CtrlK
BlogDocsLog inGet started
Tessl Logo

internal-comms-anthropic

To write internal communications, use this skill for:

50

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

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

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 compact, well-organized router that delegates substantive guidance to example files with clear signaling and a sensible fallback. Its main weaknesses are implicit routing for several listed communication types and the absence of the referenced example files from the bundle.

Suggestions

Add an explicit mapping for status reports, leadership updates, project updates, and incident reports (e.g., state they route to `examples/general-comms.md`) rather than relying on the "anything else" catch-all.

Ship the four referenced `examples/*.md` guideline files — they are missing from the bundle, so the skill's core instructions are currently unreachable.

Remove the body's opening line (a verbatim repeat of the description) and fold the Keywords section into the frontmatter description to trim redundancy.

DimensionReasoningScore

Conciseness

The ~27-line body is lean, assumes Claude's competence, and explains nothing Claude already knows. Minor trim opportunities keep it from anchor 5: the opening line restates the description verbatim, and the "Keywords" section duplicates the "When to use" list in a spot that adds little for execution.

4 / 5

Actionability

The routing is concrete and executable: named files ("examples/3p-updates.md", "examples/company-newsletter.md", etc.) each mapped to a communication type, plus a defined fallback ("ask for clarification"). It falls short of anchor 5 because no inline example or format guidance exists — all substantive instruction is deferred to the example files.

4 / 5

Workflow Clarity

The three-step sequence (identify type → load guideline file → follow its instructions) with a fallback is clear and coherent, and no validation is needed for this non-destructive task. It misses anchor 5 because four of the seven listed use cases (status reports, leadership updates, project updates, incident reports) have no explicit file mapping — the reader must infer the general-comms.md catch-all.

4 / 5

Progressive Disclosure

The structure is textbook progressive disclosure: clear sections, one-level-deep references each labeled with its purpose, matching the anchor-5 shape. However, scoring against the actual bundle, none of the four referenced `examples/*.md` files exist in the skill directory, so the well-signaled navigation dead-ends — a gap that keeps it at anchor 4.

4 / 5

Total

16

/

20

Passed

Description

36%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 names its domain but is functionally truncated: the promised list after "use this skill for:" never appears, leaving no concrete capabilities, no trigger conditions, and only one keyword. It reads as an unfinished sentence rather than a complete description.

Suggestions

Complete the sentence by listing the concrete communication types in the description itself (e.g., "3P updates, company newsletters, FAQ responses, status reports, leadership updates, incident reports") instead of ending at a colon.

Add an explicit trigger clause such as "Use when the user asks for internal comms, team updates, weekly status reports, or company newsletters."

Include natural synonyms users would actually say — "internal comms", "weekly update", "team update" — to improve trigger term coverage.

DimensionReasoningScore

Specificity

The description is "To write internal communications, use this skill for:" — it names the domain but offers only the single generic action "write" and then truncates with nothing after the colon. This matches anchor 2 ("Names the domain but actions are minimal or generic", e.g. "Processes PDF files") and lacks the 1-2 concrete actions needed for anchor 3.

2 / 5

Completeness

The "what" is thin — it never says which communication types it covers because the sentence ends at "for:" — and there is no "when"/trigger clause at all ("use this skill for:" is not an explicit use-when condition). This fits anchor 2 (vague what, no when); anchor 3 would require a clearly specified set of concrete actions.

2 / 5

Trigger Term Quality

The only natural keyword is "internal communications", which is the core phrase a user might say, but common variations and synonyms ("internal comms", "newsletter", "weekly update", "3P update") are entirely absent. It has some relevance beyond anchor 2's generic keywords but not the coverage of anchor 4.

3 / 5

Distinctiveness Conflict Risk

"Internal communications" is a recognizable niche, but with no named communication types, actions, or distinguishing triggers, the description could plausibly be claimed by generic business-writing or document skills. Anchor 4 would require more distinct trigger surface than a bare domain name provides.

3 / 5

Total

10

/

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
administrakt0r/AI-Agents-Safe-Coding-Skills
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.