task-management

Manage Joel's task system in Todoist. Triggers on: 'add a task', 'create a todo', 'what's on my list', 'today's tasks', 'what do I need to do', 'remind me to', 'inbox', 'complete', 'mark done', 'weekly review', 'groom tasks', 'what's next', or when actionable items emerge from other work. Also triggers when Joel mentions something he needs to do in passing — capture it.

Quality

88%

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

Quality

Content

82%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 is highly actionable with comprehensive, executable Todoist CLI guidance and clearly sequenced workflows guarded by anti-patterns and a "do it instead of tasking it" gate. The main weaknesses are mild over-explanation in the Philosophy section and the absence of an explicit confirm-before-delete validation step in the inbox triage flow.

Suggestions

Add an explicit validation/confirmation checkpoint before destructive inbox-triage actions (e.g., 'Confirm the delete/move/complete batch with Joel before executing') to satisfy the batch/destructive validation requirement.

Tighten the Philosophy section by trimming the generic GTD/Shape Up/Tiny Habits summaries down to the practitioner rules that shape agent behavior, since Claude already knows these frameworks.

Consider moving the full CLI command reference and Pro filter syntax into a separate REFERENCE.md with a one-line pointer, leaving SKILL.md as a leaner overview.

Dimension	Reasoning	Score
Conciseness	The body is dense and largely assumes Claude's competence (CLI command tables, priority/schedule mappings), but the Philosophy section summarizes GTD/Shape Up/Tiny Habits — frameworks Claude already knows — and the Credits section adds length that could be trimmed; mostly efficient with minor over-explanation.	4 / 5
Actionability	It provides fully executable, copy-paste-ready `todoist-cli` commands covering read, write, filters, and project/section creation, plus concrete good/bad task examples and a priority-convention table mapping UI to API values.	5 / 5
Workflow Clarity	Multi-step processes (Process Inbox, Weekly Review, Create Tasks From Work, ADR→Tasks) are clearly numbered with commands, and batch triage is presented "as a batch decision" with a "could the agent just do this?" gate; however, destructive steps (delete/complete) lack an explicit confirm-before-execute validation checkpoint, leaving a minor validation gap.	4 / 5
Progressive Disclosure	The skill is a single well-organized file with clear section headers (Philosophy, Todoist Adapter, Agent Behaviors, SOP, Anti-Patterns) and no nested references; the full CLI reference and filter syntax are inline, which is reasonable for a hands-on CLI skill but represents content that could optionally be split into a reference file.	4 / 5
	Total	17 / 20 Passed

Description

95%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 strong: it answers both what and when with an extensive, natural-language trigger list and a clear Todoist niche. The only minor gap is that capabilities are implied via triggers rather than enumerated as a clean action list.

Dimension	Reasoning	Score
Specificity	"Manage Joel's task system in Todoist" names the domain and tool, and trigger phrases surface concrete actions (add, complete, mark done, weekly review, groom), but the capabilities are scattered across trigger wording rather than enumerated as a clean action list, and core verbs like delete/schedule/move are absent from the description.	4 / 5
Completeness	It explicitly states what the skill does ("Manage Joel's task system in Todoist") and provides explicit trigger guidance ("Triggers on: ...") with concrete trigger phrases, satisfying the 'Use when...' requirement that would otherwise cap completeness at 3.	5 / 5
Trigger Term Quality	The description lists comprehensive natural phrases a user would actually say — "add a task", "create a todo", "what's on my list", "today's tasks", "what do I need to do", "remind me to", "weekly review", "what's next" — including synonyms (task/todo, several "what's on/next" variants) plus the implicit-capture case.	5 / 5
Distinctiveness Conflict Risk	"Joel's task system in Todoist" carves a clear niche with Todoist-specific, task-management-only triggers; words like "inbox" and "complete" are generic in isolation but unambiguous in this Todoist framing, giving minimal conflict risk.	5 / 5
	Total	19 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: joelhooks/joelclaw
Path: skills/task-management/SKILL.md
Commit: 7094ced

Reviewed: 3 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.