skill-task-management

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

Quality

76%

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

77%Weight 40%Scale 1-3

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 with clearly sequenced workflows and status checkpoints, but it is over-long and repetitive — especially the recurring checkpoint template — and makes no use of progressive disclosure despite content that would benefit from being split into reference files.

Suggestions

De-duplicate the checkpoint TaskCreate template (it appears nearly verbatim in section 2, Best Practices, and the Full Workflow Example); keep one canonical example and reference it.

Move the migration guide, integration patterns, and full worked example into separate reference files under ./references/ and link to them from the main body to improve progressive disclosure.

Trim the Benefits list and restated capability summaries; native Task-tool behavior is already known to Claude and need not be enumerated.

Dimension	Reasoning	Score
Conciseness	The body is concrete and does not lecture on concepts Claude already knows, but at ~660 lines it is padded with redundancy — the checkpoint template recurs nearly verbatim in sections 2, Best Practices, and the Full Workflow Example — so it could be tightened significantly; not level 3 due to this repetition, not level 1 because it avoids explaining known concepts.	2 / 3
Actionability	It provides copy-paste-ready, executable TaskCreate/TaskUpdate calls with real parameters plus concrete git commands, matching the level-3 anchor for fully executable, specific examples.	3 / 3
Workflow Clarity	Each capability is laid out as numbered Step 1–4 sequences with status checks (git status, TaskList) before acting and supporting checklists (Red Flags, Best Practices); task management is not a destructive/batch operation requiring error-recovery loops, so the clear sequencing and checkpoints meet level 3.	3 / 3
Progressive Disclosure	There are no bundle files at all and the entire ~660-line skill is inline with well-organized sections, but content that could be split (the migration guide, integration patterns, full worked example) lives in the main file; it is structured rather than a disorganized wall (not level 1) but lacks any one-level-deep references (not level 3).	2 / 3
	Total	10 / 12 Passed

Description

75%Weight 40%Scale 1-3

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 uses natural trigger terms, but it answers "what" far more clearly than "when", lacking an explicit Use-when trigger clause, and its "delegate work" / "monitor progress" phrasing risks overlap with adjacent skills.

Suggestions

Add an explicit 'Use when ...' trigger clause naming scenarios (e.g., 'Use when the user wants to add items to a todo list, checkpoint progress, or resume saved work') to raise completeness.

Tighten the conflict-prone terms: replace or qualify 'delegate work' so it reads as task-tracking rather than subagent delegation.

Consider including a brief 'Do not use for ...' cue in the description to sharpen distinctiveness from git/PR skills.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "track TODOs, delegate work, and monitor progress" — matching the level-3 anchor of several specific concrete actions rather than a single domain/action at level 2.	3 / 3
Completeness	It clearly states WHAT ("Manage tasks ... track TODOs, delegate work, and monitor progress") but the WHEN is only capability phrasing ("use to ...") with no explicit "Use when ..." trigger guidance, which the rubric caps at 2; it is not level 3 because no explicit trigger scenarios are given.	2 / 3
Trigger Term Quality	Natural terms a user would say are well covered ("tasks", "TODOs", "track", "delegate work", "monitor progress"), matching the level-3 anchor for good coverage of natural user phrasing.	3 / 3
Distinctiveness Conflict Risk	"Manage tasks with Claude Code native tools" carves a niche, but "delegate work" and "monitor progress" overlap with subagent-delegation and general progress skills, so it could still conflict; it is not level 3 because the triggers are not uniquely distinctive.	2 / 3
	Total	10 / 12 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 (684 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: 9f39f0c

Reviewed: 6 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.