skill-task-management

Manage tasks with Claude Code native tools — use to track TODOs, delegate work, and monitor progress

Quality

66%

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 ./.claude/skills/skill-task-management-v2/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 concrete tool calls and well-sequenced workflows, but it is verbose (heavy repetition of the same patterns) and monolithic with no progressive disclosure into reference files. Validation gaps around the git commit step also limit workflow clarity.

Suggestions

Collapse the repeated checkpoint/task-creation examples into a single canonical example and remove the redundant summary tables ('Red Flags', 'Quick Reference', 'The Bottom Line') that restate earlier sections.

Add a validation checkpoint after the batch git commit (e.g. verify 'git log -1' shows the WIP commit and 'git status' is clean) before declaring progress saved.

Move the migration guide and the full-workflow example into separate reference files (e.g. references/migration.md, references/full-workflow.md) and link to them one level deep from the overview.

Dimension	Reasoning	Score
Conciseness	The body is actionable but padded: the checkpoint/task-creation pattern is demonstrated three to four times across sections, and summary tables ('Red Flags', 'Quick Reference', 'The Bottom Line') restate earlier content, so it could be tightened considerably.	2 / 3
Actionability	Concrete, copy-paste-ready tool calls (TaskCreate/TaskUpdate with specific parameters) and exact git commands appear throughout, including a good-vs-poor task comparison, meeting the fully-executable bar.	3 / 3
Workflow Clarity	Multi-step flows are clearly numbered with state-assessment gates and user-confirmation prompts, but the batch 'git add .' + commit step never validates success or reviews what is staged, so validation gaps cap this at 2.	2 / 3
Progressive Disclosure	No bundle files exist and the 650-line SKILL.md is monolithic; the migration guide, full-workflow example, and best-practice patterns are inline content that would be better split into one-level-deep reference files.	2 / 3
	Total	9 / 12 Passed

Description

67%

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 specific and distinct, naming three concrete actions within a clear task-management niche. It is held back by an absent explicit 'Use when...' trigger clause and incomplete coverage of the skill's actual trigger terms.

Suggestions

Add an explicit 'Use when...' trigger clause naming the body's real triggers, e.g. 'Use when the user wants to track TODOs, save/checkpoint progress, or resume work across sessions'.

Expand trigger terms to include 'checkpoint', 'save progress', and 'resume' so the description surfaces the situations that actually invoke the skill.

Consider dropping the tooling framing ('with Claude Code native tools') from the one-line description to free space for trigger guidance while keeping the niche clear.

Dimension	Reasoning	Score
Specificity	The phrase 'track TODOs, delegate work, and monitor progress' lists multiple concrete actions, matching the anchor for enumerating specific capabilities rather than vague language.	3 / 3
Completeness	The 'what' is clear ('Manage tasks with Claude Code native tools'), but 'use to track TODOs...' states a capability, not an explicit 'Use when...' trigger condition, so the 'when' is only implied and capped at 2.	2 / 3
Trigger Term Quality	It surfaces natural terms like 'tasks' and 'TODOs' but omits the body's primary trigger phrasings ('save progress', 'checkpoint', 'resume'), so coverage of common variations is incomplete.	2 / 3
Distinctiveness Conflict Risk	Scoping to 'Claude Code native tools' for task/TODO management carves a clear niche with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 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
skill_md_line_count	SKILL.md is long (659 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: nyldn/claude-octopus
Path: .claude/skills/skill-task-management-v2/SKILL.md
Commit: 9f39f0c

Reviewed: 2 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.