skill-task-management

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

Quality

51%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/skill-task-management-v2/SKILL.md

Quality

Content

50%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 content is highly actionable with concrete native-Task tool calls and clear step sequences, but it is padded with redundant restatements and inlines material that should be split into reference files. The batch git-checkpoint flow also lacks validation, capping workflow clarity.

Suggestions

Add a validation step to the checkpoint flow before `git commit` (e.g., verify `git status` reflects intended changes, confirm branch) and a re-validate/retry loop.

Collapse the recurring checkpoint template and remove redundant sections (Common Patterns, Red Flags table, Quick Reference, Bottom Line) that restate earlier guidance.

Move the Migration-from-TodoWrite section, verbose Best Practices examples, and the full-workflow example into separate reference files and link to them one level deep.

Dimension	Reasoning	Score
Conciseness	The ~660-line body is noticeably padded: the checkpoint template recurs ~4 times, and 'Common Patterns', 'Red Flags', 'Quick Reference', 'Bottom Line', and verbose Good/Poor task examples restate earlier content and basic task-tracking knowledge.	2 / 5
Actionability	Concrete, mostly copy-paste-ready TaskCreate/TaskUpdate/TaskList calls and git commands cover the common cases, with only minor gaps from interpolated placeholders like `${branchName}` and `taskId: '[task-id]''.	4 / 5
Workflow Clarity	Each capability is numbered into clear steps with a status workflow diagram, but the checkpoint flow runs batch `git add . && git commit` with no validation/verification step, so the destructive/batch cap of 3 applies.	3 / 5
Progressive Disclosure	It is a single monolithic file with no bundle references; sections are well-organized but large chunks (Migration, Best Practices examples, full-workflow example) that belong in separate reference files are inlined.	3 / 5
	Total	12 / 20 Passed

Description

53%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 conveys what the skill does and is largely distinct, but it lacks an explicit 'Use when...' trigger clause and leans on capability language ('delegate work', 'monitor progress') rather than natural user phrases. It sits at the middle of the rubric across most dimensions.

Suggestions

Add an explicit 'Use when...' clause with concrete user phrases (e.g., 'Use when the user wants to save progress, resume tasks, or checkpoint work').

Swap capability-language ('delegate work', 'monitor progress') for natural trigger terms users actually say ('save progress', 'resume tasks', 'pick up where we left off', 'checkpoint this').

Tighten the action list toward concrete mechanics (e.g., 'create checkpoints with WIP commits, resume from saved task state') rather than abstract verbs.

Dimension	Reasoning	Score
Specificity	The description lists several actions ('track TODOs, delegate work, and monitor progress') but they remain high-level abstractions rather than concrete mechanics, matching the '1-2 concrete actions, not comprehensive' anchor.	3 / 5
Completeness	There is a clear 'what' ('Manage tasks with Claude Code native tools') but only a weakly implied 'when' ('use to...') with no explicit 'Use when...' trigger clause, which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	'TODOs' is a natural user term, but 'delegate work' and 'monitor progress' are capability-language rather than phrases users utter, and natural triggers from the body ('save progress', 'resume tasks', 'checkpoint') are absent.	3 / 5
Distinctiveness Conflict Risk	Task management with a delegation/orchestration angle is a reasonably distinct niche with only minor overlap risk against generic todo tooling.	4 / 5
	Total	13 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (685 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: nyldn/claude-octopus
Path: .claude/skills/skill-task-management-v2/SKILL.md
Commit: bc76e7c

Reviewed: ~16 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.