Name: run-without-you
Rating: 72 (1 reviews)
Author: alirezarezvani

run-without-you

Phase 4 of building a Claude Managed Agent — make it run without you. Turn a graded agent into a recurring scheduled deployment (POSIX-cron), an event-driven curl trigger, or confirmed on-demand use, then finalize the versioned roadmap. Use when the user says "run it every morning", "put it on a schedule", "nightly", "weekly", "automate this", "make it recurring", or when the orchestrator routes phase=run-without-you. deployment_builder.py builds the POST /v1/deployments payload (initial_events must include user.message; optionally nests a user.define_outcome so each firing self-grades); cron_validator.py validates the 5-field cron + IANA timezone and prints the wall-clock DST note; next_directions_writer.py writes NEXT-DIRECTIONS.md. No tool makes API calls — the deployment is created via BYOK curl. Distinct from grade-iterate (the in-session loop) and wrap-up (closeout).

Quality

90%

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

The canonical home for this skill is run-without-you in alirezarezvani/claude-skills

Quality

Content

88%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.

A well-structured, actionable skill body with executable commands, a validated multi-step workflow, and a clear test-before-trust feedback loop. The two weakest points are mild verbosity in the forcing-question scaffolding and one inline citation lacking a navigable link.

Suggestions

Convert the inline 'Cite: cma-primitives.md' reference into a markdown link (e.g. [cma-primitives.md](../../references/cma-primitives.md)) so all references are navigable.

Tighten the Forcing-question library by collapsing the repeated 'Recommend:'/'Cite:' scaffolding into a compact table or a single lead-in line, trimming tokens without losing the recommend-and-cite guidance.

Move the wall-clock DST explanation (spring-forward skipped / fall-back fires twice) into the referenced loops-and-workflows.md and keep only the actionable rule ('avoid 02:00–03:00 in DST zones') inline.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no explanation of what cron or a deployment is), but the four-item 'Forcing-question library' with repeated Recommend/Cite scaffolding and the inline DST explanation add a little that could be trimmed, so it is efficient rather than maximally lean.	4 / 5
Actionability	Provides copy-paste-ready, fully-specified commands for each tool — 'python3 scripts/cron_validator.py --cron "0 9 * * *" --timezone Europe/Berlin', 'python3 scripts/deployment_builder.py --sheet ... --agent-id ... --env-id ... --nest-outcome --out ...', 'goal_state.py set --phase wrap-up' — covering the common cases with real flags.	5 / 5
Workflow Clarity	The recurring workflow is a clearly sequenced five-step process with explicit validation checkpoints and a feedback loop: cron_validator exits 1 on bad input, 'Test before you trust — Fire one manual run, read the verdict, only then leave the cron in place', and 'Pin the agent version... once it passes'.	5 / 5
Progressive Disclosure	Well-organized into distinct sections (trigger table, workflow, hard rules, forcing questions, tools) with a one-level-deep signaled reference ([../../references/loops-and-workflows.md]), but the cited cma-primitives.md is referenced by name only without a link path, a minor navigation gap.	4 / 5
	Total	18 / 20 Passed

Description

92%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 dense, specific description that concretely states capabilities, gives natural trigger phrases, and explicitly distinguishes the skill from adjacent phases. Only minor trigger-term gaps (daily/hourly/monthly) keep it from a perfect mark.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the deployment lifecycle — 'recurring scheduled deployment (POSIX-cron)', 'event-driven curl trigger', 'on-demand use', 'finalize the versioned roadmap' — plus tool-level actions ('builds the POST /v1/deployments payload', 'validates the 5-field cron + IANA timezone', 'writes NEXT-DIRECTIONS.md'), giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' ('Turn a graded agent into a recurring scheduled deployment... or confirmed on-demand use, then finalize the versioned roadmap') and 'when' (concrete 'Use when the user says...' trigger phrases), matching the anchor for clearly answering both with concrete triggers.	5 / 5
Trigger Term Quality	Strong natural-phrase coverage ('run it every morning', 'put it on a schedule', 'nightly', 'weekly', 'automate this', 'make it recurring') with synonyms, but common cadence terms like 'daily', 'hourly', and 'monthly' are missing, so it sits just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (Phase 4 recurring deployment) and explicitly disambiguates ('Distinct from grade-iterate (the in-session loop) and wrap-up (closeout)'), minimizing conflict risk with sibling skills.	5 / 5
	Total	19 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 suspicious	Warning
referenced_paths_exist	Referenced path issues: 6 missing	Warning

	Total	13 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/run-without-you/SKILL.md
Commit: 19392f7

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.