agent-self-scheduling

Make an AI agent run on a schedule, loop, or interval — cron, heartbeats, recurring autonomous checks. Use for "run every N minutes", "schedule a task", "run on a loop", "heartbeat". Covers external clocks (Claude Code, Codex, Pi) vs Hermes' built-in scheduler.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Advisory

Suggest reviewing before use

Quality

Content

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tightly written, highly actionable reference with clear sequencing and verification checkpoints. The only weakness is progressive disclosure: all content is inline with no external references for a multi-tool skill that has grown past 50 lines.

Suggestions

Consider moving the per-tool detail (Hermes-unique features, cmux orchestration notes) into reference files and linking to them from a leaner overview.

Add a short pointer near the top indicating where each tool's specifics live, so the overview stays a quick entry point.

If keeping everything inline is intentional, trim the cmux/Hermes feature lists to only the must-know items to stay within a single-file overview's budget.

Dimension	Reasoning	Score
Conciseness	The body is dense and lean, assuming Claude's competence; it adds only tool-specific detail Claude would not know (Hermes/cmux) and avoids explaining generic concepts, so every token earns its place.	3 / 3
Actionability	It provides fully executable commands — 'claude -p "PROMPT" --output-format json --allowedTools "Read,Edit,Bash"', 'hermes cron create "every 1h" ...', cron entries, and while-sleep loops — that are copy-paste ready with only justified placeholders.	3 / 3
Workflow Clarity	A clear decision flow (Camp A vs Camp B) is paired with an explicit 'Verify it fires (before reporting success)' validation checklist and a gotchas section covering error recovery, matching the top anchor.	3 / 3
Progressive Disclosure	The skill is well-organized with clear headers but is a 68-line multi-tool reference kept entirely inline with no external references; per-tool detail (Hermes features, cmux) could be split into reference files to lighten the overview. Not a 3 because there are no well-signaled one-level-deep references, and not a 1 because structure and navigation are clean.	2 / 3
	Total	11 / 12 Passed

Description

100%

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 strong, specific description with explicit trigger guidance and concrete actions. It distinguishes its niche clearly and avoids vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'run on a schedule, loop, or interval — cron, heartbeats, recurring autonomous checks' — and names specific mechanisms rather than vague abstractions, matching the top anchor.	3 / 3
Completeness	It explicitly answers both 'what' (make an agent run on a schedule/loop/interval) and 'when' ('Use for ...' trigger clause), satisfying the top anchor for both halves.	3 / 3
Trigger Term Quality	It includes natural user phrasings via 'Use for "run every N minutes", "schedule a task", "run on a loop", "heartbeat"', giving good coverage of terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	It carves a clear niche (agent self-scheduling, distinguishing external clocks vs Hermes' built-in scheduler) with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mishatojk/davidskills
Commit: 66860fb

Reviewed: 6 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.