docs(agents): review Tessl skills registry (closes #103) - #216
docs(agents): review Tessl skills registry (closes #103)#216dem-extra1 wants to merge 7 commits into
Conversation
Add a coding-agents section on Tessl so the lab has a recorded answer to whether its skills registry, package manager, security scanning, and evals are worth adopting alongside the Agent Skills standard and the Posit skill collection the lab already uses. The verdict is that the package-manager and governance features solve a sprawl problem a single-repo lab does not have, while the registry's security scans and the with/without eval model are worth borrowing. Every claim is cited to a Tessl page fetched on 2026-09-09; the pages fetched do not describe spec-driven development, and the section says so rather than filling the gap from memory. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The chapter spell-check flags the possessive as a separate token, as it does for the other possessives already listed. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The section heading advertised "Spec-Driven Tooling" while the body reports that the fetched Tessl pages do not describe spec-driven development; the heading now matches the body. The training-data and auto-update claims carried no citation of their own, so each now cites the documentation page the surrounding paragraph already draws on. One line carrying two clauses is split per semantic line breaks. Findings from the adversarial pre-push review (agy --print). Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
|
Pushed with the pre-push guard's ALLOW_UNREVIEWED_PUSH=1 override. The adversarial-reviewer subagent the guard expects is not registered in this session, so the adversarial pre-push review was performed by the Google Antigravity CLI (agy --print) against the full branch diff; real findings were fixed before this push. The @claude review workflow and a requested Copilot review are the independent reviews of record. Posted by Claude Code (AI agent) --- not written by a human. |
|
👀 Picked up by workflow run #34435956141. Setup runs first; Claude itself responds after that. |
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
There was a problem hiding this comment.
🟡 Changes recommended
The new Tessl install instructions include a curl | sh command without the safety note used elsewhere in the chapter, which should be addressed before merging.
Once you've addressed the issues Copilot identified, you can request another Copilot review.
Pull request overview
This PR adds documentation to the “Working with AI” site describing Tessl as a public registry and CLI for discovering, installing, and evaluating Agent Skills, and wires that new content into the coding-agents chapter so readers can learn about skill distribution beyond the standard and Posit’s collection.
Changes:
- Added a new
chapters/ai-tools/tessl.qmdpage fragment describing Tessl’s registry, CLI workflow, security scanning/evals, and pricing/telemetry considerations. - Inserted a new “Tessl: Skills Registry and CLI” section into
chapters/coding-agents.qmdimmediately after the existing Agent Skills section. - Added bibliography entries and spelling wordlist terms needed by the new Tessl content.
File summaries
| File | Description |
|---|---|
references.bib |
Adds Tessl website/docs citations used by the new Tessl fragment. |
inst/WORDLIST |
Adds new proper nouns/acronyms referenced in the Tessl content for spellcheck. |
chapters/coding-agents.qmd |
Adds a new Tessl section and includes the new fragment. |
chapters/ai-tools/tessl.qmd |
New documentation fragment covering Tessl’s registry/CLI and how it relates to Agent Skills and Posit skills. |
Review details
- Files reviewed: 4/4 changed files
- Comments generated: 1
- Review effort level: Lite
💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
Copilot's PR review flagged the curl | sh install one-liner for missing the safety note used elsewhere in the chapter (see installing-claude-code-windows.qmd); the Claude review separately flagged that the Node.js 22.17+ requirement was cited to the installation page, which never mentions Node.js, instead of the supported-platforms page where that fact actually lives.
There was a problem hiding this comment.
🔵 Needs a closer look
The Tessl page content currently conflicts with the PR description around “spec-driven development” coverage and should be reconciled for accuracy/consistency.
Review details
Suppressed comments (1)
Previously missed (1) — in code that hasn't changed since the last review.
chapters/ai-tools/tessl.qmd:44
- The PR description says this write-up covers Tessl's spec-driven development tooling, but this paragraph reads more like a missing-feature note (and the rest of the page doesn’t revisit spec-driven development). To avoid a mismatch between the PR description and the content, consider rephrasing this to explicitly frame spec-driven development as a marketed feature that isn’t documented in the reviewed sources (or add a short dedicated subsection elsewhere if you have more details).
- Files reviewed: 4/4 changed files
- Comments generated: 0 new
- Review effort level: Lite
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
# Conflicts: # inst/WORDLIST # references.bib
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
There was a problem hiding this comment.
🟡 Changes recommended
references.bib currently has a malformed Tessl entry (missing fields/closing brace) that will likely break bibliography parsing during renders.
Once you've addressed the issues Copilot identified, you can request another Copilot review.
Review details
- Files reviewed: 4/4 changed files
- Comments generated: 2
- Review effort level: Lite
| [Tessl](https://tessl.io/) is a commercial platform for managing | ||
| [Agent Skills](https://agentskills.io/home) | ||
| (see @sec-ai-agent-skills for what a skill is) | ||
| the way `npm` or `pip` manage code dependencies: | ||
| a searchable registry of skills and plugins, | ||
| a `tessl` command-line tool that installs them into a project, | ||
| and a hosted service that scores each skill for quality and security | ||
| and measures whether it changes what an agent produces | ||
| [@tessl_docs_overview]. | ||
| The notes below reflect the Tessl website and documentation | ||
| as read on 2026-09-09. |
The union resolver used for the sync dropped the blank line between every pre-existing entry and truncated one entry, which made pandoc reject the file and failed the build. The file is now rebuilt from the two parent versions: main's entries in main's order and formatting, then this branch's new entries appended, validated with pandoc. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
There was a problem hiding this comment.
🟡 Changes recommended
The new Tessl page introduces a couple of concrete documentation/style issues (unsupported blog reference and a long comma-separated list that conflicts with repo prose conventions).
Once you've addressed the issues Copilot identified, you can request another Copilot review.
Review details
Suppressed comments (1)
Previously missed (1) — in code that hasn't changed since the last review.
chapters/ai-tools/tessl.qmd:95
- This is a comma-separated list of 7 items; repo style guidance prefers bullet lists for 3+ items in Quarto prose (see .github/copilot-instructions.md:26-44). Converting this to a bullet list improves readability and keeps the style consistent across chapters.
- Files reviewed: 4/4 changed files
- Comments generated: 1
- Review effort level: Lite
| The pages fetched for this review do not describe spec-driven development: | ||
| apart from one blog article linked from the home page, | ||
| the current site is about managing skills, | ||
| not about generating code from specifications. |
|
Claude finished review — View run Review: PR #216 —
|
|
Why
Issue #103 asks for a review of Tessl, which runs a public registry of Agent Skills plus a CLI for installing them and for spec-driven development. The website already covers the Agent Skills standard (
@sec-ai-agent-skills) and Posit's skill collection (@sec-ai-posit-skills) but has nothing on where skills are published and discovered, or on Tessl's spec-driven tooling. This PR adds achapters/ai-tools/tessl.qmdfragment covering what Tessl is, how its registry relates to the standard and to Posit's skills, how to use it with Claude Code and other agents, pricing tiers, and a "Useful to us?" verdict, and includes it inchapters/coding-agents.qmddirectly after the Agent Skills section.Closes #103
🤖 Generated with Claude Code