product-plugins

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.

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.

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 an eval scenario for whether its result means anything — whether the task can discriminate, and whether a judge applying its criteria reaches the same verdict twice. Use as one lens in a code review run.

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 change for what an adversary could do with it, and for what it exposes about people. Use as one lens in a code review run.

Review a change for what happens when there is more of it than expected, and when something it depends on fails. Use as one lens in a code review run.

Review a change for whether the next person can understand it and change it safely. Use as one lens in a code review run.

Review a change for whether it does what it is meant to do, and whether the data it touches survives it intact. Use as one lens in a code review run.

Install or update Tessl Code Review in a GitHub repository by writing a thin caller workflow that invokes the Tessl Code Review Action. Inspects existing workflows and any Code Review caller already present, asks when reviews should run and whether findings should block the merge, proposes the change, and only writes after explicit approval. Use when someone wants to add, set up, enable, configure, update, or remove Tessl Code Review, AI code review, or automated pull-request review in a repository, or wants to switch it between advisory and gate mode.

Author a review lens for Tessl Code Review, the reviewer skill that decides what a review looks for in a diff. Settles the review question and the bar a finding has to clear, drafts the lens, runs it against changes that should and should not trip it, backtests it against changes that already carry review feedback, and packages it as a pinned reference a workflow can select. Use when someone wants their code review to catch something it misses, to stop flagging something it should not, or to write, fork, tune, or debug a code review lens. Not for `tessl review` rubrics, which score skill quality rather than code.

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

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.

Run task evals, analyze results, diagnose failures, apply targeted fixes, and re-run to verify improvements. Use when debugging evaluation scores, fixing failing or regressed criteria, analyzing why eval criteria pass or fail, reviewing eval rubric quality and redundant criteria, tracking before/after score improvements, editing plugin content to fix specific failing behaviors, or improving agent performance based on eval evidence.

Run the full optimization cycle for a plugin — review best practices, generate eval scenarios, run BOTH activation evals (does the skill self-activate?) and content evals (does the plugin help solve tasks?), diagnose gaps, fix, and re-run until scores improve. Use when someone says "optimize my skill", "improve my plugin", "run evals", "benchmark my plugin", or wants to measure and improve how well a plugin helps agents solve tasks.

Review and improve your skill with actionable recommendations. Reviews the whole bundle, validates syntax and references, explains rubric, shows before/after scores, and edits the SKILL.md and its reference docs. Use when reviewing skill quality, improving a SKILL.md or its reference files, checking scoring dimensions and quick wins, auditing progressive disclosure and orphaned bundle files, generating improvement recommendations, running a post-edit quality audit, creating approval-gated change proposals, or automating the skill review workflow. For the full optimization cycle (review + evals + improve), use `optimize-skill-performance-and-instructions`.

Run task evals across multiple Claude models, compare results side-by-side, and optimise. Use when you want to benchmark a skill across models, compare haiku vs sonnet vs opus performance, run multi-model comparison or benchmark reports, identify model-specific gaps versus universal plugin gaps, evaluate whether a skill works for all model tiers, or validate a skill before publishing it to the registry.

Derive custom review-plugin judges, rubrics, and scoring criteria from evidence — existing skills, PR review feedback, and accumulated agent logs — by finding where agents needed correction or skills failed to activate, then translating those patterns into scoring dimensions and anchors. Hands the rubric design to create-review-plugin for scaffolding. Use when the user wants a custom skill reviewer or scoring rubric grounded in how their agents actually behave — to grade skills consistently, or build review criteria from past PR feedback and agent logs.

Scaffold and author a custom Tessl reviewer plugin, by forking the default rubric or building one from scratch. Fetches the published default Tessl review rubric (tessl/default-skill-review) so you can read and tweak it, scaffolds the plugin directory, writes rubric files and config.json, and validates with tessl review run. Use when the user wants to create or customise a review plugin, fork or tweak the default reviewer rubric, change scoring weights, add custom judges, or build a domain-specific rubric for tessl review.

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.

Use once the problem and artifacts are understood, to decide the right shape for the context. Produces a short composition plan - a single skill for simple cases, or a plugin with the right mix of skills, rules, hooks, MCP servers, and commands - and confirms it with the user before anything is built.

Use at the start of creating context, to understand the problem the user is solving and take stock of what they already have. The user may arrive with an existing skill or plugin, code, a written prompt or transcript, or nothing but a pointer ("go look at my PRs"). Gathers what exists and fills the gaps - by asking or by hunting - until there is enough to plan a composition.