internal-comms-anthropic

To write internal communications, use this skill for:

Quality

43%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/internal-comms-anthropic/SKILL.md

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

Quality

Content

63%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 well-structured and lean, with a clear identify-load-follow workflow and an explicit fallback. However, it offloads all substantive guidance to `examples/*.md` files that are not present in the bundle, so the skill as shipped provides no actual formatting, tone, or content-gathering instruction.

Suggestions

Ship the referenced `examples/` guideline files (3p-updates.md, company-newsletter.md, faq-answers.md, general-comms.md) so the load-file step has real targets; without them the skill is non-functional.

Add inline minimal formatting/tone guidance for at least the most common type (e.g. the 3P update structure) so the skill is usable even if a guideline file is missed.

Add a short verification step (e.g. confirm the matched type against the request before drafting, or re-check tone/length against the guideline after drafting) to lift workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is lean — a short trigger list, a 3-step procedure, and a fallback line — with no padding or explanations of concepts Claude already knows, matching 'efficient; minor instances of over-explanation that could be trimmed'; not a 5 only because the 'When to use' list duplicates the description's promised content.	4 / 5
Actionability	It gives a concrete file-loading procedure but defers all substantive guidance (formatting, tone, content gathering) to `examples/*.md` files that do not exist in the bundle, leaving the instruction 'Follow the specific instructions in that file' without a target, matching 'some concrete guidance but incomplete; missing key details'.	3 / 5
Workflow Clarity	The sequence (identify type → load guideline file → follow its instructions) is clear and includes an explicit fallback for unmatched types, matching 'clear sequence with most checkpoints present'; this is a non-destructive writing skill so the destructive-operation cap does not apply, but no verification step keeps it from 5.	4 / 5
Progressive Disclosure	Structure and signaling are good — a concise overview pointing one level deep to named files with descriptions — but the referenced `examples/3p-updates.md`, `examples/company-newsletter.md`, `examples/faq-answers.md`, and `examples/general-comms.md` are absent from the bundle, so the navigation links are broken, pulling it down from 4 to 3.	3 / 5
	Total	14 / 20 Passed

Description

23%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 truncated and non-functional: it ends with a colon and defers all substance to the body, listing neither concrete actions nor a 'Use when...' trigger clause. It also uses second-person voice ('use this skill') instead of third person.

Suggestions

Rewrite the description in third person as a complete sentence, e.g. 'Drafts internal communications — 3P updates, company newsletters, FAQ responses, status and leadership updates, incident reports. Use when writing company newsletters, weekly 3P updates, FAQs, or status/leadership updates.'

Add explicit 'Use when...' trigger language with natural user phrases (newsletter, weekly update, 3P update, FAQ, status report) directly in the frontmatter description rather than relying on the body.

Move the bulleted capability list from the body into the description so the frontmatter self-contains both 'what' and 'when'.

Dimension	Reasoning	Score
Specificity	The description 'To write internal communications, use this skill for:' names the domain but lists no concrete actions (no 'write newsletters', 'draft 3P updates', etc.), matching the 'names domain but actions minimal/generic' anchor at 2; reduced by 1 for the second-person 'use this skill' voice to 1.	1 / 5
Completeness	It offers a vague 'what' ('write internal communications') and no 'when'/'Use when...' trigger clause (the trailing colon defers the list to the body), matching the 'vague what and no when' anchor; the missing trigger clause also caps completeness at 3, but this is below that cap.	2 / 5
Trigger Term Quality	Only the single generic phrase 'internal communications' appears; none of the natural terms users say (newsletter, 3P update, status report, FAQ) are in the description, matching the 'one or two generic keywords; missing natural phrases' anchor.	2 / 5
Distinctiveness Conflict Risk	'Internal communications' is a recognizable niche but the description alone is broad enough to overlap with general writing or status-reporting skills, matching 'somewhat specific but could still overlap with similar skills'.	3 / 5
	Total	8 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/internal-comms-anthropic/SKILL.md
Commit: 57c135b

Reviewed: 4 days 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.