task-management

Task management CLI for tracking and managing feature subtasks with status, dependencies, and validation

Quality

57%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.opencode/skills/task-management/SKILL.md

Quality

Content

65%

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

The content is highly actionable with executable commands and complete schemas, but it is overly verbose due to heavy command repetition across sections, keeps reference-grade detail inline instead of splitting it into separate files, and does not embed validation checkpoints directly inside the multi-step workflows. Tightening duplication and externalizing detailed schemas would meaningfully improve it.

Suggestions

Consolidate the repeated status/next/blocked/validate commands: keep them once in the Command Reference and Examples, and remove the duplicative Common Workflows and Tips restatements.

Move the full task.json/subtask JSON schemas and the detailed validation-rule checklists into a separate reference file (e.g., references/TASK-SCHEMA.md) and link to it from the body.

Add explicit inline validation checkpoints to the Completing Tasks and Starting a New Feature workflows (e.g., run `validate` after `complete` and before delegating the next task).

Dimension	Reasoning	Score
Conciseness	The body is mostly accurate and useful with concrete commands, but ~385 lines repeat the same status/next/blocked/validate commands across Quick Start, Examples, Common Workflows, and Tips sections, which could be tightened considerably; it avoids re-explaining basic concepts but still pads with duplication.	2 / 3
Actionability	Provides concrete, copy-paste-ready bash commands with realistic sample output, a full command reference table, and complete JSON schemas for task.json and subtask files, giving fully executable guidance.	3 / 3
Workflow Clarity	Workflows (Starting a New Feature, Completing Tasks) are clearly sequenced and a validate command with troubleshooting exists, but the inline workflows do not embed explicit validation checkpoints after state-changing steps, so per the rubric guideline workflow clarity is capped at 2.	2 / 3
Progressive Disclosure	Sections are well-organized and the body correctly points to the real scripts/task-cli.ts bundle file, but the SKILL.md is monolithic (~385 lines) with JSON schemas, full validation rule lists, and all examples inline, and no separate reference files exist, so content that should be split out is not.	2 / 3
	Total	9 / 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 uses correct third-person voice and conveys what the skill does with a few concrete facets, but it omits any explicit 'Use when...' trigger guidance and leans on generic verbs like 'tracking and managing'. Adding trigger terms and sharper, more numerous concrete actions would raise specificity, completeness, and distinctiveness.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers (e.g., 'Use when tracking feature subtasks, checking task status, resolving task dependencies, or validating a task breakdown').

Replace generic verbs with several concrete actions (e.g., 'show task status, find next eligible tasks, identify blocked tasks, mark subtasks complete, validate dependency trees').

Include common term variations users would say (e.g., 'task tracking', 'what should I work on next', 'blocked tasks', 'dependency graph') to improve trigger coverage and distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain ('Task management CLI') and several concrete facets ('status, dependencies, and validation'), but the verbs 'tracking and managing' are generic rather than enumerating multiple specific actions like the score-3 anchor.	2 / 3
Completeness	Clearly states what the skill does, but provides no 'Use when...' clause or equivalent explicit trigger guidance, so per the rubric guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	Includes some natural terms a user might say ('task management', 'subtasks', 'dependencies', 'status'), but lacks common variations and a trigger phrase; coverage is partial rather than comprehensive.	2 / 3
Distinctiveness Conflict Risk	'Task management CLI for tracking...feature subtasks' is somewhat specific but 'task management' is generic enough to overlap with other task-tracking or planning skills, so it is not a clearly unconflicting niche.	2 / 3
	Total	8 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: darrenhinde/OpenAgentsControl
Path: .opencode/skills/task-management/SKILL.md
Commit: 37ca233

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.