CtrlK
BlogDocsLog inGet started
Tessl Logo

inbox-write

別エージェントのinboxにメッセージを送信する。agent-to-agent通信の唯一の手段。

63

Quality

75%

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 ./.cursor/skills/inbox-write/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

96%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 instruction set with exact commands and concrete examples, well-organized for a simple skill; the only gap is that the referenced scripts/inbox_write.sh is not present in the bundle.

DimensionReasoningScore

Conciseness

The body is lean — a one-line rule, a prohibition, the exact command, a compact type table, and three examples — with no padding and no explanation of concepts Claude already knows, matching 'lean and efficient; every token earns its place'; not 4 because there are no over-explanation instances to trim.

5 / 5

Actionability

Provides the exact executable command with named parameters, a type→purpose table, and three copy-paste-ready examples covering common cases, matching 'fully executable; copy-paste ready; specific examples cover common cases'; not 4 because the guidance is complete rather than having minor gaps.

5 / 5

Workflow Clarity

This is a simple single-task skill whose single action (call the script with the right type) is unambiguous, so the simple-skill exception applies; the destructive/batch cap does not apply since sending one inbox message is neither destructive nor batch; not 4 because no checkpoint is meaningfully missing for a single unambiguous action.

5 / 5

Progressive Disclosure

Content is well-organized into clear sections (使い方, type一覧, 例) with a one-level-deep, clearly signaled reference to scripts/inbox_write.sh, matching 'good structure; references mostly clear; minor organization gaps'; not 5 because the referenced scripts/inbox_write.sh is absent from the bundle, and not 3 because the structure and signaling are genuinely good rather than merely adequate.

4 / 5

Total

19

/

20

Passed

Description

53%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 third-person with a clear, distinct niche, but it states only what the skill does without any 'when to use it' trigger guidance and with limited keyword coverage.

Suggestions

Add a 'Use when...' clause (e.g., 'Use when sending a message to another agent or coordinating agent-to-agent communication') so the 'when' is explicit and completeness can exceed 3.

Include more natural trigger terms and synonyms (e.g., 'notify an agent', 'inter-agent message', 'inbox message') to broaden trigger_term_quality beyond a single phrasing.

Optionally enumerate 1-2 more concrete actions (e.g., assigning tasks, reporting completion) to lift specificity toward listing several specific actions.

DimensionReasoningScore

Specificity

Names the domain (agent-to-agent messaging) and one concrete action ('別エージェントのinboxにメッセージを送信する') but lists only a single action, matching the anchor for 'domain and 1-2 concrete actions, not comprehensive'; it is not 4 because there are not several specific actions, and not 2 because the action is concrete rather than generic.

3 / 5

Completeness

Provides a clear 'what' (sends messages to another agent's inbox, the sole agent-to-agent means) but no 'Use when...' or equivalent trigger guidance, so the missing-'when' cap at 3 applies; not 4 because 'when' is entirely absent rather than just weakly implied.

3 / 5

Trigger Term Quality

Contains some natural phrases a user might say ('メッセージを送信', 'inbox', 'agent-to-agent通信') but misses common variations and synonyms, fitting 'some relevant keywords but missing common variations'; not 4 because keyword coverage is thin rather than good.

3 / 5

Distinctiveness Conflict Risk

'agent-to-agent通信の唯一の手段' carves a clear, distinct niche with minimal conflict risk, matching 'mostly distinct; minor overlap risk'; not 5 because there are no explicit distinct trigger phrases, and not 3 because the 'sole means' framing is more specific than 'somewhat specific but could overlap'.

4 / 5

Total

13

/

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: 4 missing

Warning

Total

15

/

16

Passed

Repository
yohey-w/multi-agent-shogun
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.