Name: wrap-up
Rating: 74.4 (1 reviews)
Author: alirezarezvani

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

93%

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 wrap-up in alirezarezvani/claude-skills

Quality

Content

93%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 tight, actionable skill body with executable commands and clean structure. The only gap is an explicit validation/confirmation checkpoint in the workflow, though the operations are non-destructive.

Suggestions

Add an explicit verification step after regenerating the overview (e.g. confirm agent-overview.html was written) to close the workflow-clarity gap.

Since the referenced scripts/ files are not present in the bundle, either ship them or note in the body that they are provided by the companion run-without-you skill.

Dimension	Reasoning	Score
Conciseness	Lean body: a short intro, a numbered workflow with executable commands, hard rules, and a tools list — no padding or explanations of concepts Claude already knows.	5 / 5
Actionability	Provides copy-paste-ready bash commands with full flags, specific file paths, and concrete parameters (e.g. '--top 2', '--status live'), covering the common cases.	5 / 5
Workflow Clarity	Clear 4-step sequence with a final finalize step, but lacks an explicit verification checkpoint (e.g. confirm the overview regenerated or the sheet was read) — the hard rules serve as implicit constraints instead.	4 / 5
Progressive Disclosure	Self-contained, well-organized into sections (Workflow, Hard rules, Forcing-question library, Tools) for a single-purpose close-out skill; the Tools list cleanly signals the three referenced scripts.	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.

A strong, specific description that clearly states what the skill does and when to use it, with natural trigger phrases and a distinct niche. Trigger-term coverage is good but not exhaustive of every possible synonym.

Suggestions

Add a couple more trigger synonyms (e.g. 'finish up', 'handoff summary') to push trigger-term coverage toward comprehensive.

Consider noting the explicit 'not for' boundary (e.g. not for mid-build phases) to further reduce conflict risk.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'recap every primitive', 'regenerate the single-file overview page', 'suggest the next 1-2 upgrades' — and enumerates the owned primitives (agent, environment, session, memory, outcome, deployment), giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what ('Close out a launched Claude Managed Agent...') and when ('Use when the user says...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Lists natural user phrases ('wrap up', 'close this out', 'what do I own now', 'give me the summary', 'recap the agent') with synonyms, but a few common variations are absent so it sits just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (the wrap-up phase of a Claude Managed Agent) with distinct triggers and an explicit companion relationship, minimizing overlap with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

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

	Total	14 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/wrap-up/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.