CtrlK
BlogDocsLog inGet started
Tessl Logo

schema-unify

Migrate a brain from gbrain-base (or any pack) to gbrain-base-v2's 14-canonical-type taxonomy via gbrain onboard --check + the unify-types Minion handler. Collapses 94 noisy types to 15 canonical with subtypes, alias rows, and link rows. Triggers when an agent notices pack_upgrade_available, type_proliferation, or asks "what is the canonical taxonomy / how do I clean up my page types".

74

Quality

92%

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

A thorough, highly actionable migration playbook with a clear phased workflow, validation checkpoints, and rollback guidance. Its main weakness is conciseness — a duplicated anti-patterns section and decorative output blocks add tokens without value.

Suggestions

Merge the two 'Anti-patterns' / 'Anti-Patterns' sections (lines 155 and 209) into one, since both repeat the 'do not run unify-types under autopilot' guidance — this removes the largest redundancy.

Trim the decorative celebration-summary box (lines 232-242) to a one-line example or move it to a reference doc; the structured UnifyTypesResult mention already conveys the output.

Condense the 'Mental model' paragraph, which narrates the pre-migration messiness at length; the essential counts (94 → 15) already appear elsewhere.

DimensionReasoningScore

Conciseness

Dense and competent — no explaining of basic concepts, packed with D8/D13/D14/D15/D17 references and exact commands — but ~220 lines long with redundancy: two overlapping anti-patterns sections ('Anti-patterns' at line 155 and 'Anti-Patterns' at line 209 both say not to run under autopilot) and a decorative celebration-summary box. Could be tightened by deduplicating those sections. Not scored 1 because it does not pad with concepts Claude already knows; not scored 3 because of the verbatim duplication and length.

2 / 3

Actionability

Fully executable, copy-paste-ready guidance throughout: exact CLI commands with flags, params JSON ('--params {"target_pack":"gbrain-base-v2"}'), a jq filter, rollback SQL, and concrete expected outputs. The decision tree and Contract section add specific, actionable branches.

3 / 3

Workflow Clarity

Clear five-phase sequence (Discovery → Preview → Apply → Verify → Post-migration) with explicit validation checkpoints: a dry-run '--explain' before apply, a dedicated Verify phase with expected 'ok' states, and a Rollback section. For a destructive/batch taxonomy migration, the required feedback loops and checkpoints are present.

3 / 3

Progressive Disclosure

Self-contained with a clearly signaled, one-level-deep 'Reference' section pointing to external docs (plan, architecture, pack-upgrade-mechanism, GitHub issue). No nested 2+-level references, and sections are well-organized for navigation; no bundle files exist to verify against, but the structure is clean.

3 / 3

Total

11

/

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 states the capability and provides explicit trigger guidance with natural keyword coverage. It is specific, complete, and unlikely to conflict with other skills.

DimensionReasoningScore

Specificity

Names multiple concrete actions ('Migrate a brain ... to gbrain-base-v2's 14-canonical-type taxonomy', 'Collapses 94 noisy types to 15 canonical with subtypes, alias rows, and link rows') via specific tools (gbrain onboard --check, unify-types Minion handler).

3 / 3

Completeness

Clearly answers what (migrate/collapse types via specific handlers) AND when, with an explicit 'Triggers when an agent notices pack_upgrade_available, type_proliferation, or asks ...' clause. Not capped at 2 because the 'Use when/Triggers when' guidance is explicit, not merely implied.

3 / 3

Trigger Term Quality

Includes natural user phrasings ('clean up my page types', 'unify my types', 'migrate to gbrain-base-v2', '94 types to 14') plus an explicit 'Triggers when ...' clause covering onboard findings. A few terms are jargon-heavy (pack_upgrade_available) but overall strong coverage of terms a user would actually say.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (gbrain taxonomy migration) with distinct triggers and named tools, making overlap with unrelated skills unlikely.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
garrytan/gbrain
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.