blueprint

Turn a one-line objective into a step-by-step construction plan for multi-session, multi-agent engineering projects. Each step has a self-contained context brief so a fresh agent can execute it cold. Includes adversarial review gate, dependency graph, parallel step detection, anti-pattern catalog, and plan mutation protocol. TRIGGER when: user requests a plan, blueprint, or roadmap for a complex multi-PR task, or describes work that needs multiple sessions. DO NOT TRIGGER when: task is completable in a single PR or fewer than 3 tool calls, or user says "just do it".

Quality

88%

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

The canonical home for this skill is tdg-personal/blueprint

Quality

Content

81%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 well-structured, mostly actionable skill body with a clear validated pipeline and good organization. The main weaknesses are minor verbosity in the Installation section and features that are advertised but not detailed anywhere.

Suggestions

Trim the Installation section (ECC vs vendored update commands) to the essential one-line statement that the skill ships with ECC, removing the git fetch/log/checkout walkthrough.

Either elaborate the 'anti-pattern catalog' and 'plan mutation protocol' inline or move them into reference files (e.g., ANTI_PATTERNS.md, MUTATION.md) linked from the body so advertised features are actually delivered.

Tighten the 'Zero runtime risk' bullet to a single clause rather than enumerating every absent artifact (hooks, scripts, package.json, build step).

Dimension	Reasoning	Score
Conciseness	The core sections (When to Use, How It Works, Examples, Key Features) are efficient, but the Installation section's ECC/vendored git-update instructions and the defensive 'Zero runtime risk' bullet are minor over-explanation that could be trimmed.	4 / 5
Actionability	Concrete invocations like '/blueprint myapp "migrate database to PostgreSQL"' with specific resulting step lists, plus per-step verification commands and exit criteria, give mostly executable guidance, though execution is described as prose rather than copy-paste code.	4 / 5
Workflow Clarity	A clearly sequenced 5-phase pipeline (Research → Design → Draft → Review → Register) with an explicit adversarial Review validation gate, a fix-before-finalize feedback loop, pre-flight checks, and per-step exit criteria.	5 / 5
Progressive Disclosure	Well-organized single-file skill with clear section headers and no bundle files to reference, but the anti-pattern catalog and plan mutation protocol are only named as features rather than elaborated or split into reference files, leaving minor organization gaps.	4 / 5
	Total	17 / 20 Passed

Description

96%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, gives explicit positive and negative trigger guidance, and carves out a defined niche. Only minor overlap risk remains because the trigger words are broadly used.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'step-by-step construction plan', 'self-contained context brief', 'adversarial review gate', 'dependency graph', 'parallel step detection', 'anti-pattern catalog', and 'plan mutation protocol' — giving comprehensive, non-vague coverage.	5 / 5
Completeness	Explicitly answers both what (construction plan with context briefs and review gate) and when, with concrete 'TRIGGER when' and 'DO NOT TRIGGER when' phrases.	5 / 5
Trigger Term Quality	Uses natural synonyms users would actually say — 'plan', 'blueprint', 'roadmap' — plus 'multi-PR task' and 'multiple sessions', giving comprehensive coverage of the domain's natural terms.	5 / 5
Distinctiveness Conflict Risk	The multi-PR/multi-session niche and the 'DO NOT TRIGGER when task is completable in a single PR' guard make it mostly distinct, but 'plan/blueprint/roadmap' are broad terms with minor overlap risk against general planning skills.	4 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: skills/blueprint/SKILL.md
Commit: 06c5e11

Reviewed: 3 days 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.