CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-protocol

Inter-agent communication protocol for C-suite agent teams. Defines invocation syntax, loop prevention, isolation rules, and response formats. Use when C-suite agents need to query each other, coordinate cross-functional analysis, or run board meetings with multiple agent roles.

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 ./.gemini/skills/agent-protocol/SKILL.md

The canonical home for this skill is agent-protocol in alirezarezvani/claude-skills

SKILL.md
Quality
Evals
Security

Quality

Content

70%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 highly actionable and workflow-clarity is excellent, with concrete protocol templates and a well-sequenced verification loop. Its weaknesses are conciseness (redundant Quick Reference and verbose templates) and progressive disclosure (inlined long sections plus a missing referenced file).

Suggestions

Create references/invocation-patterns.md (or remove the dangling reference) so the 'Reference' section points to a file that actually exists.

Remove the 'Quick Reference' table since it restates the Loop Prevention hard rules already detailed in their own section, or fold it into that section instead of duplicating.

Move the long output templates (Standard Output, Proactive Alert, Board Meeting Output) into a references file linked from a short 'User Communication Standard' overview to reduce inlined bulk.

DimensionReasoningScore

Conciseness

The ~440-line body is mostly dense directive content that assumes Claude's knowledge, but it has real redundancy and trimming opportunities — the 'Quick Reference' table restates the Loop Prevention hard rules already detailed above, and the Communication Standard section packs in three large output templates — putting it at 'mostly efficient but could be tightened' rather than clearly lean.

3 / 5

Actionability

It provides concrete, copy-paste-ready protocol templates with filled examples — exact '[INVOKE:role|question]' syntax, '[RESPONSE:role]' blocks, and a complete CFO burn-rate example — giving mostly executable guidance; it stops short of a 5 only because these are templates/placeholders rather than literal runnable code.

4 / 5

Workflow Clarity

The Internal Quality Loop is a clearly sequenced multi-step process (Steps 1-4) with explicit validation checkpoints — the SELF-VERIFY checklist, the recommendation→validator peer-verify table, the critic pre-screen triggers, and the founder feedback loop with 30/60/90 review — matching the anchor for clear sequence, feedback loops, and checklists.

5 / 5

Progressive Disclosure

Section organization is present, but everything is inlined in one ~440-line file, large blocks like the Quality Loop and Communication Standard templates could reasonably live in separate files, and the one external reference ('references/invocation-patterns.md') is a dangling path — the referenced file does not exist — so it lands at 'some structure but inlined content and a non-functional reference'.

3 / 5

Total

15

/

20

Passed

Description

87%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 strong: it clearly states what the protocol does and when to use it, with concrete capability lists and distinct C-suite orchestration triggers. The only minor gap is that not every protocol feature (broadcast, conflict resolution) is enumerated in the description.

DimensionReasoningScore

Specificity

The description names the domain plus several concrete capabilities — 'Defines invocation syntax, loop prevention, isolation rules, and response formats' — matching the anchor listing several specific actions with minor gaps, but it omits other protocol features (broadcast, conflict resolution) so it is not comprehensive enough for a 5.

4 / 5

Completeness

It explicitly answers both 'what' ('Inter-agent communication protocol... Defines invocation syntax, loop prevention, isolation rules, and response formats') and 'when' ('Use when C-suite agents need to query each other, coordinate cross-functional analysis, or run board meetings...') with concrete trigger phrases, matching the top anchor exactly.

5 / 5

Trigger Term Quality

It includes natural phrases a user would plausibly say — 'query each other', 'coordinate cross-functional analysis', 'run board meetings with multiple agent roles' — giving good keyword coverage, though synonym/extension coverage is not exhaustive enough for a 5.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche (C-suite inter-agent orchestration) with distinct triggers ('C-suite agents', 'board meetings', 'inter-agent communication') and minimal overlap risk with other skills.

5 / 5

Total

18

/

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

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
alirezarezvani/claude-skills
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.