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.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

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.

A highly actionable protocol spec with excellent workflow sequencing and validation checkpoints, but it is long for a SKILL.md and keeps substantial detailed material (output templates, the quality loop) inline rather than offloading it to reference files.

Suggestions

Move the User Communication Standard output templates (standard, proactive alert, board meeting) into a references/ file and keep only the rule summary inline, reducing SKILL.md length and the conciseness penalty.

Extract the 4-step Internal Quality Loop (self-verify checklist, peer-verification table, critic pre-screen, course correction) into its own reference file, leaving a brief overview and stakes table in SKILL.md.

Remove the Quick Reference recap table and the in-body 'When to Invoke vs When to Assume' section, since both duplicate rules already stated above and the latter is fully covered in references/invocation-patterns.md.

Dimension	Reasoning	Score
Conciseness	The body is competent and avoids explaining concepts Claude already knows, but at ~451 lines it carries redundancy — the Quick Reference table recapitulates the loop-prevention rules, and the 'When to Invoke vs When to Assume' guidance is duplicated in references/invocation-patterns.md — so it could be tightened rather than being merely minor over-explanation (4).	3 / 5
Actionability	Every protocol construct ships as a copy-paste-ready template with a fully filled worked example — [INVOKE], [RESPONSE] with the CFO hiring example, [BLOCKED], [ASSUMPTION], [CONFLICT], [BROADCAST], [PEER-VERIFY], [CRITIC-SCREEN] — covering the common cases concretely.	5 / 5
Workflow Clarity	Multi-step processes are explicitly sequenced with validation checkpoints and feedback loops: the 4-step Internal Quality Loop, the SELF-VERIFY CHECKLIST with explicit gates ('If >50% ASSUMED → flag low confidence', 'Only proceed when validation passes'), the founder feedback loop with re-verify, and the Verification Level by Stakes table.	5 / 5
Progressive Disclosure	Headers and the single clearly-signaled, one-level-deep reference (references/invocation-patterns.md) give good navigation, but large detailed blocks — the User Communication Standard templates and the 4-step quality loop with its tables — are inlined in SKILL.md rather than split into reference files, fitting the 'content that should be separate is inline' anchor.	3 / 5
	Total	16 / 20 Passed

Description

83%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, well-structured description that clearly states both what the skill does and when to use it, with concrete capabilities and natural trigger phrases. Its only soft spot is minor overlap with sibling C-suite orchestration skills on the 'board meetings' trigger.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities — 'invocation syntax, loop prevention, isolation rules, and response formats' — naming the domain and four specific actions, matching the 'several specific actions; minor gaps' anchor rather than the 1-2 actions of a 3 or the maximally atomic comprehensive list of a 5.	4 / 5
Completeness	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, mirroring the anchor-5 example pattern.	5 / 5
Trigger Term Quality	The 'Use when' clause supplies natural phrases a user would say — 'query each other', 'coordinate cross-functional analysis', 'run board meetings with multiple agent roles' — giving good coverage, though a few common synonyms are missing so it stops short of comprehensive.	4 / 5
Distinctiveness Conflict Risk	The 'inter-agent communication protocol for C-suite agent teams' niche is mostly distinct with minimal conflict risk, but the 'run board meetings' trigger overlaps closely related C-suite orchestration skills (board-meeting, chief-of-staff), so it is not a clean 5.	4 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: alirezarezvani/claude-skills
Path: c-level-advisor/skills/agent-protocol/SKILL.md
Commit: 19392f7

Reviewed: ~24 hours ago

Table of Contents

Discovery Implementation Validation

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.