replit-deck

For product and technical management work: turn PRDs, roadmaps, RFCs, architecture reviews, and retros into decision documents. Built around the core query "pm-feature-business-case-deck", with product strategy lead judgment, buyer-ready proof, and this outcome: approve the feature, architecture, roadmap, or incident follow-up.

Quality

68%

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 ./design-templates/replit-deck/SKILL.md

Quality

Content

77%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 well-sequenced, actionable workflow with a strong validation gate, and it uses progressive disclosure to push detail into reference files. Its main weakness is referencing an examples/ directory that does not exist in the bundle, which undermines navigation integrity.

Suggestions

Ship the four referenced example decks (examples/example-helix.html, -holm.html, -atlas.html, -bluehouse.html) or remove the examples/ entries from the resource map and Step 6/Verification prose to keep references truthful.

Trim the Verification curl block to a one-line check, since the full JSON dump is more provenance than actionable guidance.

Confirm the cross-references to references/components.md and references/themes.md in the Hard rules section match the actual filenames and headings.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence (no basic HTML/CSS primers), using tight tables, a resource map, and direct commands; only minor sections (the Verification curl block, Browser/runtime support) could be trimmed.	4 / 5
Actionability	Provides concrete executable guidance — the P0 grep command, the artifact emit snippet, a slide-rhythm example, and a theme-selection table — with the main remaining gap being that layout snippets live in references rather than inline.	4 / 5
Workflow Clarity	A clear six-step sequence (pre-flight through emit) with an explicit, gating validation checkpoint in Step 5 (P0 theme-lock grep plus the five-dimension 1–5 critique with "Any dimension ≤ 3 → re-do before emit"), giving a real validate→fix→retry feedback loop.	5 / 5
Progressive Disclosure	The overview points to clearly signaled one-level-deep references (themes/layouts/components/checklist), but the resource map and body reference an examples/ directory with four HTML decks that are not present in the bundle, breaking reference integrity and navigation.	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 specifies concrete inputs, output, and outcome with a distinct niche, but lacks an explicit "Use when..." trigger clause and leans on an internal core query rather than natural user phrasing. Completeness and trigger-term quality are the limiting dimensions.

Suggestions

Add an explicit "Use when..." clause naming natural user phrases (e.g., "Use when the user asks to write a feature business case, justify a roadmap decision, or turn an RFC into a decision document").

Replace or supplement the internal core query "pm-feature-business-case-deck" with terms users actually say, such as "business case", "decision deck", or "feature justification".

Consider naming concrete artifact types or extensions the user might mention (e.g., "slide deck", "one-pager", "review pre-read") to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names concrete inputs (PRDs, roadmaps, RFCs, architecture reviews, retros), a specific output (decision documents), and an explicit outcome (approve the feature, architecture, roadmap, or incident follow-up); framed as a transformation rather than a discrete verb list, leaving minor coverage gaps.	4 / 5
Completeness	Has a clear "what" (turn rough materials into decision documents) but only weakly implies "when" via "For product and technical management work" with no explicit "Use when..." clause, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Includes relevant domain terms (PRDs, roadmaps, RFCs, architecture reviews, retros) but anchors on the internal core query "pm-feature-business-case-deck" which users would not naturally say, and misses common synonyms and concrete file-type triggers.	3 / 5
Distinctiveness Conflict Risk	Carves a distinct decision-document / business-case niche anchored by a unique core query, with only minor overlap risk against general deck or PM skills.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nexu-io/open-design
Path: design-templates/replit-deck/SKILL.md
Commit: f580271

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.