task

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

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/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 a highly actionable, well-sequenced workflow with strong validation feedback loops and concrete commands throughout. Its main weaknesses are length/redundancy (gates restated across sections) and a monolithic structure with no reference files, despite sections large enough to warrant progressive disclosure.

Suggestions

Deduplicate the autoreview, docs-creator, and security-advisory gate descriptions that recur across Intake, Review And Risk Gates, and Verification — state each gate once and reference it.

Move the long 'Security Advisory Hotfixes' and 'Task-Style PR Body' procedures into reference files (e.g. references/security-advisory.md, references/pr-body.md) and link to them from the body to improve progressive disclosure.

Tighten the 'Skill Diet' list and repeated skill-loading guidance, which overlap with the Intake classification steps, to reduce token cost.

Dimension	Reasoning	Score
Conciseness	The body is dense and rule-driven with no basic-concept fluff, but at ~480 lines it repeats the same gates (autoreview, docs-creator, security-advisory) across Intake, Review And Risk Gates, and Verification, so it could be tightened; matches anchor 2 rather than the 'every token earns its place' bar of anchor 3.	2 / 3
Actionability	Pervasive concrete executable commands ('gh issue view', 'gh api repos/<owner>/<repo>/security-advisories/<GHSA_ID>', 'npx skills remove <skill> -y', 'pnpm run reinstall', 'npm view <package>@<version>', 'gh pr view --json body') plus an exact emoji/table PR-body format make it copy-paste ready, matching anchor 3.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced (numbered Intake 1-14, per-type Execution Paths) with explicit validation checkpoints and feedback loops (reinstall-then-rerun on local-corruption signals, autoreview retried until no accepted findings) plus a Success Criteria checklist, matching anchor 3.	3 / 3
Progressive Disclosure	No bundle files exist and the skill is a well-sectioned but monolithic ~480-line document; large blocks like 'Security Advisory Hotfixes' and 'Task-Style PR Body' could be split into reference files, so it matches anchor 2 rather than a cleanly split overview with 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 states what the skill does in compact third-person voice but is generic: it names high-level workflow phases without concrete actions and omits any 'Use when...' trigger guidance, capping completeness at 2. Trigger terms are weak and it risks overlapping with sibling task-style skills.

Suggestions

Add an explicit 'Use when...' clause listing natural trigger phrases users would say (e.g. 'Use when fixing a bug, implementing a feature, or working a GitHub/Linear issue end-to-end').

Replace abstract phases with concrete actions a user would recognize (e.g. 'reproduce, fix at the ownership boundary, verify, and ship a PR') to lift specificity.

Add distinctive trigger terms (issue links, PRs, bug reports, tracker items) so it does not collide with the sibling 'major-task' skill.

Dimension	Reasoning	Score
Specificity	Names the domain ('task') and three action phases ('lean context gathering, implementation, and verification'), but these are generic abstract stages rather than concrete specific actions, matching anchor 2 and falling short of anchor 3's multiple concrete actions.	2 / 3
Completeness	It answers 'what' ('Work a task end-to-end...') but has no 'Use when...' clause or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 2; anchor 3 requires explicit when-triggers.	2 / 3
Trigger Term Quality	Contains some relevant generic keywords ('task', 'implementation', 'verification') but no natural trigger phrasing a user would actually say (e.g. 'fix this bug', 'work on this issue') and no common variations, matching anchor 2.	2 / 3
Distinctiveness Conflict Risk	Describes a somewhat specific end-to-end lean workflow, but the generic 'task' term and a sibling 'major-task' skill create real overlap, matching anchor 2 rather than a clearly distinct niche.	2 / 3
	Total	8 / 12 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: 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.