CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

new-project-bootstrap

Comprehensive bootstrap flow for a brand-new project. Begins with a deep-dive architectural conversation, then runs a plan → implement → review chain, and finally writes the initial UML.md. Load this when the user starts pi in an empty or near-empty directory, or when explicitly asked to bootstrap a new project.

Quality

97%

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

100%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 body is an exemplary process skill: concise, immediately actionable, and sequenced with explicit user-confirmation and plan-update checkpoints. All content belongs inline for a skill of this scope, and cross-skill references are clearly signaled with fallbacks.

DimensionReasoningScore

Conciseness

The body is lean and efficient: terse question batches, a compact plan template, and three-bullet guardrails, with no explanation of concepts Claude already knows ('walking skeleton' is used without definition). Not 4 because there is no over-explanation to trim; every section earns its place.

5 / 5

Actionability

Fully actionable for an instruction-only skill: 12 copy-paste-ready interview questions in four labeled batches, a concrete plan.md template, an explicit phase-4 self-review checklist, and build + smoke-test steps. Not 4 because guidance is specific enough to execute directly with no gaps.

5 / 5

Workflow Clarity

Four phases are explicitly sequenced ('Do not skip phases') with validation checkpoints throughout: wait-for-answers, user confirmation of the summary, explicit approval before phase 3, a stop-and-update-the-plan feedback loop, and a phase-4 review/build/report step. Not 4 because checkpoints are explicit and include error-recovery loops.

5 / 5

Progressive Disclosure

The ~80-line body is self-contained with well-organized per-phase sections, and no content needs splitting into separate files. External skill references ('planning-first', 'uml-maintenance') are clearly signaled with an inline fallback ('if it is available; otherwise use this structure'), keeping navigation one level deep. Not 4 because organization and signal placement have no notable gaps.

5 / 5

Total

20

/

20

Passed

Description

92%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 description that clearly states concrete capabilities and provides an explicit, condition-based trigger clause. The only weakness is slightly limited trigger synonym coverage, which leaves a small chance of missing phrasings users might naturally use.

DimensionReasoningScore

Specificity

Lists multiple concrete actions covering the full flow — 'deep-dive architectural conversation', 'plan → implement → review chain', 'writes the initial UML.md' — with comprehensive coverage of what the skill does. Not 4, since there are no minor gaps in coverage; the described actions span the entire skill workflow.

5 / 5

Completeness

Explicitly answers both 'what' (architectural conversation, plan/implement/review chain, writes UML.md) and 'when' ('Load this when the user starts pi in an empty or near-empty directory, or when explicitly asked to bootstrap a new project') with concrete trigger conditions. Not 4 because the 'when' clause is explicit and specific rather than needing more precision.

5 / 5

Trigger Term Quality

Natural trigger phrases like 'bootstrap a new project', 'brand-new project', and 'empty or near-empty directory' are present and would plausibly be said by users. Not 5 because common synonyms and variations ('scaffold', 'start a new project', 'initialize', 'greenfield') are missing; not 3 since keyword coverage is good rather than partial.

4 / 5

Distinctiveness Conflict Risk

Clear niche — bootstrapping a brand-new project in an empty or near-empty directory — with distinct triggers unlikely to fire for general planning or coding skills. Not 4 because overlap risk is minimal, not merely reduced.

5 / 5

Total

19

/

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

g23polar/dotfiles

Path

pi/agent/skills/new-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.