skill-task-management

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

Quality

52%

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 ./skills/skill-task-management/SKILL.md

Quality

Content

42%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 body delivers genuinely useful, well-sequenced guidance for adding, checkpointing, resuming, and advancing tasks with native tools, supported by good/bad task examples and a quick-reference table. However, it is roughly twice as long as needed, contains duplicated and marketing-style content, and relies on references to files and scripts that are not part of the bundle.

Suggestions

Cut the "Benefits", "The Bottom Line", and "Example: Full Workflow" sections and consolidate the duplicated checkpoint templates — the core guidance could fit in roughly half the length.

Remove or fix dangling references ("skills/blocks/codex-host-adapter.md", "${HOME}/.claude-octopus/plugin/scripts/migrate-todos.sh") and move the legacy v7.22 migration material into a separate optional reference file.

Add validation to the checkpoint workflow (e.g. verify the WIP commit landed and confirm task status changes via TaskList before reporting success) and correct the garbled config example in the "Backward Compatibility" section that mixes YAML with prose text.

Dimension	Reasoning	Score
Conciseness	The ~660-line body has several padded sections: a marketing-style "Benefits" ✅ list, "The Bottom Line", a redundant "Example: Full Workflow" that re-demonstrates content already shown, a near-duplicate checkpoint template, and a migration section for a legacy v7.22 tool most users will not have. This matches the level-2 anchor (several unnecessary explanations or padded sections) rather than level 3's mostly-efficient profile.	2 / 5
Actionability	Concrete TaskCreate/TaskUpdate/TaskList call shapes and git commands are provided, but the code uses placeholders ("[task-id]", "[Brief task description]") rather than executable examples, and it references files and scripts that do not exist in this bundle ("skills/blocks/codex-host-adapter.md", "${HOME}/.claude-octopus/plugin/scripts/migrate-todos.sh"). Concrete guidance exists but is incomplete, matching level 3 rather than level 4's minor-gaps profile.	3 / 5
Workflow Clarity	Each capability is clearly sequenced with numbered steps (assess state → checkpoint → update tasks → resume instructions), which is above level 2. However, the checkpoint workflow's "git add ." plus commit is a batch operation that stages everything with no post-commit validation and no error-recovery loop, so the rubric's cap on batch operations without validation holds it at level 3.	3 / 5
Progressive Disclosure	Section headers are clear and consistent, but everything is inlined in one long file — the migration guide, integration examples, and full-workflow example clearly belong in separate reference files — and the single reference cited ("skills/blocks/codex-host-adapter.md") does not exist in the bundle. Some structure with content that should be separate inline matches the level-3 anchor.	3 / 5
	Total	11 / 20 Passed

Description

62%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 is serviceable: it names the domain, includes a use-to clause, and has one strong natural trigger term ("TODOs"). Its weaknesses are generic action verbs, an unsubstantiated "delegate work" claim, and omission of the skill's own most distinctive triggers (checkpoint, save progress, resume).

Suggestions

Rewrite to name the concrete capabilities the body actually delivers, e.g. "Add items to the todo list, checkpoint progress, and resume saved work using Claude Code's native task tools".

Include the body's natural trigger phrases users actually say: "add to my todos", "save progress", "checkpoint this", "resume tasks".

Remove the "delegate work" claim or add matching guidance in the body, since the body contains no delegation workflow.

Dimension	Reasoning	Score
Specificity	The description lists three actions ("track TODOs, delegate work, and monitor progress"), but they are generic verbs rather than concrete capabilities, and "delegate work" is an over-claim not substantiated by the skill body. It names the domain with several actions but is not comprehensive, matching the level-3 anchor better than level 4's specific action list.	3 / 5
Completeness	Both "what" ("Manage tasks with Claude Code native tools") and "when" ("use to track TODOs, delegate work, and monitor progress") are present, but the when-clause is a merged purpose statement rather than explicit trigger conditions like "Use when the user says...". It is above level 3 (which has no when) but below level 5's concrete trigger phrases.	4 / 5
Trigger Term Quality	"TODOs", "tasks", and "track" are natural terms users would say, but the description omits the skill's core trigger phrases from its own body — "save progress", "checkpoint", "resume", "pick up where we left off". Some relevant keywords are present while common variations are missing, which is the level-3 anchor.	3 / 5
Distinctiveness Conflict Risk	Task/todo management with native-tool framing is a distinct niche with low conflict risk, though "delegate work" and "monitor progress" are broad phrases that could overlap with other orchestration or delegation skills. Mostly distinct with minor overlap risk, matching the level-4 anchor.	4 / 5
	Total	14 / 20 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 (660 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: nyldn/claude-octopus
Path: skills/skill-task-management/SKILL.md
Commit: 0093dab

Reviewed: 5 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.