wrap-up

Close out a launched Claude Managed Agent — recap every primitive the founder now owns, regenerate the single-file overview page, and suggest the next 1-2 upgrades. Use when the user says "wrap up", "close this out", "what do I own now", "give me the summary", "recap the agent", or when the orchestrator routes phase=wrap-up. primitives_inventory.py tables everything owned (agent, environment, session, memory, outcome, deployment); overview_page.py regenerates a self-contained ./my-agent/agent-overview.html; upgrade_suggester.py ranks the next moves from recorded deferrals plus standing hardening steps. Companion to run-without-you; the last stop before phase=done.

Quality

85%

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

78%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 compact, well-structured overview with executable commands and real script references, supported by clear hard rules. Weakest spots are the slightly vague Finalize step and validation expressed as constraints rather than explicit inline checkpoints.

Suggestions

Make the Finalize step fully executable by giving the exact goal_state.py invocation (with script path) and a concrete check for NEXT-DIRECTIONS.md currency.

Convert the Hard rules into an inline validation checkpoint (e.g., verify the overview regenerated and phase advanced) within the workflow sequence.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, with tight bash commands and short hard rules, but the opening framing ('The explicit close-out. Confirm what's live...') and the supplementary forcing-question library add minor tokens that could be trimmed.	4 / 5
Actionability	The three main workflow commands are concrete, copy-paste ready bash with full flags and existing script paths, but the 'Finalize' step ('Ensure NEXT-DIRECTIONS.md is current... then goal_state.py advance') is less specific, leaving a minor gap.	4 / 5
Workflow Clarity	A clear four-step sequence is present with verification guidance in the Hard rules ('read it from the sheet + goal state, never assert primitives that weren't created'), though checkpoints are stated as constraints rather than inline validate-then-proceed steps.	4 / 5
Progressive Disclosure	Well-organized into Workflow, Hard rules, Forcing-question library, and Tools sections, with one-level-deep references to real bundle scripts (primitives_inventory.py, overview_page.py, upgrade_suggester.py) that match the actual file listing.	5 / 5
	Total	17 / 20 Passed

Description

91%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 strong, well-structured description that clearly states what the skill does and when to invoke it, with rich natural trigger terms and a distinct close-out niche. Slight room to tighten the per-script elaboration and sharpen distinctiveness from its companion skills.

Suggestions

Trim the per-script breakdown in the description to reduce padding while keeping the three core actions explicit.

Add a brief discriminator from the companion 'run-without-you' skill to reduce overlap risk in the phase pipeline.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('recap every primitive the founder now owns, regenerate the single-file overview page, and suggest the next 1-2 upgrades') with per-script elaboration, but the core action list is three high-level moves rather than an expansive set, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both 'what' (close out the agent: recap, regenerate overview, suggest upgrades) and 'when' (a full 'Use when the user says...' clause with concrete trigger phrases).	5 / 5
Trigger Term Quality	Provides comprehensive natural trigger phrases a user would actually say ('wrap up', 'close this out', 'what do I own now', 'give me the summary', 'recap the agent') plus the orchestrator routing cue, covering synonyms and variations.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche ('Close out a launched Claude Managed Agent', 'the last stop before phase=done') with distinct phase=wrap-up routing, but as a self-described 'Companion to run-without-you' in a phase pipeline it carries minor overlap risk with related skills.	4 / 5
	Total	18 / 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/wrap-up/SKILL.md
Commit: 19392f7

Reviewed: ~14 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.