 3
Distinctiveness Conflict Risk	"advice on what to do next" is a fairly generic orientation niche that overlaps with the sibling skills named in the body (/project-stage-detect, /gate-check, /start); the triggers help but it could still fire for the wrong orientation skill, so it is not the clearly-distinct score-3.	2 / 3
	Total	10 / 12 Passed

Validation

87%

Warnings & errors only

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

Criteria	Description	Result
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/help/SKILL.md
Commit: 984023d

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.