Summarizes a Product’s recorded changes, pending owner actions, and failures since the last successful delivery. It writes the report to the configured wiki and sends it through the configured interface, or records a quiet check when nothing needs attention.
Deliver the Product summary through its configured interface and wiki.
Run score Not tested
See how to installThis skill reviews a Product’s actual records, Tasks, and attention counts. It summarizes what changed since the last successful delivery, what the owner needs to address, and which items failed, using those records and summary.md as evidence. It passes the summary to summarize_company_product, which records it in the configured wiki and delivers it through the configured interface and destination. If summary.md contains an undelivered attempt, the comparison still starts from the last successfully delivered snapshot. When nothing needs attention, the skill records a quiet successful check.
Use it to keep track of a Product’s status over time or to share which items an owner should review or handle. It is also useful when you want recorded changes and failures summarized in the wiki and sent to the configured destination.
The skill does not add progress that is absent from the records. It does not accept or complete work or change Sources or schedules. Delivery uses the configured interface and destination.
This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.
AI checked the SKILL.md for operations that need care and for setup requirements. The score comes only from actually running the skill (hands-on test).
Not counted in the score. Rated by AI (OpenAI Codex) as of Oct 25, 2026. Treat it as a guide and read the original before installing.
Review the instructions the agent will receive before you install.
Read the Product identified in the message, its Tasks and attention counts. Explain what changed, what awaits the owner and what failed, using actual records and summary.md. That page may retain an undelivered attempt; the summary tool compares changes against the last successfully delivered snapshot. Pass your narrative to summarize_company_product to write the summary to its wiki and deliver it through the configured interface and destination. Do not invent progress. Do not accept or complete work, alter Sources or schedules. When nothing needs attention, record a quiet successful check.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Reviews code for style, naming, error handling, exposed credentials, and possible bugs, security, or performance issues. It can run an automated style check and returns structured feedback grouped by severity, from critical fixes to optional improvements.
Get practical guidance for Git commits, branch names, and pull requests. The skill follows a consistent commit format, offers naming patterns and a PR description template, and includes common commands for starting, updating, and submitting work.
Reviews configured sources and proposes actionable backlog tasks tied to a suitable project. Each proposal cites inspected evidence and its observed content hash, while stable keys prevent duplicate proposals across later scans.
Refreshes a product’s status using its playbook, projects, tasks, and configured sources. It records observed progress and failures, removes references to archived work, and presents project completion proposals for human review without changing task or project states.
Inspect the host running the AgentOS process, including its operating system, architecture, Python runtime, processor, and UTC time. You can also list the direct contents of a chosen directory, with the skill folder as the default location.