skill-task-management

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

Quality

59%

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

56%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 actionable, well-sequenced workflows for every user intent it targets, supported by concrete tool calls and state-verification steps. Its weaknesses are length and structure: material is duplicated across sections, legacy-migration content consumes a large share of the file, and everything lives inline in one monolithic SKILL.md instead of being split into reference files. Cutting duplication and offloading the migration guide would lift both conciseness and progressive disclosure.

Suggestions

Remove the duplicated checkpoint example (lines ~137-162 vs ~489-523) and the redundant 'Example: Full Workflow' section, which repeats prior content almost verbatim.

Move the TodoWrite migration guide and backward-compatibility instructions into a separate references/migration.md and reference it one level deep, keeping SKILL.md as an overview.

Fix the tool-call presentation: show TaskList/TaskGet as tool invocations rather than synchronous JavaScript (const tasks = TaskList()), and clarify how to obtain real task IDs for addBlockedBy.

Dimension	Reasoning	Score
Conciseness	The 660-line body is noticeably verbose: a full checkpoint TaskCreate example appears twice nearly verbatim, the 'Example: Full Workflow' repeats earlier material, and sections like 'Benefits' checklists, 'The Bottom Line', and the TodoWrite migration/backward-compatibility guide pad the file with content Claude does not need. This matches 'noticeably verbose; several unnecessary explanations or padded sections' — not 1, since it does not explain basic concepts Claude already knows.	2 / 5
Actionability	Concrete guidance throughout: real TaskCreate/TaskUpdate/TaskList invocations with all parameters, bash commands for state assessment, good/poor task contrasts, and dependency examples. Minor gaps keep it below 5: TaskList() is presented as synchronous JavaScript returning a value (it is a tool call), and addBlockedBy: ["1"] assumes task IDs not yet known, so the code is adaptable rather than copy-paste ready.	4 / 5
Workflow Clarity	Each capability is sequenced as explicit Step 1–4 with state assessment (git status, TaskList) before acting, plus red-flags and quick-reference tables. It lacks the explicit validation feedback loops of a 5, but the operations are not destructive or batch operations requiring validation, so no cap applies — 'clear sequence with most checkpoints present; minor validation gaps'.	4 / 5
Progressive Disclosure	Section headers and a quick-reference table give it real structure, but the ~660-line monolith inlines content that clearly belongs in separate files (TodoWrite migration guide, integration patterns, extended examples), and the only referenced script (${HOME}/.claude-octopus/plugin/scripts/migrate-todos.sh) is external to the bundle — no references/ or scripts/ files exist. Fits 'some structure but could be better organized; content that should be separate is inline' rather than 2, since navigation via headers is possible.	3 / 5
	Total	13 / 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.

A serviceable description that states the domain and several capabilities with an explicit use clause, but the trigger coverage is thin — the natural phrases the skill is built around (save progress, resume, checkpoint) never appear, and the when-clause restates the what rather than describing when to invoke it. It would be stronger with concrete trigger situations mirroring the frontmatter's trigger field.

Suggestions

Fold the natural trigger phrases from the trigger field into the description (e.g., 'Use when the user says "add to the todo's", "save progress", or "pick up where we left off"').

Mention the checkpoint/resume capability explicitly — it is the skill's most distinctive function but is absent from the description.

Replace the generic verbs ("delegate work", "monitor progress") with more concrete actions like "create, update, and checkpoint tasks".

Dimension	Reasoning	Score
Specificity	The description names the domain ("Manage tasks with Claude Code native tools") and three actions ("track TODOs, delegate work, and monitor progress"), but the actions are generic verbs and omit core capabilities the body emphasizes (checkpointing, resuming sessions). It matches the anchor 'names domain and 1-2 concrete actions, but not comprehensive' — several actions are listed but none are concretely specified, and coverage has gaps, so it sits at the boundary rather than clearly at 4.	3 / 5
Completeness	It answers what ("Manage tasks with Claude Code native tools — track TODOs, delegate work, and monitor progress") and includes an explicit use clause ("use to…"), but the when merely restates the capabilities without describing user situations or trigger phrases. This fits 'has both what and when; when could be more explicit or specific', not 5 which requires concrete trigger phrases, and not 3 since a use clause is explicitly present.	4 / 5
Trigger Term Quality	"tasks", "TODOs", and "progress" are relevant keywords a user might say, but common natural variations the skill itself targets ("add to the todo's", "save progress", "resume tasks", "checkpoint") are absent from the description. This matches 'some relevant keywords but missing common variations or synonyms' rather than 4's 'good keyword coverage'.	3 / 5
Distinctiveness Conflict Risk	"with Claude Code native tools" distinguishes it from generic task/todo skills, and the todo-tracking framing is fairly specific, but it could still overlap with any progress-tracking or delegation skill. Fits 'mostly distinct; minor overlap risk with closely related skills' rather than 5's clear niche with minimal conflict.	4 / 5
	Total	14 / 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: 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.