routine-advisor

Suggests relevant cron routines based on user context, goals, and observed patterns

Quality

67%

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/routine-advisor/SKILL.md

Quality

Content

77%

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 concrete capabilities, schemas, and a clear creation workflow including a validation checkpoint. Conciseness and progressive disclosure are the weak points: the ideas catalog and delivery prose add length that could be offloaded to a reference file.

Suggestions

Move the "Routine Ideas by User Type" catalog into a referenced file (e.g. ROUTINE_IDEAS.md) and keep only a one-line pointer in SKILL.md.

Tighten the "Delivering Results" section to a concise rule plus the capability list, removing explanatory prose Claude can infer.

Consider trimming the per-user-type bullet lists to 2 representative examples each to reduce inline bulk.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence, but the delivery-routing explanation and the lengthy "Routine Ideas by User Type" list add tokens that could be tightened or moved out of the core flow.	2 / 3
Actionability	Provides concrete capability names, executable parameter schemas with JSON examples, and specific cron expressions—copy-paste ready guidance.	3 / 3
Workflow Clarity	The suggest → confirm → check trigger_list → create sequence is clearly ordered with an explicit duplicate-avoidance checkpoint before creation.	3 / 3
Progressive Disclosure	Well-sectioned single file with no broken references, but at ~80 lines the inline "Routine Ideas by User Type" catalog is content that could be split into a separate reference file rather than kept in the overview.	2 / 3
	Total	10 / 12 Passed

Description

57%

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 identifies a clear, specific niche but only names a single action and omits an explicit "Use when..." trigger clause, capping completeness. Adding concrete trigger phrasing would lift the trigger-term and completeness scores.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user mentions recurring tasks, daily/weekly habits, reminders, or wanting to automate a repeatable check."

List more concrete actions or outputs (e.g. "creates scheduled routines, picks a delivery channel, avoids duplicate triggers") to raise specificity.

Include natural user phrasings ("remind me", "every morning", "automate") in the description for better trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names a concrete action ("Suggests relevant cron routines") and inputs ("user context, goals, and observed patterns") but lists only one action rather than multiple specific concrete actions.	2 / 3
Completeness	It states what the skill does but lacks an explicit "Use when..." trigger clause; the "when" is only implied by "based on user context, goals, and observed patterns".	2 / 3
Trigger Term Quality	"cron routines" is a relevant natural term but the description alone offers limited coverage of common user phrasings like "remind me", "every morning", or "automate".	2 / 3
Distinctiveness Conflict Risk	The cron-routine suggestion niche is distinct and unlikely to trigger for the wrong skill.	3 / 3
	Total	9 / 12 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: nearai/ironclaw
Path: skills/routine-advisor/SKILL.md
Commit: 800b781

Reviewed: 2 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.