stage-launch

Phase 2 of building a Claude Managed Agent — turn a validated build sheet into exact API payloads and a resumable BYOK curl launch script, then launch (environment → agent → session → kickoff) using the founder's OWN Anthropic key. Use when the user says "launch it", "deploy the agent", "create the agent now", or when the orchestrator routes phase=stage-launch. payload_generator.py emits the four ordered payloads; launch_script_writer.py writes launch.sh that reads $ANTHROPIC_API_KEY at runtime and never embeds it; payload_validator.py runs a pre-launch check including an API-key-leak scan. No tool in this skill makes network calls — the user runs launch.sh themselves. Distinct from interview (planning) and grade-iterate (the outcome loop).

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

92%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 a lean, fully executable launch playbook with an explicit validation feedback loop and a clean one-level-deep split into real bundle scripts. Its lone blemish is restating the key-safety rule across three sections.

Dimension	Reasoning	Score
Conciseness	The body is efficient — short prose, executable code blocks, and no padding with concepts Claude already knows. It stops at 5 because the API-key-safety message is restated in three places (the intro, workflow step 4, and the 'Hard rules' section), a minor redundancy that could be consolidated.	4 / 5
Actionability	Every step ships copy-paste-ready commands — 'python3 scripts/payload_generator.py --sheet ... --out-dir ...', 'python3 scripts/payload_validator.py --dir ...', the key-presence check, 'export ANTHROPIC_API_KEY=...', and './my-agent/launch.sh' — covering the common cases end to end. It matches the score-5 anchor and is not 4 because there are no material gaps in executable detail.	5 / 5
Workflow Clarity	A clearly numbered 5-step sequence (generate → write → validate → key step → launch+watch) with an explicit validation checkpoint and feedback loop ('FAIL blocks — Fix and re-run') plus resumability. Although the launch is somewhat irreversible, validation is present so the destructive-cap does not apply; it is not 4 because checkpoints and error recovery are explicit.	5 / 5
Progressive Disclosure	SKILL.md is an overview whose detailed logic lives in three real bundle scripts (payload_generator.py, launch_script_writer.py, payload_validator.py), all referenced by path and listed in a 'Tools' section — one level deep, clearly signaled, and verified to exist in ./scripts. It matches the score-5 anchor and is not 4 because the split is clean and navigation is easy.	5 / 5
	Total	19 / 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.

The description is concrete, trigger-rich, and explicitly demarcates both its scope and its boundaries against sibling phases. Its only weakness is a couple of missing natural trigger synonyms and a reliance on one internal routing phrase.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — turning a build sheet into 'exact API payloads', a 'resumable BYOK curl launch script', launching in an ordered 'environment → agent → session → kickoff' sequence, plus per-tool responsibilities (emits four ordered payloads, writes launch.sh, runs a key-leak scan). Coverage is comprehensive, matching the score-5 anchor; it is not score 4 because there are no meaningful gaps.	5 / 5
Completeness	Explicitly answers both 'what' (build sheet → payloads + launch script → ordered launch) and 'when' via a concrete 'Use when the user says...' clause with multiple trigger phrases. It matches the score-5 anchor directly and is not 4 because the 'when' is explicit and specific, not merely implied.	5 / 5
Trigger Term Quality	Includes natural user phrases — 'launch it', 'deploy the agent', 'create the agent now' — which users would actually say, giving good keyword coverage. It falls short of 5 because a few natural synonyms ('start the agent', 'spin up') are missing and the 'orchestrator routes phase=stage-launch' trigger is internal jargon rather than a user utterance.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (Phase 2 launch of a Claude Managed Agent) and explicitly states 'Distinct from interview (planning) and grade-iterate (the outcome loop)', minimizing overlap. It is not 4 because the boundaries against sibling skills are stated outright, not merely implied.	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: alirezarezvani/claude-skills
Path: agent-launcher/skills/stage-launch/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.