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

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./Plugins/harness-engineering/skills/he-reframe/SKILL.md

Quality

Content

67%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.

The body is a well-structured, actionable instruction skill with concrete validation commands and a clear phased procedure. Its main weaknesses are repeated boundary statements across three sections and a few dangling or unreferenced bundle paths.

Suggestions

Merge the overlapping do-not statements in Preconditions, Constraints, and Execution Boundaries into a single authoritative boundary list to recover tokens.

Reconcile the reference list with the actual bundle: either add the missing `../../references/...` files or note they live in a shared cross-skill tree, and reference `references/task-profile.json` from the Inputs or Procedure section.

Number the validation checkpoints inside the Procedure (e.g., an explicit "Validate before writing" step) so the fail-fast loop is as explicit as the good_overall workflow example.

Dimension	Reasoning	Score
Conciseness	The body is dense and avoids padding of concepts Claude already knows, but Preconditions, Constraints, and Execution Boundaries repeatedly restate the same "do not mutate code / create Linear objects / author strategy" boundaries and could be consolidated.	3 / 5
Actionability	Concrete paths (`.harness/reframes/**`), an explicit return-field list, and copy-paste validation commands (`check_bluf_structure.py ... --json`, `./bin/ask skills audit ... --json`) give mostly executable guidance with only minor gaps.	4 / 5
Workflow Clarity	A 12-step procedure with explicit fail-fast validation and a Blocked feedback loop sequences the work clearly; the destructive/batch operations have validation present, though a couple of checkpoints are implicit rather than numbered.	4 / 5
Progressive Disclosure	Section structure is good with well-signaled one-level references and a deferred-context index, but several `../../references/...` paths are not present in the bundle and the bundled `references/task-profile.json` is never referenced from the body.	4 / 5
	Total	15 / 20 Passed

Description

62%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.

The description cleanly states both capability and trigger conditions for a specialized internal skill, but its reliance on harness-engineering jargon limits natural-language trigger quality and broad specificity. It is distinct within its niche but overlaps slightly with sibling he-* skills.

Suggestions

Add a plain-language capability verb or two (e.g., "stage", "draft", "gate") alongside "Create" so the action set reads as more than one concrete action.

Soften or supplement the trigger terms with user-natural phrasing (e.g., "migration plan", "rollback plan", "architecture change") so non-jargon users can still surface the skill.

Add a one-clause disambiguator (e.g., "route formal strategy docs to he-strategy") in the description to reduce sibling-skill overlap.

Dimension	Reasoning	Score
Specificity	Names the domain and 1-2 concrete actions ("Create evidence-backed HE reframe migration programs", "phased rollback-safe execution") but the action set is not comprehensive and is wrapped in internal jargon rather than plain capabilities.	3 / 5
Completeness	It explicitly answers both what ("Create evidence-backed HE reframe migration programs") and when ("Use when structural drift, routing ambiguity, or source-prompt gaps need phased rollback-safe execution"), though the when-clause leans on specialized terms.	4 / 5
Trigger Term Quality	The "Use when structural drift, routing ambiguity, or source-prompt gaps" triggers are domain-relevant keywords, but they are internal HE jargon rather than phrases a user would naturally say, and common synonyms are missing.	3 / 5
Distinctiveness Conflict Risk	"HE reframe migration programs" is a clear niche with distinct triggers, but it sits in a family of sibling he-* skills (he-strategy, he-spec, he-plan, he-work) creating minor overlap risk.	4 / 5
	Total	14 / 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: jscraik/Agent-Skills
Path: Plugins/harness-engineering/skills/he-reframe/SKILL.md
Commit: 2f91362

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.