CtrlK
BlogDocsLog inGet started
Tessl Logo

tessl/code-review-lens-creator

Author a review lens for Tessl Code Review: the reviewer skill that decides what `tessl code review` and the Tessl Code Review Action look for in a diff. Frames the review question and the bar a finding has to clear, drafts the lens, validates it by running it against changes that should and should not trip it, backtests it against pull requests that already carry review feedback, then packages it as a pinned registry ref 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.

90

1.29x
Quality

97%

Does it follow best practices?

Impact

96%

1.29x

Average score across 2 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Overview
Quality
Evals
Security
Files

Quality

Content

92%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.

The body is a tight, well-structured procedure that assumes competence, carries only domain-specific context Claude lacks, and routes detail into two clearly signaled reference files. Validation and feedback loops are explicit throughout the run/backtest/tune cycle.

DimensionReasoningScore

Conciseness

Lean and domain-specific: it explains only what Claude would not know (how a Tessl review uses a lens — the six facts) and avoids generic padding about code review basics; every section earns its place.

5 / 5

Actionability

Concrete procedural steps and executable bash commands for publishing/pinning ('tessl code review --skill ./review-lenses/...' and the pinned '@1.0.0#...' form), but the actual lens-authoring detail is delegated to references/lens-anatomy.md rather than carried inline.

4 / 5

Workflow Clarity

A clearly sequenced six-step procedure with explicit validation checkpoints — run on a should-trip and a should-not change, backtest against known-good feedback — and a feedback loop ('Tune and re-run until... Report counts, not impressions' and 'Re-backtest against the same set before adopting').

5 / 5

Progressive Disclosure

SKILL.md is an overview that signals one-level-deep references inline ('Read references/lens-anatomy.md first, for...') to two real bundle files (lens-anatomy.md, validation.md); content is appropriately split and easy to navigate.

5 / 5

Total

19

/

20

Passed

Description

100%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.

The description is specific, complete, and distinctive: it names concrete actions, gives natural trigger phrases for both what and when, and draws a clear boundary against the related rubric skill. Third-person voice is maintained throughout with no padding.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — '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... and packages it as a pinned reference' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both 'what' (author/settle/draft/run/backtest/package a lens) and 'when' ('Use when someone wants their code review to catch something it misses...'), plus an explicit boundary ('Not for tessl review rubrics').

5 / 5

Trigger Term Quality

Natural trigger phrases users would actually say are well covered: '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', including synonyms (write/fork/tune/debug).

5 / 5

Distinctiveness Conflict Risk

Clear niche — Tessl Code Review lenses — with distinct triggers and an explicit exclusion ('Not for tessl review rubrics, which score skill quality rather than code'), giving minimal conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

Table of Contents