CtrlK
BlogDocsLog inGet started
Tessl Logo

review-homecore-migration

Review Home Assistant migration as untrusted versioned input and no-clobber output.

56

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./harness/homecore/.claude/skills/migrate/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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 exceptionally lean and well-structured for a simple instruction-only skill, scoring top marks on conciseness and progressive disclosure. Its weaknesses are abstract actionability and a missing validation feedback loop that caps workflow clarity.

Suggestions

Add a concrete verification/feedback step for the review (e.g., 'Re-validate that no writes clobber existing files and that rejected schema versions are reported back to the user before finishing') to lift the workflow_clarity cap.

Make at least one rule executable with specifics — e.g., name which storage schema versions are supported or how to detect an unsupported one — to raise actionability.

Optionally include a short inline example of an atomic no-clobber write (command or pseudo-code) so the rule is copy-pasteable rather than abstract.

DimensionReasoningScore

Conciseness

Six terse numbered rules with no concept-explanation padding ('Inspect before writing', 'Never expose secret values...'); every token earns its place and the skill assumes Claude's competence. It is not below 5 because nothing is padded or over-explained.

5 / 5

Actionability

Rules are directive ('Reject unsupported storage schema versions', 'Use explicit destinations and atomic no-clobber writes') but lack concrete specifics — no schema version numbers, commands, or examples. It is not a 4 because the guidance, while actionable in intent, is abstract rather than executable, and not a 2 because each rule does prescribe a concrete behavior.

3 / 5

Workflow Clarity

A clear six-step numbered sequence is present, but for a review involving destructive/batch operations (no-clobber writes, schema-version rejection) there is no explicit validate→fix→retry checkpoint; per the rubric, missing validation feedback loops in such contexts caps workflow_clarity at 3. It is not a 4 because verification checkpoints are absent.

3 / 5

Progressive Disclosure

Under 50 lines, single-purpose, no external references needed, and organized as a clean numbered list; per the simple-skill exception this scores 5. No bundle files exist, and the self-contained structure needs no further navigation.

5 / 5

Total

16

/

20

Passed

Description

53%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 states a precise 'what' with a distinctive, low-conflict niche, but provides no 'Use when...' trigger guidance and has thin natural keyword coverage. Its strongest dimension is distinctiveness; completeness is the main cap.

Suggestions

Append a 'Use when...' clause naming natural triggers, e.g. 'Use when reviewing a Home Assistant migration, config-entry import, or storage schema upgrade.'

Add natural verb/synonym trigger terms ('review', 'check', 'audit', 'config-entry', 'schema version') so users would naturally say them when they need the skill.

Expand the 'what' beyond one action to list a couple concrete review operations (e.g., 'reject unsupported schema versions, preserve unknown fields, label incomplete automations') to lift specificity.

DimensionReasoningScore

Specificity

Names the domain ('Home Assistant migration') and two concrete review postures ('untrusted versioned input', 'no-clobber output'), but these are modifiers on a single action rather than a comprehensive list of actions. It is not a 4 because the actions are framed as review stances, not multiple distinct concrete operations.

3 / 5

Completeness

It gives a clear 'what' (review migration as untrusted versioned input and no-clobber output) but entirely lacks a 'when'/'Use when' trigger clause; per the rubric, a missing 'Use when...' caps completeness at 3. It is not a 4 because there is no explicit usage trigger at all.

3 / 5

Trigger Term Quality

'Home Assistant migration' is a natural user phrase, but the description omits common verbs users would say ('review', 'check', 'audit') and any synonyms or version/extension cues. It is not a 4 because several natural trigger terms are missing.

3 / 5

Distinctiveness Conflict Risk

'Home Assistant migration' scoped by 'untrusted versioned input' and 'no-clobber output' carves a clear niche with minor overlap risk against a generic review skill. It is not a 5 because the description lacks distinct trigger phrases that would fully separate it.

4 / 5

Total

13

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ruvnet/RuView
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.