CtrlK
BlogDocsLog inGet started
Tessl Logo

project-bootstrap

Entrevista profunda greenfield + decide stack (priorizando Luana: FastAPI + Next.js + Clerk + Postgres + Qdrant) + scaffold inicial + PROJECT-MAP. Para proyectos VACÍOS o casi vacíos. NO ejecutar en proyectos con código existente — usar /project-audit en su lugar. Activa cuando Chris dice: '/project-bootstrap', 'arrancamos proyecto nuevo', 'greenfield', 'desde cero', 'bootstrap proyecto', 'crear scaffold', 'iniciá proyecto'.

66

Quality

81%

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

SKILL.md
Quality
Evals
Security

Quality

Content

68%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.

A highly actionable, well-structured greenfield bootstrap skill with a strong scaffold script and clear phasing. Its main weaknesses are a missing validation checkpoint before the destructive git-init/commit step in the batch scaffold, and some tightening potential in the Phase 2 decision template.

Suggestions

Add an explicit validation checkpoint in Phase 3 between scaffolding and 'git init + git add + git commit' (e.g. verify KIT_PATH templates resolved and no overwrite of tracked files), with a fix-and-retry loop, to lift workflow_clarity above the destructive-operation cap.

Tighten the Phase 2 'Tech decisions' template: condense the per-decision rationale blocks or move the full Decisión 1-10 templates into a reference file, keeping only the format contract inline.

Since this skill has no local bundle files, either add bundled templates under references/scripts so the scaffold is self-contained, or make the Referencias section explicitly note that templates live in the external luana-method kit at $KIT_PATH.

DimensionReasoningScore

Conciseness

The body is mostly efficient and assumes Claude's competence, but the long Phase 2 'Tech decisions' template (Decisión 1-10 with full rationale blocks) and repeated inline file-tree/project-map blocks add bulk that goes beyond what is strictly needed, so it is tightenable rather than lean.

3 / 5

Actionability

Phase 3 provides a fully executable, copy-paste-ready scaffold bash script with concrete mkdir/cp/sed/git commands covering the common cases, and Phase 0 includes a runnable state-check; placeholders are explicitly interpolation-driven.

5 / 5

Workflow Clarity

Steps are clearly sequenced across Phase 0-5, but Phase 3 is a batch filesystem-mutating/destructive scaffold with no validation checkpoint between scaffold and the irreversible git init + initial commit, so the validation-gap cap applies.

3 / 5

Progressive Disclosure

Well-organized into phased sections with a clear overview, and it points to external kit paths and sibling skills via a Referencias block; however no bundle files exist in this skill's references/scripts/assets, so navigation is to external kit locations rather than a bundled one-level-deep reference set.

4 / 5

Total

15

/

20

Passed

Description

95%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.

A strong, highly specific description with concrete actions, the default stack named, explicit trigger phrases, and a clear when-NOT boundary. The only minor weakness is that scaffold actions are summarized rather than enumerated.

DimensionReasoningScore

Specificity

Lists several concrete actions ('Entrevista profunda greenfield + decide stack + scaffold inicial + PROJECT-MAP') and the exact default stack (FastAPI + Next.js + Clerk + Postgres + Qdrant), but does not enumerate scaffold sub-actions exhaustively, leaving minor coverage gaps.

4 / 5

Completeness

Explicitly answers both what it does (interview + stack decision + scaffold + PROJECT-MAP) and when to use it ('Activa cuando Chris dice...') with concrete trigger phrases, plus an explicit when-NOT guard ('NO ejecutar en proyectos con código existente').

5 / 5

Trigger Term Quality

Comprehensive coverage of natural trigger phrases Chris would say ('arrancamos proyecto nuevo', 'greenfield', 'desde cero', 'bootstrap proyecto', 'crear scaffold', 'iniciá proyecto', plus the literal '/project-bootstrap'), including synonyms and variations.

5 / 5

Distinctiveness Conflict Risk

Clear greenfield niche with the explicit anti-trigger pointing to /project-audit for existing-code projects, minimizing overlap and conflict with sibling skills.

5 / 5

Total

19

/

20

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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

referenced_paths_exist

Referenced path issues: 5 missing, 2 deeper-than-1-level

Warning

Total

13

/

16

Passed

Repository
alpacapurpura/luana-method
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.