blueprint

Turn a one-line objective into a step-by-step construction plan any coding agent can execute cold. Each step has a self-contained context brief — a fresh agent in a new session can pick up any step without reading prior steps.

Quality

40%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/blueprint/SKILL.md

Quality

Content

36%Scale 1-5

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

This skill reads more like a README or marketing page for a tool than an actionable skill for Claude. It explains what Blueprint does conceptually but fails to provide the concrete, executable guidance Claude needs to actually generate plans, handle edge cases, or validate outputs. The content would benefit significantly from showing actual plan output format, template structure, and step-by-step operational instructions rather than abstract pipeline descriptions.

Suggestions

Add a concrete example showing the actual output format of a generated plan (e.g., the markdown structure with context briefs, dependency graphs, branch naming) so Claude knows what to produce.

Replace the abstract 'How It Works' pipeline with actionable steps including specific commands, expected outputs at each stage, and what to do when the review step rejects the plan.

Remove or drastically shorten the 'Key Differentiators' section — it's marketing copy that doesn't help Claude execute the skill.

Add validation checkpoints: how to verify the plan is well-formed, how to check that context briefs are truly self-contained, and what constitutes a passing adversarial review.

Dimension	Reasoning	Score
Conciseness	The skill includes some unnecessary sections like 'Key Differentiators' which reads like marketing copy rather than actionable guidance. The 'How It Works' section explains the tool's internal pipeline which Claude doesn't need explained — it needs to know how to invoke and configure it. The 'When to Use This Skill' section is reasonable but could be tighter.	3 / 5
Actionability	The skill shows how to invoke the command (`/blueprint <project> <objective>`) and how to install it, but provides no concrete guidance on what the generated plan looks like, how to customize templates, what the output format is, how to handle review feedback, or how to execute/modify plans. The 'How It Works' section describes an abstract pipeline without executable details.	2 / 5
Workflow Clarity	The 5-step 'How It Works' pipeline is described at a high level but lacks any validation checkpoints, error handling, or concrete commands for each step. There's no guidance on what to do if research fails, if the review rejects the plan, or how to iterate. For a multi-step planning tool that generates construction plans, the workflow for using and acting on those plans is critically underspecified.	2 / 5
Progressive Disclosure	The skill references external examples (small-plan.md, large-plan.md) and a GitHub repository, which is good progressive disclosure. However, no bundle files are provided, so we can't verify these references exist. The main content itself could benefit from separating the conceptual overview from the operational guide, and the inline content doesn't clearly signal what additional detail lives where.	3 / 5
	Total	10 / 20 Passed

Description

45%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 communicates a reasonably unique concept — converting objectives into agent-executable step-by-step plans — but lacks explicit trigger guidance ('Use when...') and misses common natural language terms users would employ. The specificity is moderate; it describes the approach conceptually but doesn't enumerate concrete actions or outputs.

Suggestions

Add an explicit 'Use when...' clause with trigger phrases like 'break down this task', 'create an implementation plan', 'decompose into steps', or 'plan this project for an agent'.

Include more natural user-facing keywords and synonyms such as 'task breakdown', 'implementation plan', 'project decomposition', 'work plan', and 'coding roadmap'.

Specify concrete outputs or actions, e.g., 'Generates a numbered plan with context briefs, dependency notes, and acceptance criteria for each step.'

Dimension	Reasoning	Score
Specificity	The description names the domain (turning objectives into construction plans) and describes a couple of concrete aspects (step-by-step plan, self-contained context briefs), but lacks specifics about what format, tools, or outputs are involved. It's more conceptual than action-oriented.	3 / 5
Completeness	The 'what' is moderately clear (converts objectives into agent-executable plans with self-contained steps), but there is no explicit 'when' clause or trigger guidance. The absence of a 'Use when...' clause caps this at 3, and the 'what' is only moderately specific, bringing it to 2.	2 / 5
Trigger Term Quality	Terms like 'step-by-step', 'construction plan', 'coding agent', and 'objective' are somewhat relevant, but it misses natural user phrases like 'break down task', 'implementation plan', 'project plan', 'decompose', 'task breakdown', or 'plan coding work'.	3 / 5
Distinctiveness Conflict Risk	The niche of creating agent-executable construction plans with self-contained context briefs is fairly distinctive. It could overlap with general 'planning' or 'task decomposition' skills, but the specific framing around coding agents and cold-start execution reduces conflict risk.	4 / 5
	Total	12 / 20 Passed

Validation

90%

Warnings & errors only

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

Validation — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/blueprint/SKILL.md
Commit: 57c135b

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.