major-task

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

Quality

63%

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

77%

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

The body is highly actionable with concrete commands, well-sequenced workflows, and explicit validation/checklist sections. Its main weaknesses are length with some cross-section redundancy and a monolithic structure that does not progressively disclose detail into reference files.

Suggestions

De-duplicate the branch/setup and tracker sync-back rules that recur across Intake, Tracked Task Rules, and Code-Changing Major Work.

Move the long 'Load Skills Only When Justified' catalog and per-lane execution paths into a one-level-deep reference file signaled from the overview.

Tighten the Intake list by merging near-duplicate classification steps.

Dimension	Reasoning	Score
Conciseness	The body is directive and assumes Claude's competence without explaining known concepts, but at ~340 lines it repeats branch/setup and sync-back rules across Intake, Tracked Task Rules, and Code-Changing Major Work, so it could be tightened.	2 / 3
Actionability	Provides executable commands (e.g. `node .agents/skills/autogoal/scripts/create-goal-scratchpad.mjs --template major-task`, `gh issue view`) and specific per-condition helper loading, giving copy-paste-ready guidance.	3 / 3
Workflow Clarity	Intake is a numbered 17-step sequence, execution paths are per-lane numbered workflows, and the Verification and Success Criteria sections provide explicit checkpoints and a checklist.	3 / 3
Progressive Disclosure	Sections are well-organized, but the skill is a single monolithic SKILL.md with no bundle files; the long helper catalog and execution paths are inline content that could be split into one-level-deep references.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 is third-person and names a domain plus a few abstract actions, but it lacks explicit trigger guidance and concrete action verbs. It reads as a capability summary rather than a discoverable trigger.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers (architecture redesign, framework migration, benchmarking, RFC/proposal work).

Replace abstract verbs ('planning-first research', 'rigorous handoff') with concrete actions the skill performs.

Tighten distinctiveness by leading with the heavyweight/major-work qualifier so it does not compete with ordinary task skills.

Dimension	Reasoning	Score
Specificity	Names the domain ("heavyweight framework or library tasks") and some actions ("planning-first research, selective deep analysis, and rigorous handoff"), but the actions are abstract rather than concrete like 'extract text, fill forms'.	2 / 3
Completeness	The 'what' is present but the 'when' is only implied (heavyweight tasks); there is no explicit 'Use when...' clause, which caps completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	"framework or library tasks" supplies relevant keywords, but common variations users would say (migration, architecture, benchmark, RFC, refactor) are absent from the description.	2 / 3
Distinctiveness Conflict Risk	"heavyweight" scopes a niche of major/complex tasks, but 'framework or library tasks' is broad enough to overlap with general task or research skills.	2 / 3
	Total	8 / 12 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: 45116fd

Reviewed: about 13 hours 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.