routine-advisor

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

Quality

60%

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

67%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 concrete capability names, schedule shapes, and cron examples, and its workflow includes a dedup checkpoint and confirmation gate. Its main weakness is conciseness: the delivery/conditional-routine behavior is repeated across sections and could be consolidated.

Suggestions

Consolidate the conditional-routine / no-delivery-call guidance into one authoritative passage; the current three restatements (prompt parameter, Delivering Results intro, delivery-step paragraph) are redundant.

Add one complete end-to-end builtin__trigger_create example showing name, prompt, and schedule filled in together to lift actionability to copy-paste readiness.

Consider moving the "Routine Ideas by User Type" catalog or the detailed delivery rules into a reference file so the overview stays lean.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but the conditional-routine / no-delivery-call behavior is restated three times (prompt param, Delivering Results intro, and the delivery-step paragraph) and could be tightened.	3 / 5
Actionability	Concrete capability names (builtin__trigger_create, builtin__trigger_list, builtin__outbound_delivery_targets_list, builtin__outbound_deliver), explicit JSON schedule shapes, and ready cron expressions give highly actionable guidance; the only gap is the absence of one full end-to-end create call stitching all parameters together.	4 / 5
Workflow Clarity	There is a clear sequence with a dedup checkpoint (check builtin__trigger_list before creating) and a wait-for-user-confirm gate, plus pacing rules; it falls short of 5 because no explicit error-recovery feedback loop is specified.	4 / 5
Progressive Disclosure	Content is well organized into clearly labeled sections and is self-contained with no nested references; the body is somewhat long and the dense delivery guidance could plausibly live in a separate reference file, keeping it just below a 5.	4 / 5
	Total	15 / 20 Passed

Description

53%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 clear and third-person with a well-defined niche, but it states only the "what" and lacks an explicit "when to use" trigger clause, capping completeness. Trigger-term coverage is moderate and could be enriched with natural phrasing users actually say.

Suggestions

Add an explicit "Use when…" clause naming concrete trigger phrases (e.g. "Use when the user mentions recurring tasks, daily/weekly check-ins, or wanting to automate something on a schedule").

Weave in natural trigger terms users say ("every morning", "remind me", "schedule", "automate") rather than relying on the more technical "cron routines".

Optionally list one or two more concrete actions (e.g. "creates and manages scheduled routines") to lift specificity above a single verb.

Dimension	Reasoning	Score
Specificity	Names the domain ("cron routines") and one concrete action ("Suggests") plus its basis ("user context, goals, and observed patterns"), but does not enumerate multiple distinct actions, so it sits between the score-2 and score-4 anchors.	3 / 5
Completeness	Clearly states what the skill does but provides no "Use when…" trigger guidance; per the judging guidelines a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Includes relevant terms ("cron routines", "routines", "patterns") but omits the natural phrases users actually say (e.g. "every morning", "remind me", "schedule", "automate"), matching the "some relevant keywords but missing common variations" anchor.	3 / 5
Distinctiveness Conflict Risk	"cron routines" carves a clear scheduling-automation niche with minimal conflict risk, though it overlaps slightly with general reminder/scheduling skills so it is not a clean 5.	4 / 5
	Total	13 / 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: nearai/ironclaw
Path: skills/routine-advisor/SKILL.md
Commit: 9102166

Reviewed: ~16 hours 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.