shape

Decide the technical path once the ask is clear. Use when the WHAT is confirmed but more than one way to build it remains — architecture, technology, design.

1.13x

Quality

75%

Does it follow best practices?

Impact

76%

1.13x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./hope/skills/shape/SKILL.md

Quality

Content

78%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 an exceptionally lean, well-structured routing skill with concrete dispatch rules and an explicit loop-termination condition. Its one structural defect is a dangling reference: `loop-selection.md` is cited but missing from the bundle, so the promised detail cannot be reached.

Suggestions

Create `loop-selection.md` (e.g., in a references/ directory) or remove the "read `loop-selection.md`" line so no reference is broken.

Add one short worked example of an open choice routed to a skill to ground the abstract routing conditions.

Reorder so the closing "The path" section's ask-then-state steps visibly follow the routing loop, or add a one-line ordering note to make the sequence immediately readable.

Dimension	Reasoning	Score
Conciseness	Phrases like "Decide only among ways that differ where it matters" and "the fewest versions that show a real fork, differing where it matters — who owns the data, where the seam sits, what fails how" are lean and purely instructional with zero padding and no concepts Claude already knows. Every token earns its place, matching the anchor-5 example.	5 / 5
Actionability	Concrete dispatch rules (five condition→skill mappings), a named tool invocation ("invoking the named skill with the Skill tool"), and "Ask any choice still open first, with AskUserQuestion" give mostly executable guidance. Not level 5 because the routing conditions are abstract and no worked example of a real choice is given.	4 / 5
Workflow Clarity	The sequence (look up settled facts → route each open choice → re-enter routing) has an explicit termination condition ("Route again until every open choice has the user's decision or confirmation and none conflict") and a conflict-surfacing rule. Not level 5 because the ordering across the "Route" and "The path" sections takes a re-read and there are no explicit error-recovery checkpoints.	4 / 5
Progressive Disclosure	Two well-organized sections in a ~24-line body would qualify for a 5 under the simple-skill exception, but the body directs "read `loop-selection.md`" and that file does not exist anywhere in the bundle (no references/ directory). The only external pointer is broken, so navigation fails; not level 4.	3 / 5
	Total	16 / 20 Passed

Description

58%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 correctly pairs a what with an explicit when-clause, but its trigger vocabulary is abstract and self-referential rather than the natural phrases a user would say when facing a build-path decision. Specificity rests on a single verb plus broad domain words, weakening routing precision.

Suggestions

Replace meta-language ("the WHAT is confirmed") with concrete user trigger phrases such as "which database should we use", "React vs Svelte", or "pick the tech stack".

Enumerate the concrete actions the skill performs (e.g., routes each open choice to a decision skill, resolves conflicts, confirms with the user) instead of the single verb "Decide".

Tighten distinctiveness by scoping the domain words, e.g., "choosing among implementation approaches once requirements are settled" rather than the broad trio "architecture, technology, design".

Dimension	Reasoning	Score
Specificity	"Decide the technical path" names one concrete action with its domains ("architecture, technology, design") but lists no further actions, matching the anchor for domain plus 1-2 actions without comprehensive coverage. It is not level 4 because it never enumerates several specific actions.	3 / 5
Completeness	Both what ("Decide the technical path") and when ("Use when the WHAT is confirmed but more than one way to build it remains") are explicitly stated. Not level 5 because the when-clause relies on internal jargon rather than concrete, natural user trigger phrases.	4 / 5
Trigger Term Quality	Some relevant keywords ("architecture", "technology", "design", "more than one way to build it") are present, but common variations users actually say — "tech stack", "approach", "which library", "A vs B" — are missing. Not level 4 because synonym coverage is thin and the phrasing is meta-language ("the WHAT is confirmed").	3 / 5
Distinctiveness Conflict Risk	The "HOW open after WHAT is confirmed" condition carves a niche, but "architecture, technology, design" are broad terms that overlap with planning and design skills. Not level 4 because the domain words alone would match many similar skills.	3 / 5
	Total	13 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: saadshahd/moo.md
Path: hope/skills/shape/SKILL.md
Commit: 595eda0

Reviewed: 6 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.