CtrlK
BlogDocsLog inGet started
Tessl Logo

build-daily-inspiration-sites

Turn a completed daily UI inspiration capture into exactly five original landing-page builds, one per separate Codex task, using Sites. Use when the user asks to turn the daily inspiration references, a five-item UI prompt pack, or a dated `*-ui-inspiration-capture` article into distinct HTML landing pages while changing the source brands, names, copy, people, numbers, pricing, claims, and imagery.

74

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured orchestration skill with a clear sequenced workflow, concrete commands and templates, and proper progressive disclosure through one real reference file and one real script. The main weakness is repetition of the originality boundary across multiple sections.

Suggestions

Consolidate the repeated originality/replacement boundary list (brands, names, copy, people, numbers, pricing, claims, imagery) into a single canonical statement in 'Preserve the boundary' and reference it from sections 2, 3, 5, and the Completion checks to reduce token duplication.

In section 2, the guidance to 'Search the five proposed names against one another for accidental similarity' could name the concrete comparison step or tool rather than leaving the check implicit.

Section 4 mixes projectless targets and worktree creation; splitting the 'when to use a worktree' decision into its own short subsection would make the branching path more scannable.

DimensionReasoningScore

Conciseness

The body is dense and operational with no padding about concepts Claude already knows, but the originality/replacement boundary list (brands, names, copy, people, numbers, pricing, claims, imagery) is restated across 'Preserve the boundary', sections 2, 3, 5, and the completion checks. Not a 3 because that repetition could be consolidated into one canonical list referenced from each section; not a 1 because the prose is otherwise lean and assumes competence.

2 / 3

Actionability

Provides concrete executable guidance: a real validation command 'node <skill-dir>/scripts/validate_capture.mjs <article-dir>/manifest.json', exact non-fenced Markdown image syntax, a concrete task-title pattern 'Build <Brand> landing page', and a full prompt template in the referenced contract. Not a 2 because the instructions are copy-paste ready rather than pseudocode.

3 / 3

Workflow Clarity

Six numbered sections form a clear sequence with explicit validation checkpoints: 'Stop if validation fails', build-then-'fix failures', 'Confirm all five tasks are active', and a dedicated Completion checks list. Not a 2 because validation feedback loops and checkpoints are explicit for this batch operation.

3 / 3

Progressive Disclosure

The body is an overview that signals one-level-deep references clearly — 'Read [references/thread-brief-contract.md](references/thread-brief-contract.md)' and the validate_capture.mjs script — both of which exist as real bundle files, and the detailed prompt contract is appropriately split out rather than inlined. Not a 2 because references are well signaled and only one level deep.

3 / 3

Total

11

/

12

Passed

Description

100%

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 strong, specific description that names concrete actions, provides an explicit 'Use when' trigger with multiple natural phrasings, and occupies a distinct niche. Voice is appropriately imperative/third-person with no first- or second-person phrasing.

DimensionReasoningScore

Specificity

Lists multiple concrete actions: 'exactly five original landing-page builds, one per separate Codex task, using Sites' plus an explicit replacement list (brands, names, copy, people, numbers, pricing, claims, imagery). Not the level below because it goes beyond naming the domain to enumerate specific operations.

3 / 3

Completeness

Explicitly answers both what ('Turn a completed daily UI inspiration capture into exactly five original landing-page builds') and when ('Use when the user asks to turn...'). Not a 2 because the 'Use when' trigger clause is present and explicit.

3 / 3

Trigger Term Quality

Covers natural trigger phrasings a user of this workflow would say: 'daily inspiration references', 'a five-item UI prompt pack', 'a dated *-ui-inspiration-capture article', and 'distinct HTML landing pages'. Not a 2 because it lists several relevant variations rather than a single keyword.

3 / 3

Distinctiveness Conflict Risk

Occupies a very specific niche (five-item UI inspiration capture → five Codex/Sites landing pages) with distinct triggers unlikely to fire for unrelated skills. Not a 2 because the scope is too narrow to overlap meaningfully with generic web-build skills.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
MengTo/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.