count-registry
Provides canonical entity counts from count-manifest.json. Use when agents need to reference how many agents, skills, instructions, or validators exist. Prevents hard-coded counts. WHEN: agent count, skill count, how many agents, how many skills, entity inventory, project statistics.
90
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted skill description that clearly communicates its purpose, provides specific concrete actions, and includes an explicit WHEN clause with natural trigger terms. It covers a narrow, well-defined niche making it highly distinguishable from other skills. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists specific concrete actions: provides canonical entity counts from a specific file (count-manifest.json), references specific entity types (agents, skills, instructions, validators), and states a clear purpose (prevents hard-coded counts). | 3 / 3 |
Completeness | Clearly answers both 'what' (provides canonical entity counts from count-manifest.json, prevents hard-coded counts) and 'when' (explicit WHEN clause with multiple trigger scenarios like agent count, skill count, how many agents). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'agent count', 'skill count', 'how many agents', 'how many skills', 'entity inventory', 'project statistics' — these are phrases users would naturally say when needing this information. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — it targets a very specific niche (entity counts from a manifest file) with unique trigger terms like 'count-manifest.json', 'entity inventory', and 'how many agents/skills'. Unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, concise skill that clearly defines the single source of truth for entity counts and provides actionable phrasing patterns. Its main weakness is the lack of a concrete example showing the manifest's JSON structure or a command to read it, which would make the guidance more immediately actionable. The canonical phrasing table is a strong, practical addition.
Suggestions
Add a brief inline example of count-manifest.json's structure (2-3 lines) so Claude knows the schema without needing to read the file first.
Include a concrete command or code snippet for reading a count from the manifest (e.g., `cat tools/registry/count-manifest.json | jq '.agents.value'`).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. Every section serves a clear purpose—source of truth location, referencing rules, canonical phrasing patterns, and computed entity explanation. No unnecessary explanations of concepts Claude already knows. | 3 / 3 |
Actionability | The skill provides clear rules (prefer descriptive language, read the manifest, never hard-code) and a useful phrasing table, but lacks a concrete executable example of reading count-manifest.json (e.g., a code snippet or shell command to extract a value). The guidance is specific but not fully copy-paste ready. | 2 / 3 |
Workflow Clarity | This is a simple, single-purpose skill with a clear 3-step priority sequence for referencing counts (prefer descriptive → read manifest → never hard-code). The workflow is unambiguous and the single task is clearly defined. Validation is handled by the referenced validator. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and a useful table, but it references tools/registry/count-manifest.json and validate-no-hardcoded-counts.mjs without linking to them or providing a brief example of the manifest's structure. A small inline example of the JSON schema or a link would improve navigation. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- jonathan-vella/azure-agentic-infraops
- Commit
ec7b8ff
- 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.