he-reframe
Create evidence-backed HE reframe migration programs. Use when structural drift, routing ambiguity, or source-prompt gaps need phased rollback-safe execution.
36
33%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./Plugins/harness-engineering/skills/he-reframe/SKILL.mdQuality
Discovery
25%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is heavily laden with undefined jargon and buzzwords that make it nearly impossible to understand what the skill actually does or when it should be used. While it follows the structural pattern of 'what + when', the content is too abstract and obscure to be useful for skill selection. It fails to communicate concrete actions or use natural language that a user would employ.
Suggestions
Replace jargon like 'HE reframe migration programs', 'structural drift', and 'routing ambiguity' with plain-language descriptions of what the skill concretely does (e.g., specific file types, operations, or outputs).
Rewrite the 'Use when...' clause with natural trigger terms that a user would actually say when they need this skill, rather than internal technical terminology.
Add 2-3 specific concrete actions the skill performs (e.g., 'generates migration plans', 'validates rollback steps') so Claude can distinguish this from other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses highly abstract jargon like 'HE reframe migration programs', 'structural drift', 'routing ambiguity', and 'source-prompt gaps' without explaining any concrete actions. No specific, understandable capabilities are listed. | 1 / 3 |
Completeness | It technically has both a 'what' ('Create evidence-backed HE reframe migration programs') and a 'when' ('Use when structural drift, routing ambiguity, or source-prompt gaps need phased rollback-safe execution'), but the 'when' clause is so jargon-laden it provides no practical guidance for skill selection. | 2 / 3 |
Trigger Term Quality | The terms used ('structural drift', 'routing ambiguity', 'source-prompt gaps', 'HE reframe migration') are obscure technical jargon that no user would naturally say. These are not natural trigger terms. | 1 / 3 |
Distinctiveness Conflict Risk | The extremely niche jargon makes it unlikely to conflict with other skills, but the terms are so opaque that it's unclear what domain this actually serves, making it hard to assess true distinctiveness. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a heavily process-oriented migration safety framework that demonstrates strong progressive disclosure and reference organization but suffers from excessive jargon, abstract directives, and verbosity. The procedure is sequenced but reads more like an internal governance document than actionable instructions Claude can execute. The skill would benefit significantly from concrete artifact examples, tighter language, and replacing abstract process terminology with specific, executable guidance.
Suggestions
Add a concrete example of a generated reframe program artifact (even abbreviated) showing the expected output structure with schema_version, phases, rollback conditions, and eval proof — this would dramatically improve actionability.
Cut or collapse sections that don't add unique actionable value (Philosophy, Accessibility Requirements, Anti-Patterns) into a single short constraints block to improve token efficiency.
Replace abstract procedure steps like 'Resolve the he-reframe subagent stage map from routing-map.json' with concrete examples showing what the resolution looks like and what decisions result from it.
Add a concrete before/after example in the Examples section showing the actual content structure of a reframe program rather than just describing the filename and high-level intent.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose with heavy jargon and domain-specific terminology that reads more like an internal process document than actionable instructions. Many sections (Philosophy, Anti-Patterns, Accessibility Requirements, Gotchas) add marginal value while consuming significant tokens. Concepts like 'architecture-evolution compression,' 'source-prompt family status,' and 'context-disposition policy' are used without clear definitions, creating density without clarity. | 1 / 3 |
Actionability | The procedure section provides a numbered 12-step workflow and the validation section includes specific commands (e.g., `python3 Plugins/harness-engineering/scripts/check_bluf_structure.py`), which is concrete. However, most steps are abstract directives ('Resolve the he-reframe subagent stage map,' 'Apply the BLUF review contract') rather than executable instructions with concrete examples of what the artifacts should look like or contain. | 2 / 3 |
Workflow Clarity | The 12-step procedure provides a clear sequence with some validation checkpoints (step 7's gate requirements, step 12's pass/fail/blocked outcomes, and the validation section's fail-fast approach). However, the steps are dense and abstract, lacking explicit feedback loops for error recovery within the procedure itself. The handoff rules and failure modes are well-defined but the core workflow lacks concrete validation checkpoints between steps. | 2 / 3 |
Progressive Disclosure | The References section provides well-organized, clearly signaled one-level-deep references to specific contracts, policies, and supporting documents. The skill explicitly states 'Move deep context to references instead of bloating the entrypoint' and follows this principle. Navigation paths are specific and categorized by purpose. Without bundle files to verify, the structure itself is exemplary. | 3 / 3 |
Total | 8 / 12 Passed |
Validation
90%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 |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- jscraik/Agent-Skills
- Commit
4c78f98
- 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.