CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

communication

Load before writing a message to a person: a reply, report, briefing, decision request, or work-item description or comment.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

An exemplary lean router skill: minimal token footprint, concrete read conditions, a clean task-to-reference table, and a real one-level bundle whose files all exist and hold the actual guidance. The only weakness is mild over-compression in the scope sentence, which borders on cryptic.

DimensionReasoningScore

Conciseness

The ~29-line body is lean and assumes Claude's competence: scope in two sentences, a compact reading-routes table, and two copy-paste install snippets. The revision-tracking rule is novel skill-specific semantics rather than explanation of known concepts, so every token earns its place.

5 / 5

Actionability

Concrete, executable routing: exact file paths in a task-to-reference table ("Request a decision or action → questions.md"), explicit read conditions, and copy-paste install lines. It falls short of fully actionable because the compressed sentence "Agent-to-agent messages, literal return formats, tool prompts, documentation and text sent as the user follow their own owners" requires interpretation, and the actual message-writing guidance is deferred to the references.

4 / 5

Workflow Clarity

This is a simple single-purpose routing skill and its one action is unambiguous: read SKILL.md and messages.md once per revision, add the task-specific reference from the table, apply to every message, with explicit conditions for when to re-read. There are no destructive or batch operations, so no validation cap applies.

5 / 5

Progressive Disclosure

The body is a clear overview with well-signaled one-level-deep references: all four referenced files (messages.md, questions.md, reports.md, voice.md) exist in the bundle with real content, and the task-to-file table makes navigation trivial. Cross-references between reference files (e.g., reports.md → messages.md anchors) link real content at the same level rather than nesting deeper.

5 / 5

Total

19

/

20

Passed

Description

75%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 description with an explicit trigger clause and a concrete enumeration of message types, all in third person with no fluff. Its main weaknesses are the unstated capability (what the skill does to messages) and missing natural synonyms such as email, chat, or spoken replies.

DimensionReasoningScore

Specificity

The description enumerates six concrete message types ("a reply, report, briefing, decision request, or work-item description or comment") rather than vague filler, but omits spoken/voice replies that the skill's own summary covers, leaving minor gaps in coverage. It is above anchor 3 (which expects only 1-2 concrete actions) but not fully comprehensive.

4 / 5

Completeness

The 'when' is explicit ("Load before writing a message to a person: a reply, report, briefing, decision request..."), satisfying the trigger-guidance requirement. However, the 'what' is implicit — it never states what the skill actually does with those messages (e.g., plain-language structure, reader modes), so it does not clearly answer both questions at anchor 5.

4 / 5

Trigger Term Quality

It uses natural phrases people actually say — "reply", "report", "briefing", "decision request", "comment" — matching how users would describe the task. A few natural terms are missing (e.g., email, chat message, spoken reply), so it falls just short of the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The scope is clearly limited to person-directed messages of enumerated types, giving it a distinct niche with well-differentiated triggers. There remains minor overlap risk with other general writing or documentation skills, keeping it below anchor 5.

4 / 5

Total

16

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

Repository

vanillagreencom/kendex

Path

skills/communication/SKILL.md

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.