major-task

Work heavyweight framework or library tasks with planning-first research, selective deep analysis, and rigorous handoff

Quality

59%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/major-task/SKILL.md

Quality

Content

63%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.

A well-structured, actionable orchestration skill with concrete commands, clear sequenced workflows, and explicit verification checkpoints. Its main weaknesses are repetition of PR/tracker-sync guidance across sections and a monolithic single-file structure with no progressive disclosure into reference files.

Suggestions

Consolidate the PR/tracker-sync-back rules that recur across Tracked Task Rules, Verification, Final Handoff, and Post Back To Tracker into a single authoritative section referenced from the others.

Split the "Load Skills Only When Justified" helper catalog and the per-lane Execution Paths into reference files (e.g. HELPERS.md, EXECUTION-PATHS.md) so SKILL.md reads as an overview with one-level-deep navigation.

Tighten the redundant verification bullets (e.g. PR-creation and tracker-comment rules appear multiple times) to recover token budget.

Dimension	Reasoning	Score
Conciseness	The body uses terse imperative bullets and avoids concept-explanation padding, but PR/tracker-sync and verification guidance is repeated across Tracked Task Rules, Verification, Final Handoff, and Post Back To Tracker and could be consolidated.	3 / 5
Actionability	Concrete executable guidance is present throughout (`gh issue view`, the autogoal create script with exact flags, exact changeset markdown blocks, specific paths like `@docs/analysis/editor-architecture-candidates.md`, named frameworks), with minor gaps where directives stay abstract.	4 / 5
Workflow Clarity	A clear 17-step Intake sequence, per-lane numbered Execution Paths, an explicit proportional Verification section, and a Success Criteria checklist provide strong sequencing with most checkpoints present; explicit validate->fix->retry feedback loops are less crisp than the top anchor.	4 / 5
Progressive Disclosure	Section headers are well organized and external skill references are clearly signaled, but the skill is a monolithic ~340-line single file with no bundle files; the helper catalog and per-lane Execution Paths are inlined detail that could be split into reference files.	3 / 5
	Total	14 / 20 Passed

Description

55%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 names a clear domain and three concrete work modes, but lacks an explicit "Use when..." trigger clause and the natural trigger terms (architecture, migration, benchmark, RFC) that users would actually say. Distinctiveness is moderate due to the broad "framework or library" framing.

Suggestions

Add an explicit "Use when..." clause naming concrete trigger situations (architecture/public API redesign, framework migration, benchmarking, RFC/proposal work, serious plan review).

Include natural trigger terms users would say (migration, architecture, benchmark, RFC, refactor, proposal) rather than only "framework or library tasks".

Sharpen distinctiveness by contrasting with ordinary work, e.g. "Use for heavyweight architectural decisions, not routine bug fixes or one-package features."

Dimension	Reasoning	Score
Specificity	"planning-first research, selective deep analysis, and rigorous handoff" lists several specific actions for "heavyweight framework or library tasks", with minor coverage gaps (actual task types like migration/RFC/benchmark are not enumerated here).	4 / 5
Completeness	The description gives a clear "what" but no explicit "Use when..." trigger clause; per the judging guideline, missing explicit trigger guidance caps completeness at 3.	3 / 5
Trigger Term Quality	"framework or library" provides some relevant natural keywords, but common variations users would actually say (architecture, migration, benchmark, RFC, refactor, proposal) are missing.	3 / 5
Distinctiveness Conflict Risk	"heavyweight framework or library tasks" is somewhat specific via the "heavyweight" qualifier, but "framework or library tasks" is broad enough to overlap with general development task skills.	3 / 5
	Total	13 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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
Path: .agents/skills/major-task/SKILL.md
Commit: bc7104f

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.