CtrlK
BlogDocsLog inGet started
Tessl Logo

reviewer-protocol

Reviewer rejection workflow and strict lockout semantics

55

Quality

63%

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 ./.copilot/skills/reviewer-protocol/SKILL.md

The canonical home for this skill is reviewer-protocol in FritzAndFriends/BlazorWebFormsComponents

SKILL.md
Quality
Evals
Security

Quality

Content

77%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 content is a well-structured, actionable policy skill with explicit validation checkpoints, feedback loops for deadlock, and a checklist of anti-patterns; its main weakness is redundancy between the rules, examples, and anti-patterns that could be tightened.

Suggestions

Collapse the Anti-Patterns list or cross-reference the rules instead of restating them, since most anti-patterns duplicate rules 1-7 verbatim.

Trim Examples 1-4 to remove mechanics already specified in the Patterns section, keeping only the illustrative dialogue that adds new information.

Consider a one-line 'When to apply' pointer at the top of the body to compensate for the description's missing trigger guidance.

DimensionReasoningScore

Conciseness

The body is mostly efficient but the Anti-Patterns section largely restates the seven lockout rules (e.g. rule 3 vs. 'Skipping verification...' and 'Accepting the Reviewer's assignment...'), and the four examples restate the same mechanics, so it could be tightened — matching the score-3 anchor.

3 / 5

Actionability

Guidance is concrete and prescriptive with imperative rules ('Coordinator MUST verify... NOT the original author', 'MUST refuse and ask the Reviewer to name a different agent') plus four worked examples covering reassign, escalate, deadlock, and accidental naming; it is not 5 because, as policy text, it lacks the fully copy-paste-ready specificity of the score-5 anchor.

4 / 5

Workflow Clarity

Sequences are explicitly numbered in the examples, rule 3 is an explicit pre-spawn validation checkpoint, rule 7 plus Example 3 form a deadlock escalation/feedback loop, and the Anti-Patterns list acts as a checklist — matching the score-5 anchor with explicit validation steps and feedback loops.

5 / 5

Progressive Disclosure

No bundle files exist (references/scripts/assets absent) and none are needed; the body is self-contained and well-organized into Context, Patterns, Examples, and Anti-Patterns sections with clear headers, which per the simple-skill guidance earns a 5 for well-organized structure.

5 / 5

Total

17

/

20

Passed

Description

48%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 concise and names a clear, distinct niche, but it is a noun-phrase label rather than an action-oriented statement and omits any 'Use when...' trigger guidance, which caps completeness at 3.

Suggestions

Rewrite the description in third-person action voice listing concrete behaviors, e.g. 'Enforces reviewer rejection and lockout rules: reassigns rejected artifacts to a different agent, escalates to a new expert, and refuses self-revision by the original author.'

Add an explicit 'Use when...' clause naming natural trigger phrases such as 'when a reviewer rejects an artifact', 'reassign after rejection', or 'enforce author lockout'.

Include common synonyms/variants ('reject', 'approve', 'reassign', 'escalate', 'deadlock') to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

The phrase 'Reviewer rejection workflow and strict lockout semantics' names the domain and two sub-concepts but lists no concrete actions (verbs), matching the score-2 anchor 'Names the domain but actions are minimal or generic' rather than the score-3 anchor which requires 1-2 concrete actions.

2 / 5

Completeness

It states a clear 'what' (reviewer rejection workflow and lockout semantics) but provides no 'Use when...' trigger guidance, so per the rubric cap it cannot exceed 3; it is not 4 because the 'when' is entirely absent rather than merely implicit.

3 / 5

Trigger Term Quality

'Reviewer', 'rejection', and 'lockout' are relevant keywords an orchestrator might naturally say, but common variations/synonyms (e.g. 'reject', 'approve', 'reassign', 'escalate') are missing, fitting the score-3 anchor 'Some relevant keywords but missing common variations or synonyms'.

3 / 5

Distinctiveness Conflict Risk

The niche (reviewer rejection + lockout enforcement) is clearly distinct from most skills with only minor overlap risk against general orchestration/review skills, matching the score-4 anchor; it is not 5 because the terse description does not articulate distinct trigger phrases.

4 / 5

Total

12

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
microsoft/waza
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.