CtrlK
BlogDocsLog inGet started
Tessl Logo

slack-announcement

Produce a themed Slack post announcing Ark releases. Pulls from BOTH the Ark core repo (mckinsey/agents-at-scale-ark) and the Marketplace repo (mckinsey/agents-at-scale-marketplace), validates docs links, groups features by theme with relevant emoji, and ends with a "Coming next" section sourced from the current sprint on the ARK project board. Invoke when the user asks for a "release announcement", "slack post", "what's new since vX", "changelog for

76

Quality

96%

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

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.

A highly actionable, well-sequenced operational skill with executable commands and robust validation loops. The main weaknesses are mild redundancy between the process steps, 'Do NOT', and the final checklist, and the absence of any progressive disclosure for a skill of this length.

Suggestions

Move the docs URL mapping tables (steps 3b) and the GraphQL sprint queries (step 8) into a references/ file, keeping SKILL.md as a lean overview with clearly signaled one-level-deep links.

Consolidate the ops/CI filter list, which currently appears in step 2, the 'Do NOT' section, and the sanity checklist, into a single authoritative location referenced from the other two.

Trim the duplicated bullet-format examples in step 5 (the plain-bullet example repeats a bullet already shown in the heading-with-link example).

DimensionReasoningScore

Conciseness

The body is dense with non-obvious operational knowledge (URL mapping rules, SPA curl-404 behavior, link blocklist) and mostly avoids explaining things Claude already knows. However, the 'Pre-delivery sanity check' checklist and the 'Do NOT' section substantially restate rules already stated in the process steps (e.g., the ops filter appears three times), which could be trimmed.

4 / 5

Actionability

Fully executable throughout: copy-paste-ready gh CLI and GraphQL commands with jq filters, concrete file-path-to-URL mapping tables, exact bullet/heading formats, and worked examples covering the common cases. Commands are complete, not pseudocode.

5 / 5

Workflow Clarity

Steps 1–9 are clearly sequenced with explicit validation checkpoints (source-file existence check as primary link validation, curl as secondary, fallback order 3a–3f, blocklist) and a pre-delivery checklist. Error paths are handled (PR touches no docs, no breaking changes) with concrete recovery guidance.

5 / 5

Progressive Disclosure

Sections are well-organized, but the entire 294-line skill is a single inline file with no bundle files at all; content that would fit a one-level-deep reference (the docs URL mapping tables, the GraphQL sprint queries, the bullet-format examples) is inlined in SKILL.md.

3 / 5

Total

17

/

20

Passed

Description

100%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 exemplary: third-person voice, concrete multi-action capability list, named repositories, and an explicit trigger clause with natural user phrasings. It clearly matches the top anchors on every dimension.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Pulls from BOTH the Ark core repo (mckinsey/agents-at-scale-ark) and the Marketplace repo', 'validates docs links', 'groups features by theme with relevant emoji', and 'ends with a "Coming next" section sourced from the current sprint' — comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both 'what' (produce a themed Slack post from both repos with validated links and themed grouping) and 'when' via a concrete 'Invoke when the user asks for…' clause with multiple trigger phrases.

5 / 5

Trigger Term Quality

Natural trigger phrases with good variation: 'release announcement', 'slack post', 'what's new since vX', 'changelog for #channel', plus 'or similar' for coverage — these are exactly what a user would say when they need this skill.

5 / 5

Distinctiveness Conflict Risk

A clear niche (Ark release announcements in Slack) with named repos and distinct triggers; minimal overlap risk with other skills.

5 / 5

Total

20

/

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

relative_links

Relative link issues: 3 missing, 3 suspicious

Warning

Total

15

/

16

Passed

Repository
mckinsey/agents-at-scale-ark
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.