CtrlK
BlogDocsLog inGet started
Tessl Logo

tessl/code-review-setup

Install Tessl Code Review into a GitHub repository. Inspects the repository's existing workflows and any Code Review caller already present, asks the two setup questions (when reviews run, and whether findings block the merge), then writes or updates a thin caller workflow that invokes the Tessl Code Review Action. 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 asks to switch it between advisory and gate mode.

94

1.40x
Quality

92%

Does it follow best practices?

Impact

97%

1.40x

Average score across 5 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

Overview
Quality
Evals
Security
Files

Quality

Content

85%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.

Well-structured procedural content with a clear phased workflow, explicit validation checkpoints, and clean one-level-deep progressive disclosure. Slight verbosity in a few editorial passages and reliance on the templates reference for the actual workflow YAML keep actionability and conciseness at 4 rather than 5.

Suggestions

Tighten the 'The Action repository' editorial paragraph ('This is the only place that name is decided; it is written in several. Everywhere else in this skill...') to a sentence or two — the maintenance instruction can be stated more directly.

Consider inlining a minimal skeleton of the caller workflow YAML in the Write phase so the core deliverable is copy-paste ready without first opening workflow-templates.md, or more explicitly label that reference as required reading before phase 4.

The 'Who may request a round' paragraph runs long; condense the policy rationale and alternatives into a tighter block, deferring the full trade-off detail to the workflow-templates reference.

DimensionReasoningScore

Conciseness

Mostly efficient and assumes Claude's competence (no explanation of what a GitHub Action is), with product-specific prose that earns its place; a few editorial passages such as 'This is the only place that name is decided; it is written in several' could be trimmed.

4 / 5

Actionability

Provides concrete, executable commands (the gh api SHA-resolution calls, the yaml.safe_load validation one-liner, 'gh secret list') and specific per-phase guidance, but the core deliverable workflow YAML lives in the templates reference rather than inline, leaving a minor gap.

4 / 5

Workflow Clarity

Six explicitly sequenced phases with an approval checkpoint ('Do not write any file before phase 4', 'Do not proceed on silence or on a vague reply'), a dedicated Verify phase with a 6-item checklist, and feedback loops (SHA resolution with 'stop and ask' on failure) — matching the checklist-and-validation anchor.

5 / 5

Progressive Disclosure

A clear overview body points to four real, one-level-deep references (interview.md, workflow-templates.md, operations.md, file-profiles.md, all verified present), each signaled with a markdown link at the exact step it is needed and scoped with guidance like 'Do not paste that file wholesale.'

5 / 5

Total

18

/

20

Passed

Description

96%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.

A strong, specific description that clearly states what the skill does and when to use it, with rich natural-language trigger terms. The only soft spot is mild conflict risk from the broad 'AI code review' phrasing, which slightly overlaps generic review skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Install or update', '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', 'only writes after explicit approval' — giving comprehensive coverage.

5 / 5

Completeness

Explicitly answers both what ('Install or update Tessl Code Review ... by writing a thin caller workflow that invokes the Tessl Code Review Action') and when, with concrete trigger phrases in a clearly demarcated 'Use when...' clause.

5 / 5

Trigger Term Quality

The 'Use when someone wants to add, set up, enable, configure, update, or remove Tessl Code Review, AI code review, or automated pull-request review ... or wants to switch it between advisory and gate mode' clause covers many natural synonyms and phrasings a user would actually say.

5 / 5

Distinctiveness Conflict Risk

The product-specific triggers ('Tessl Code Review', 'advisory and gate mode') are distinct, but the broader secondary triggers ('AI code review', 'automated pull-request review') create minor overlap risk with generic code-review skills, keeping it just below a 5.

4 / 5

Total

19

/

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