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

81%

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

62%

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

A well-structured overview with a clear, validated 5-phase pipeline and concrete examples, but it is held back by tangential padding and by naming features (anti-pattern catalog, mutation protocol, plan template) without specifying them. Tightening the install/meta sections and providing an actual plan-file template would lift the weaker dimensions.

Suggestions

Trim or move the Installation and 'Zero runtime risk' sections out of the execution path; they are meta-information about the skill package, not guidance an agent needs to run the pipeline, and they pad the token budget.

Add a concrete Markdown template for the plan file (step context brief, task list, verification commands, exit criteria) so the Draft phase is copy-paste ready rather than described in prose.

Either specify the anti-pattern catalog entries and the plan mutation protocol's 'formal protocols' inline, or split them into one-level-deep reference files (e.g. ANTI_PATTERNS.md, MUTATION_PROTOCOL.md) linked from the body to improve both actionability and progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The pipeline, examples, and key-features sections are efficient, but the Installation section (ECC/git-fetch/vendored-copy details) and the "Zero runtime risk" paragraph ("no hooks, no shell scripts, no executable code, no package.json, no build step") add tangential padding that could be trimmed; not score 3 because not every token earns its place, and not score 1 because it does not explain concepts Claude already knows.	2 / 3
Actionability	Provides concrete command invocations and output structure (Step 1-5 examples, invariants like "all existing tests pass"), but the core plan-file artifact has no actual Markdown template and named features like "anti-pattern catalog" and "formal protocols" are described but not specified; not score 3 because key implementation details are missing, and not score 1 because the guidance is concrete rather than abstract.	2 / 3
Workflow Clarity	The 5-phase pipeline (Research -> Design -> Draft -> Review -> Register) is clearly sequenced with an explicit adversarial review gate and a fix-before-finalize feedback loop against a checklist/anti-pattern catalog; not score 2 because validation checkpoints and error recovery are explicit, not merely implicit.	3 / 3
Progressive Disclosure	Well-organized into clear sections with no nested references, but it is a single ~90-line monolithic file with no reference splitting and tangential inline content (Installation, Zero runtime risk) that could live elsewhere or be trimmed; not score 3 because it lacks the overview-to-one-level-deep-references pattern, and not score 1 because it is not an unorganized wall of text.	2 / 3
	Total	9 / 12 Passed

Description

100%

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, third-person description that concretely names its capabilities, gives natural trigger terms, and explicitly answers both what it does and when to use it with a negative-trigger guard. It is comprehensive and clearly distinguishable from adjacent skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — "adversarial review gate, dependency graph, parallel step detection, anti-pattern catalog, and plan mutation protocol" plus "self-contained context brief" — matching the anchor for naming several specific actions; not score 2 because coverage is comprehensive rather than partial.	3 / 3
Completeness	Explicitly states what ("Turn a one-line objective into a step-by-step construction plan...") and when via a "TRIGGER when:" clause plus a "DO NOT TRIGGER when:" exclusion; not score 2 because the when is explicit, not merely implied.	3 / 3
Trigger Term Quality	Uses natural terms a user would say — "plan, blueprint, or roadmap", "complex multi-PR task", "multiple sessions" — with good synonym coverage; not score 2 because common variations are well represented rather than missing.	3 / 3
Distinctiveness Conflict Risk	Clear niche (multi-session, multi-agent, multi-PR) with distinct triggers and a negative trigger excluding single-PR/few-tool-call tasks; not score 2 because the DO NOT TRIGGER clause sharpens it against overlap with general planning skills.	3 / 3
	Total	12 / 12 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: 754b8dd

Reviewed: 2 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.