he-reframe

Create evidence-backed HE reframe migration programs. Use when structural drift, routing ambiguity, or source-prompt gaps need phased rollback-safe execution.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

85%

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

The body is a well-structured overview with a clearly sequenced, validation-gated procedure and clean progressive disclosure to real bundle files; its main weakness is dense jargon and restated boundary clauses across several sections that could be consolidated for token efficiency.

Suggestions

Consolidate the overlapping boundary statements in Constraints, Execution Boundaries, and Failure Mode into a single source of truth and cross-reference it, trimming repeated tokens.

Where possible, replace multi-clause jargon strings (e.g., 'architecture-evolution compression is high leverage enough to stage before implementation') with shorter imperative phrasing to ease parsing.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept-explanation padding Claude already knows, but it is dense with jargon-laden compound phrases and restates the same boundaries across Constraints, Execution Boundaries, and Failure Mode (e.g., 'do not create Linear objects / do not implement'), so it could be tightened.	2 / 3
Actionability	Concrete procedure directives are paired with executable validation commands ('python3 Plugins/harness-engineering/scripts/check_bluf_structure.py <path> --json', './bin/ask skills audit ... --json') and concrete artifact-path examples, giving copy-paste-ready guidance for an instruction-only skill.	3 / 3
Workflow Clarity	A 12-step numbered Procedure carries explicit gates (step 7: 'If any item is missing, return Do Not Create'), a fail-fast validation loop (step 12 + Validation: 'stop at the first failed gate'), and Blocked feedback, matching the level-3 anchor for sequence with validation checkpoints.	3 / 3
Progressive Disclosure	A dedicated ## References section signals one-level-deep contracts by name, real local bundle files (references/contract.yaml, references/evals.yaml) are present and linked, and the body explicitly directs deep context to references with a context-disposition policy rather than bloating the entrypoint.	3 / 3
	Total	11 / 12 Passed

Description

75%

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 cleanly answers what and when with an explicit Use-when clause and occupies a distinct niche, but its trigger terms lean on domain jargon and it names a single composite action rather than enumerating several concrete operations.

Suggestions

Add one or two more concrete verbs (e.g., 'stage, gate, and roll back') so multiple distinct actions are visible, pushing specificity toward level 3.

Soften trigger jargon with plainer equivalents (e.g., add 'migration' or 'rollback plan' alongside 'HE reframe' and 'structural drift') so users phrase requests more naturally.

Dimension	Reasoning	Score
Specificity	Names the domain and a concrete action ('Create evidence-backed HE reframe migration programs') plus the property 'phased rollback-safe execution', but lists one main action rather than multiple distinct concrete actions like the level-3 anchor (extract, fill, merge).	2 / 3
Completeness	Explicitly states both what it does ('Create evidence-backed HE reframe migration programs') and when to use it via an explicit 'Use when...' clause, matching the level-3 anchor.	3 / 3
Trigger Term Quality	Includes real trigger terms ('structural drift, routing ambiguity, or source-prompt gaps') but they are niche jargon rather than phrasings a user would naturally say, and common variations are missing.	2 / 3
Distinctiveness Conflict Risk	'HE reframe migration programs' is a sharply defined niche with distinct, narrow triggers, making it unlikely to fire for the wrong skill.	3 / 3
	Total	10 / 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: jscraik/Agent-Skills
Commit: 5a6027f

Reviewed: 5 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.