CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

mailbox

Load to send, read or resolve repository mailbox messages and owner questions.

Quality

73%

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 ./skills/mailbox/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 minimal SKILL.md: terse, information-dense, honest about optional dependencies and refusal behavior, with clean one-level progression into the script's own --help. The only meaningful gap is actionability — a single example invocation would let the first send/read happen without a discovery step.

Suggestions

Add one or two example invocations for the common cases (e.g. a send and a resolve command line, lifted from the script's usage text) so the body alone can drive a first operation without requiring a --help read.

DimensionReasoningScore

Conciseness

The ~110-word body is lean with zero padding: every sentence carries non-obvious information (entry point, dependency gating, refusal-before-write behavior, system dependencies, writer libraries). It assumes Claude's competence and explains nothing the model already knows. Fits the 'every token earns its place' anchor exactly.

5 / 5

Actionability

A concrete runnable entry point is named ("Use `scripts/lane-mail`" with "Its `--help` defines verbs, envelopes, receipts and refusal keys") and real library paths are cited, but no example invocation appears in the body — verbs and argument syntax are deferred entirely to --help, so key executable details are missing. Not 4 because there is no copy-runnable example of an actual operation; not 2 because a concrete command and its documentation source are explicitly given.

3 / 5

Workflow Clarity

This is a simple script-backed skill whose single action is unambiguous (run `scripts/lane-mail`, consult `--help`), and preconditions for gated operations are stated ("These operations refuse before writing when their required helper is absent"). Not 5 because no sequence or verification guidance is given for the common read-then-respond-then-resolve flow; not 3 because the core action and its failure behavior are explicit.

4 / 5

Progressive Disclosure

The body is a minimal overview with a well-signaled, one-level-deep reference into `scripts/lane-mail --help` for the detailed interface, and all referenced paths (`scripts/lane-mail`, `scripts/lib/file-lock.sh`, `scripts/lib/mailbox-append.sh`) exist in the bundle. At 7 lines with no external references needed, this matches the well-organized-simple-skill ideal.

5 / 5

Total

17

/

20

Passed

Description

58%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, in third person, and states concrete actions on a distinct domain, but it lacks an explicit trigger ('Use when...') clause and misses natural keyword variations. It sits solidly above the vague-baseline examples but below the exemplar descriptions that combine full capability coverage with explicit triggers.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to send, read or resolve repository mailbox messages, answer owner questions, or handle notices and directives."

Include the missing natural synonyms from the skill's own vocabulary (notices, answers, directives, inbox) so users' phrasings match the description.

Drop the "Load to" preamble in favor of a direct third-person verb phrase ("Sends, reads and resolves...") to make the capability statement unambiguous.

DimensionReasoningScore

Specificity

Names the domain ("repository mailbox messages and owner questions") and three concrete actions ("send, read or resolve"), matching the anchor for several specific actions with minor gaps. Not 3 because more than 1-2 actions are listed; not 5 because core operations the skill covers (notices, answers, directives) are omitted.

4 / 5

Completeness

The 'what' is clear (send, read or resolve repository mailbox messages and owner questions), but there is no explicit 'Use when...' clause — the trigger is only weakly implied by "Load to", which caps completeness at 3 per the judging guidelines. Not 4 because the when-guidance is not explicit.

3 / 5

Trigger Term Quality

"mailbox", "messages" and "owner questions" are natural terms, but common variations users would say — inbox, notices, answers, replies — are absent. Fits 'some relevant keywords but missing common variations'; not 4 because keyword coverage beyond the mailbox noun itself is thin.

3 / 5

Distinctiveness Conflict Risk

"repository mailbox" and "owner questions" carve a clear niche with minor overlap risk against sibling messaging/issue-tracking skills. Not 5 because "messages" alone is generic and could collide with other communication-oriented skills.

4 / 5

Total

14

/

20

Passed

Validation

81%

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

Validation — 13 / 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

referenced_paths_exist

Referenced path issues: 2 deeper-than-1-level

Warning

Total

13

/

16

Passed

Repository

vanillagreencom/kendex

Path

skills/mailbox/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.