task

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

Quality

58%

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

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 body is highly actionable and workflow-clear with strong validation feedback loops, but it is monolithic and verbose due to repeated restatement of the same gates across sections. Splitting large reference blocks into bundle files would improve navigability.

Suggestions

Extract the Task-Style PR Body format spec and the Security Advisory Hotfixes procedure into separate reference files (e.g., references/pr-body.md, references/security-advisory.md) and link to them from the body to improve progressive disclosure.

De-duplicate the autoreview, docs-creator, PR-plan, and security-advisory-pack guidance that recurs across Intake, Review And Risk Gates, Verification, and Success Criteria into a single canonical statement.

Tighten the Skill Diet / Load Skills sections, which overlap in wording about when to load niche skills.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows and is dense with operational policy, but the same gates (autoreview, docs-creator, PR-plan, security-advisory pack) are restated across Intake, Review Gates, Verification, and Success Criteria, so it could be tightened.	3 / 5
Actionability	It provides concrete, copy-paste-ready commands with exact flags and arguments (e.g., 'gh api advisories/<GHSA_ID>', the autogoal create-goal-scratchpad invocation, 'npm view <package>@<version>', 'gh pr view --json body') covering the common task surfaces.	5 / 5
Workflow Clarity	Multi-step processes are explicitly sequenced (Intake 1-14, per-shape Execution Paths, Verification) with validation checkpoints and feedback loops such as reinstall-and-rerun on corruption, re-validate-until-clean, and autoreview-until-no-findings, plus a Success Criteria checklist.	5 / 5
Progressive Disclosure	Section headers are clear and well-organized, but the skill is a single monolithic ~500-line file with no bundle files, and large blocks (Task-Style PR Body format, Security Advisory Hotfixes procedure) that could live in separate reference files are inlined.	3 / 5
	Total	16 / 20 Passed

Description

38%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 states a clear high-level purpose but is generic and lacks explicit trigger guidance or natural keywords, making it prone to overlapping with other skills. It answers 'what' weakly and omits 'when' entirely.

Suggestions

Add an explicit 'Use when ...' trigger clause naming natural phrases users would say (e.g., 'Use when the user asks to implement, fix, or investigate an issue end-to-end').

Replace generic lifecycle terms with more concrete capability language (e.g., reference issue/PR handling, reproduction, and verification) to raise specificity.

Narrow the domain or add distinguishing trigger terms so it is less likely to fire for unrelated work skills.

Dimension	Reasoning	Score
Specificity	Lists three named activities ('lean context gathering, implementation, and verification') but they are generic lifecycle phases rather than domain-specific concrete actions, fitting 'names domain and 1-2 concrete actions, not comprehensive'.	3 / 5
Completeness	The 'what' is clear (work a task through gathering, implementation, verification) but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Only generic keywords like 'task' appear; phrases such as 'lean context gathering' are jargon and the natural phrases a user would actually say are missing.	2 / 5
Distinctiveness Conflict Risk	'Work a task end-to-end' is very broad and would overlap with virtually any work-oriented skill, matching 'very broad; high overlap risk with many similar skills'.	2 / 5
	Total	10 / 20 Passed

Validation

68%

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 — 11 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (511 lines); consider splitting into references/ and linking	Warning
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	11 / 16 Passed

Repository: udecode/plate
Path: .agents/skills/task/SKILL.md
Commit: 9ec2c8e

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.