CtrlK
BlogDocsLog inGet started
Tessl Logo

internal-comms

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

81

1.58x
Quality

74%

Does it follow best practices?

Impact

95%

1.58x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/all-skills/skills/internal-comms/SKILL.md

The canonical home for this skill is internal-comms in anthropics/skills

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.

A well-structured router skill: the body stays lean, delegates detail to clearly-labeled example files, and gives unambiguous routing for the common cases. Its main flaws are redundancy (the type list and keywords repeat the description) and an internal contradiction between the general-comms.md catch-all and the instruction to ask for clarification when no guideline matches.

Suggestions

Resolve the routing contradiction: either make general-comms.md the explicit final fallback ("If nothing matches, load examples/general-comms.md") or scope it to specific cases and keep "ask for clarification" as the true fallback.

Cut the duplicated content — the "When to use" bullet list and the "Keywords" line restate the frontmatter description; keep one or fold the keywords into the description's trigger terms.

Since no examples/ bundle was present for review, verify that all four referenced files actually ship with the skill — a router whose targets are missing fails completely at runtime.

DimensionReasoningScore

Conciseness

The body is lean with no over-explanation of concepts Claude already knows, but the communication-type list is stated twice within the body ("When to use this skill" bullets and the "Keywords" line) and both largely duplicate the frontmatter description. That redundancy keeps it below the "every token earns its place" anchor.

4 / 5

Actionability

Concrete, actionable guidance: each communication type maps to a specific file to load ("examples/3p-updates.md - For Progress/Plans/Problems team updates", etc.) with a fallback behavior. It is not a 5 because the fallback contradicts itself — "general-comms.md - For anything else that doesn't explicitly match" coexists with "If the communication type doesn't match any existing guideline, ask for clarification", leaving the agent unsure which rule wins.

4 / 5

Workflow Clarity

The three-step sequence (identify type, load the matching guideline file, follow its instructions) is clearly ordered with a stated fallback, and no validation steps are needed for a non-destructive writing task. The same general-comms vs. ask-for-clarification contradiction introduces a genuine ambiguity in the routing logic, preventing a 5.

4 / 5

Progressive Disclosure

The body is a clean overview that routes to four well-signaled, one-level-deep references in `examples/`, each annotated with its purpose (3p-updates, company-newsletter, faq-answers, general-comms), with no detail inlined that belongs in those files. No bundle files were present in the review workspace to verify the referenced paths, so this is scored on the reference structure as written.

5 / 5

Total

17

/

20

Passed

Description

70%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 solid description with an explicit use-when clause and good coverage of concrete communication types, though written in first person ("help me write", "my company"), which costs it specificity and reads oddly for a Claude-facing trigger. The "what" is softened by the vague phrase "A set of resources". Trigger terms are natural but lack common synonyms.

Suggestions

Rewrite in third person and name the resources concretely, e.g. "Format guidelines and templates for writing internal communications (3P updates, newsletters, status reports, incident reports)."

Add natural trigger synonyms such as "weekly update", "internal comms", and "memo" to the use-when clause so it matches how users actually phrase these requests.

Drop "A set of resources to help me" — state directly what the skill provides so the "what" is as crisp as the "when".

DimensionReasoningScore

Specificity

The description enumerates seven concrete communication types ("status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates"), which on its own matches the anchor for listing several specific items, but the mandatory first-person penalty ("help me write", "my company likes to use") reduces it by one. It is not a 2 because it goes well beyond naming the domain — it lists concrete deliverable types.

3 / 5

Completeness

Both elements are present: an explicit "when" ("Claude should use this skill whenever asked to write some sort of internal communications") with concrete triggers, and a "what" ("write all kinds of internal communications, using the formats that my company likes to use"). It is not a 5 because the "what" is vague — "A set of resources" never states what the resources are (format guidelines, templates).

4 / 5

Trigger Term Quality

The "use this skill whenever asked to write" clause lists natural phrases users would say ("status reports", "company newsletters", "FAQs", "incident reports", "3P updates"), giving good keyword coverage. It falls short of 5 because common synonyms and variations ("weekly update", "internal comms", "memo", "leadership brief") are absent from the description itself.

4 / 5

Distinctiveness Conflict Risk

"Internal communications" is a clear niche with distinct triggers (3P updates, company newsletters, incident reports), making it mostly distinguishable from general writing or document skills. Minor overlap risk remains with generic terms like "FAQs" and "project updates" that could match other writing skills, so it does not reach 5.

4 / 5

Total

15

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
davepoon/buildwithclaude
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.