CtrlK
BlogDocsLog inGet started
Tessl Logo

open-code-review-delegate

Delegation mode for open-code-review (OCR). Instead of OCR calling an LLM endpoint, this skill instructs the host agent to perform the code review itself, using OCR only for deterministic engineering: file selection and rule resolution. Use when the host agent should drive the review with its own LLM capabilities.

65

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/open-code-review/skills/open-code-review-delegate/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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, highly actionable delegation guide with concrete commands, a well-sequenced workflow, and explicit validation plus error-recovery loops. Structure is good; the only lever is offloading some long edge-case prose into a reference file.

DimensionReasoningScore

Conciseness

Largely efficient: terse command tables, flag tables, and short gotchas assume Claude's competence, with only minor padding such as the mirroring note and slightly verbose background-context recovery prose.

4 / 5

Actionability

Fully executable throughout — concrete `ocr delegate preview --format json`, `git diff <merge_base>..<to>`, and `git show` commands plus complete flag and output-field tables that cover the common cases copy-paste ready.

5 / 5

Workflow Clarity

A clear 7-step sequence with explicit validation checkpoints (mandatory coverage of every reviewable file, marked reviewed/skipped with reason) and error-recovery feedback loops (oversized background context, CLI version incompatibility).

5 / 5

Progressive Disclosure

Well-organized into clear sections (Workflow, Sub-commands, Shared Flags, Gotchas, troubleshooting) with no nested references, though some edge-case material (background-context recovery, version troubleshooting) is inlined where a separate reference file could keep the overview leaner.

4 / 5

Total

18

/

20

Passed

Description

67%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 clearly defines a distinct delegation-mode niche and answers both what and when, using correct third-person voice. Its main weakness is trigger phrasing that is more technical than conversational, which limits natural keyword coverage.

Suggestions

Add user-facing trigger phrases such as 'review my code', 'review a pull request', or 'review a diff' alongside the technical 'delegation mode' wording.

Soften jargon like 'LLM endpoint' and 'deterministic engineering' in favor of terms a user would actually say when requesting a review.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions — host agent 'perform the code review itself', OCR does 'file selection and rule resolution' — giving a clear division of labor with only minor coverage gaps.

4 / 5

Completeness

Explicitly states both what the skill does (host performs review, OCR handles deterministic engineering) and when to use it ('Use when the host agent should drive the review...'), though the trigger is phrased technically rather than in user-facing terms.

4 / 5

Trigger Term Quality

Includes the natural term 'code review' but leans on technical jargon ('delegation mode', 'OCR', 'LLM endpoint') and omits common user phrasings like 'review my changes', 'PR review', or 'review a diff'.

3 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (LLM-free delegation mode for OCR) with distinct triggers; the main overlap risk is only with its sibling canonical OCR skill, not with unrelated skills.

4 / 5

Total

15

/

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.

Repository
alibaba/open-code-review
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.