task

Work a task end-to-end with lean context gathering, implementation, and verification

Quality

41%

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/task/SKILL.md

Quality

Content

56%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 a thorough, actionable workflow with strong sequencing and concrete commands, but it is noticeably verbose with repeated gate restatements and inlines content that would benefit from separate reference files. Progressive disclosure is limited by the absence of any bundle files.

Suggestions

Trim the repeated restatements of the autoreview, docs-creator, and security-advisory gates so each gate appears once and other sections reference it, reducing token cost.

Extract the Security Advisory Hotfixes closeout checklist and the Task-Style PR Body format into reference files under references/ and link to them one level deep.

Consolidate the Intake goal-pack matrix and the Skill Diet pack list into a single table to remove duplicated pack descriptions.

Dimension	Reasoning	Score
Conciseness	At ~480 lines the body is noticeably verbose for an instruction skill, with repeated restatements of the same gates (e.g. autoreview, docs-creator, security-advisory) across Intake, Skill Diet, Review Gates, Execution Path, Verification, and Success Criteria, which is padding beyond what Claude needs.	2 / 5
Actionability	It gives mostly executable guidance — concrete commands like `gh issue view`, `gh api advisories/<GHSA_ID>`, and the full `create-goal-scratchpad.mjs --template ... --with ...` invocation — with only minor gaps where direction stays abstract.	4 / 5
Workflow Clarity	Multi-step processes (Intake classification, Public Issue Challenge Gate repro ladder, Security Advisory closeout, Execution Path per task type) are clearly sequenced with explicit validation/checkpoint language ('hard stop', 'closeout gate', 'verify before final'), with only minor validation gaps.	4 / 5
Progressive Disclosure	No bundle files exist in references/, scripts/, or assets/ and all content is inlined into a single ~480-line SKILL.md; sections are well-headed but content that could be split out (security advisory closeout, PR body format, goal-pack matrix) is inline, matching the 'structure present but should be separate is inline' anchor.	3 / 5
	Total	13 / 20 Passed

Description

27%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 is a high-level, abstract statement of intent that answers 'what' only vaguely and omits any 'when to use' trigger guidance. It risks conflicting with many other general-purpose skills.

Suggestions

Replace the abstract phrasing with concrete actions the skill performs (e.g., 'Classifies tracker items, challenges public issue claims, runs autoreview gates, and ships task-style PRs').

Add an explicit 'Use when...' clause naming the natural triggers (e.g., 'Use when given a task description, issue id/link, or PR URL to work end-to-end').

Narrow the scope to distinguish it from sibling skills like major-task, e.g. reference 'ordinary non-heavyweight tasks' to reduce conflict risk.

Dimension	Reasoning	Score
Specificity	The description 'Work a task end-to-end with lean context gathering, implementation, and verification' names only the broadest phases (context gathering, implementation, verification) with no concrete actions or domain — comparable to 'Processes PDF files' which names a domain but with minimal action, yet here even the domain is absent.	2 / 5
Completeness	It states a vague 'what' (work a task end-to-end) but provides no 'when' or 'Use when...' clause, so per the rubric a missing explicit trigger guidance caps completeness at 3 and the vague what pulls it down to 2.	2 / 5
Trigger Term Quality	Phrases like 'Work a task end-to-end' and 'lean context gathering' are generic workflow jargon rather than natural terms a user would say when they need this skill; it lacks the common phrasings users actually invoke.	2 / 5
Distinctiveness Conflict Risk	'Work a task end-to-end' is extremely broad and overlaps with virtually any general-purpose work skill, creating high conflict risk similar to 'Helps with document files'.	2 / 5
	Total	8 / 20 Passed

Validation

75%

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 — 12 / 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
relative_links	Relative link issues: 1 suspicious	Warning

	Total	12 / 16 Passed

Repository: udecode/plate
Path: .agents/skills/task/SKILL.md
Commit: d76efae

Reviewed: 3 days 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.