CtrlK
BlogDocsLog inGet started
Tessl Logo

slate-patch

Fix Slate v2 bugs in one pass with reproduction, behavior tests, architecture/DX/perf pressure, proactive rearchitecture when the patch is not the cleanest long-term shape, and final autoreview.

57

Quality

68%

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 ./.agents/skills/slate-patch/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%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 content is a strong, highly actionable workflow document: an eight-stage pipeline with genuine validation feedback loops, copy-paste commands, and explicit ownership rules. Its weaknesses are structural — a Hard Rules section that duplicates the workflow, a machine-specific absolute path, and a coverage matrix inlined in SKILL.md despite the skill itself stating such expectations belong in a reference doc.

Suggestions

Move the Editor Selection Navigation Coverage matrix detail (lines 200-231) into docs/slate-v2/selection-navigation-coverage.md and keep only the pointer plus the 'name command/direction/topology/state' summary inline, per the skill's own rule that oversized expectations go to a reference doc.

Deduplicate Hard Rules against the workflow sections — keep Hard Rules to true invariants and let the Architecture Pressure Review and Benchmark Target Handoff sections own their details, cutting roughly 30-40 lines.

Replace the machine-specific absolute path '/Users/zbeyens/git/plate-2/.agents/skills/autoreview/scripts/autoreview' with a checkout-relative invocation so the command is executable on any machine.

DimensionReasoningScore

Conciseness

The body is dense, imperative, and almost entirely project-specific with no explanations of concepts Claude already knows, but the 'Hard Rules' section substantially duplicates the workflow sections (architecture pressure, benchmark handoff, and autoreview rules each appear twice across ~370 lines), leaving trimmable repetition that keeps it below the 'every token earns its place' anchor.

4 / 5

Actionability

Concrete commands ('pnpm bench:targets:check', 'pnpm bench:targets:dry-run -- <target-id>', the autoreview invocation with cwd), explicit file paths, a red-test taxonomy, and an explicit verdict enum make the guidance mostly executable; the machine-specific absolute path '/Users/zbeyens/git/plate-2/...' and a few abstract directives ('review it like a harsh Slate maintainer') are the minor gaps.

4 / 5

Workflow Clarity

Eight clearly sequenced workflow stages each carry explicit validation checkpoints and feedback loops: rework-before-verify on a weak pressure review, an explicit keep/rework/escalate verdict, verify gates with unrelated-debt recording, and 'rerun focused proof and autoreview until no accepted/actionable findings remain'.

5 / 5

Progressive Disclosure

No bundle files (references/, scripts/, assets/) exist, and the body inlines a detailed selection-navigation coverage matrix whose authoritative version is stated to live in 'docs/slate-v2/selection-navigation-coverage.md' — content that should be separate is inline — though section headers are well organized and the external references are named explicitly rather than buried.

3 / 5

Total

16

/

20

Passed

Description

58%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 has a strong, specific 'what' built from five concrete workflow actions in a distinct niche, but it completely lacks a 'when to use' clause and natural trigger terms, capping completeness and trigger-term quality. Adding explicit trigger guidance with user-facing vocabulary would lift it substantially.

Suggestions

Append a 'Use when...' clause naming natural trigger phrases, e.g. 'Use when the user reports a Slate v2 editor bug (selection, focus, undo, clipboard, rendering) and wants a fix, not a plan.'

Expand 'architecture/DX/perf pressure' into plain wording such as 'review the patch for architecture, API, and performance quality' so the action is concrete rather than compressed jargon.

Name the bug categories the skill handles (selection, history, normalization, IME, rendering) to widen natural keyword coverage and further separate it from slate-plan/slate-ar.

DimensionReasoningScore

Specificity

Names five concrete actions spanning the fix lifecycle ("reproduction, behavior tests, architecture/DX/perf pressure, proactive rearchitecture... final autoreview") but compressed jargon like "architecture/DX/perf pressure" and no scope hints (bug classes, editor domain) leave minor gaps, matching the 'several specific actions' anchor rather than comprehensive coverage.

4 / 5

Completeness

It clearly answers 'what' (one-pass Slate v2 bug fixing with a named workflow) but contains no 'when' clause or equivalent explicit trigger guidance, which the judging guidelines cap at 3.

3 / 5

Trigger Term Quality

"Slate v2 bugs" is a relevant keyword, but the description lacks any 'Use when' phrasing and omits natural user terms like regression, selection, or editor, matching the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

"Slate v2" pins a clear niche with minimal conflict risk, but the description does not distinguish this skill from its sibling planning/perf lanes, so a user wanting an architecture plan could still trigger it; mostly distinct with minor overlap risk.

4 / 5

Total

14

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

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

Warning

Total

13

/

16

Passed

Repository
udecode/plate
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.