product-plugins

Use when a composition is built and the user wants to share it, to publish or re-publish it to the Tessl registry. Lints it, confirms private/public visibility, and publishes.

Answer a Tessl Code Review on a pull request the responder authored. Decides what each finding deserves, fixes, refutes, or declines it with a reason, replies on the thread, and keeps the pull request doing what it was opened to do. Use when review feedback has arrived on an open pull request and the responder is the one answering it, for example "address the review", "respond to the findings", "Tessl left comments", "deal with the review comments", "the check is red and there are findings", or when review rounds keep coming and are not converging. Not for performing a review of someone else's change; that is tessl code review.

Review a change to a code block a reader is meant to copy — a workflow, command, config file, or manifest embedded in documentation — for whether it works as printed. Use as one lens in a code review run.

Review a code change for realistic functional defects, data loss, duplicate writes, ordering mistakes, and broken integration contracts. Use as one lens in a code review run when correctness or data integrity may be affected.

Review a code change for maintainability, naming, weak contracts, duplicated local precedent, misleading comments, and API or code surfaces that do not enforce what they promise. Use when reviewing for readability, refactoring, code quality, or API design issues.

Review a change to Markdown that is not part of an agent plugin (standalone skills, AGENTS.md and CLAUDE.md, READMEs, and documentation) for whether it is true of the repository, whether an agent or reader following it acts correctly, and whether it meets the repository's own rules for that content. Use as one lens in a code review run.

Review a change for observability. Use as one lens in a code review run.

Review a change to the contents of an agent plugin (its skills, references, rules, evals, manifest, README, and the scripts and hooks it bundles) for whether the plugin ships, whether an agent picks the right skill, and whether an agent following it acts correctly and safely. Use as one lens in a code review run.

Review a change to a published plugin for what users receive when it lands — whether the version step, the documentation, and the published bundle match the change. Use as one lens in a code review run.

Review a change to a public repository for content written for an internal audience, or content a reader outside the company should not have. Use as one lens in a code review run.

Use when reviewing a pull request, to check for logic bugs, style consistency, and security concerns and summarise the findings for the author.

Review a code change for load, data-volume, concurrency, retry, rollout, dependency-failure, latency, throughput, timeout, and fault-tolerance risks. Use when reviewing for performance under load, scalability, resilience, or failure handling.

Review a code change for trust-boundary, authorization, injection, secret-handling, logging, and privacy disclosure risks. Use when reviewing for security, privacy, vulnerabilities, auth bugs, secrets in logs, sensitive-data exposure, or PII disclosure.

Review a change to an agent-facing skill for whether an agent following it reaches the outcome the skill describes. Use as one lens in a code review run.

Create a repo-defined schedule in a project's tessl.json from a plain-language description, optionally authoring the repo-local skill it runs. Use when the user wants to schedule a skill to run on a recurring cadence ("run X every morning", "kick off the report nightly", "schedule this weekly"), set up a recurring launch run, or add a `schedules` block to tessl.json. The user describes the task, cadence, and environment in plain words; this skill chooses the most readable supported schedule format, adds and validates the entry, and explains what happens on push. Not for one-off runs (use `tessl launch`) or for moving an existing UI/CLI schedule into the file (use schedule-migrate).

Generate eval scenarios from a Tessl plugin (a packaged skill bundle), run baseline + with-context evals, and present results. Use when setting up an evaluation pipeline, running benchmarks, generating test scenarios, measuring skill performance or accuracy, scoring how well a skill helps agents solve tasks, or evaluating skill effectiveness before publishing.

Evaluate a SKILL.md for quality. An agent that dynamically discovers the rubric files and scores the skill against each, producing one result per rubric. Use when running a skill review workflow or testing skill quality against configurable rubrics.