CtrlK
BlogDocsLog inGet started
Tessl Logo

bazaar

Orchestrating super-premium landing-page pipelines (Discover to Launch) across 6 craft axes with rubrics and quality gates. Not for a single LP section (Funnel) or design-only chains (Atelier).

56

Quality

63%

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 ./.archive/bazaar/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

73%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-structured, action-dense orchestration spec with an excellent gated workflow and clear reference navigation. Its main weakness is redundancy — thresholds and rules restated across multiple sections plus a duplicated hidden capabilities block — that inflates token cost without adding executable value.

Suggestions

Make the Quality Gates table the single authority for numeric thresholds and remove the duplicate Lighthouse/CWV/WCAG/GEO numbers repeated in Quality Disciplines and the Handoff Protocol paragraph.

Delete or shrink the hidden CAPABILITIES_SUMMARY / COLLABORATION_PATTERNS / BIDIRECTIONAL_PARTNERS HTML comment block, which restates content already in the visible body.

Consolidate fan-out caps, Atelier delegation thresholds, and route-out rules so each appears in one place (Core Contract) rather than being restated in Core Rules, Boundaries, Subcommand Dispatch, and Output Routing.

DimensionReasoningScore

Conciseness

The body is dense and never explains concepts Claude already knows, but it repeats the same thresholds and rules across the Core Contract, Core Rules, Boundaries, Quality Disciplines, and Quality Gates, and the hidden CAPABILITIES_SUMMARY comment block duplicates the visible body — several padded sections that could be deduplicated.

3 / 5

Actionability

Highly concrete guidance throughout — named recipe subcommands, stage/delegate routing, numeric thresholds, file paths, and handoff schemas — with the main gap being that the deepest executable detail is deferred to reference files that are not present in the bundle.

4 / 5

Workflow Clarity

An 11-phase pipeline is clearly sequenced in the Workflow table with per-stage delegates, and the Quality Gates table provides explicit per-stage validation checkpoints plus repair/escalate feedback loops (≤1 retry, then escalate), satisfying the batch-operation validation requirement.

5 / 5

Progressive Disclosure

A well-signaled Reference Map table points one-level-deep to reference/_common files with clear 'Read This When' guidance, but the referenced files do not exist in the bundle and the 289-line body inlines several near-reference-grade tables, leaving minor organization gaps.

4 / 5

Total

16

/

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 nails a distinct niche and explicit boundaries, but relies on one high-level action verb and jargon-forward phrasing while omitting any positive 'Use when...' trigger guidance. It reads more as a positioning statement than a trigger-ready capability description.

Suggestions

Add a positive 'Use when...' clause naming concrete triggers, e.g. 'Use when building a full landing page from a brief across research, copy, design, build, and launch.'

Replace jargon ('super-premium', 'craft axes', 'Discover to Launch') with plain user-facing terms ('landing page', 'LP build', 'from brief to launch') so natural phrasings surface it.

List 2-3 concrete orchestration actions (select a recipe, dispatch stage delegates, enforce quality gates) instead of the single verb 'Orchestrating'.

DimensionReasoningScore

Specificity

Names the domain ('super-premium landing-page pipelines', 'Discover to Launch') and one main action ('Orchestrating ... across 6 craft axes with rubrics and quality gates'), but stops at a single orchestration verb rather than listing multiple concrete actions.

3 / 5

Completeness

The 'what' is clear, but there is no positive 'Use when...' clause; the only 'when' guidance is a negative boundary ('Not for a single LP section (Funnel) or design-only chains (Atelier)'), which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

Includes natural-ish terms ('landing-page', 'LP') but leans on jargon ('super-premium', 'craft axes', 'Discover to Launch') and omits the common phrasings a user would actually say ('build a landing page', 'create an LP').

3 / 5

Distinctiveness Conflict Risk

Explicit carve-outs naming sibling skills (Funnel, Atelier) give it a clear niche with low conflict risk, but the thin positive trigger language leaves minor overlap risk with the broader LP/design space, so it sits below a 5.

4 / 5

Total

13

/

20

Passed

Validation

100%

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
simota/agent-skills
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.