CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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'.

68

Quality

86%

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

71%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 strongly actionable, well-sequenced workflow skill: executable scripts, explicit decision rationale formats, validation guards, and a ratification loop. Its main weaknesses are inline template walls that belong in reference files (no bundle files are provided), undefined scaffold variables, and a couple of soft validation gaps (kit-missing warning without exit, no post-scaffold verification).

Suggestions

Move the Phase 2 decision template and the Phase 4 PROJECT-MAP template into reference files (e.g. references/tech-decision-template.md and references/project-map-template.md) and point to them from SKILL.md to improve progressive disclosure.

Define or explicitly derive $BACKEND_LANG and $FRONTEND_FRAMEWORK from Phase 2 decisions before the scaffold script, so the Phase 3 block is copy-paste executable as written.

Harden validation: exit (not just warn) when the method kit is missing in Step 0, and add a post-scaffold check (e.g. verifying key directories/files exist) before 'git add . && git commit'.

DimensionReasoningScore

Conciseness

The body is dense and directive — interview batches, decision templates, an executable scaffold script — with almost no explanation of concepts Claude already knows. Not 5 because the Phase 2 decision template and Phase 4 PROJECT-MAP template run long inline and the Referencias section partly duplicates information; not 3 because there is no genuinely unnecessary explanation, just minor trimming opportunities.

4 / 5

Actionability

Concrete, mostly executable guidance: a runnable Step 0 verification script, a full scaffold bash block, exact template formats, and phase-by-phase instructions. Not 5 because the scaffold script references $BACKEND_LANG and $FRONTEND_FRAMEWORK without ever defining them, and {razón}/{PROJECT_NAME} placeholders require assembly — minor gaps from copy-paste ready; not 3 because the vast majority is directly executable rather than pseudocode.

4 / 5

Workflow Clarity

Phases 0-5 are clearly sequenced with a Step 0 empty-repo guard that exits on risk and an explicit Phase 2 ratification loop ('Loop hasta Chris ratifica todas las decisions'), plus an Anti-patterns checklist. Not 5 because a missing method kit only echoes a warning (no exit), and there is no post-scaffold verification that files landed before the initial commit; not 3 because checkpoints are present for the risky pre-state even if minor validation gaps remain.

4 / 5

Progressive Disclosure

Section structure is clear (phases, anti-patterns, cost guardrails, referencias), but no bundle files exist and roughly 150 lines of templates — the Phase 2 decision format and the Phase 4 PROJECT-MAP — are inlined when they clearly belong in separate reference files the skill could point to. Matches 'some structure but content that should be separate is inline'; not 4 because the split opportunity is substantial, not 2 because structure and navigation are otherwise good.

3 / 5

Total

15

/

20

Passed

Description

100%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 is exemplary: concrete actions with named technologies, an explicit what/when pair, natural trigger phrases including the slash command, and a hard scope boundary that redirects existing-code projects to /project-audit. Voice is third person throughout, with no fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions with comprehensive coverage: 'Entrevista profunda greenfield', 'decide stack (priorizando Luana: FastAPI + Next.js + Clerk + Postgres + Qdrant)', 'scaffold inicial', 'PROJECT-MAP'. Not 4 — there are no minor gaps in the action list; each capability is named and concrete.

5 / 5

Completeness

Explicitly answers both 'what' (interview, stack decision with named technologies, scaffold, PROJECT-MAP) and 'when' ('Activa cuando Chris dice: ...' plus scope boundary 'Para proyectos VACÍOS o casi vacíos'). Matches the anchor with concrete trigger phrases exactly; not 4 because the 'when' clause is fully explicit, not merely present.

5 / 5

Trigger Term Quality

Comprehensive natural trigger coverage including the slash command and synonymous phrases users would actually say: '/project-bootstrap', 'arrancamos proyecto nuevo', 'greenfield', 'desde cero', 'bootstrap proyecto', 'crear scaffold', 'iniciá proyecto'. Not 4 — no natural variation is obviously missing.

5 / 5

Distinctiveness Conflict Risk

Clear greenfield-bootstrap niche with distinct triggers and an explicit negative boundary ('NO ejecutar en proyectos con código existente — usar /project-audit en su lugar') that routes overlapping cases away. Minimal conflict risk; not 4 — the boundary guidance is explicit rather than implied.

5 / 5

Total

20

/

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.

Validation — 13 / 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

Path

claude/skills/project-bootstrap/SKILL.md

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.