research-curator
Manage research entries in ./research/ — create, refresh, and validate. Use when asked to add a tool, "document this", "research this", "refresh this research", "validate research entries", or given a tool URL. Modes: default (single URL), --batch (multiple URLs in parallel), --rerun (refresh stale entries), --validate (structural check and auto-fix).
66
81%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
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 strong skill description that clearly communicates what the skill does (manage research entries with create/refresh/validate operations), when to use it (with explicit trigger phrases), and how it operates (four distinct modes). The description is concise yet comprehensive, uses third-person voice correctly, and provides enough specificity to distinguish it from other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: create, refresh, validate research entries, with explicit modes (single URL, batch multiple URLs, refresh stale entries, structural check and auto-fix). Very concrete and actionable. | 3 / 3 |
Completeness | Clearly answers both 'what' (manage research entries — create, refresh, validate with multiple modes) and 'when' (explicit 'Use when...' clause with specific trigger phrases and scenarios). | 3 / 3 |
Trigger Term Quality | Includes natural trigger phrases users would actually say: 'document this', 'research this', 'refresh this research', 'validate research entries', 'add a tool', and 'tool URL'. Good coverage of natural language variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: managing research entries in a specific directory (./research/), with specific modes and URL-based workflows. Unlikely to conflict with generic documentation or code skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a highly actionable and well-structured orchestration skill with excellent workflow clarity through mermaid diagrams, explicit validation checkpoints, and concrete agent invocation patterns. Its primary weakness is extreme verbosity — the file is far too long, with repetitive patterns across modes (analysis agent spawning, backlink detection, relay rules) that could be consolidated into shared references. The relay rules section, while useful, is over-specified for Claude's capabilities.
Suggestions
Extract the Agent Result Relay Rules and Pre-Relay Quality Checklist into a separate reference file (e.g., ./references/relay-rules.md) and reference it with a one-line summary, reducing ~50 lines to ~3.
Consolidate the repeated analysis-agent spawning pattern (insight-extractor + utilization-assessor + cross-referencer + backlink-detector) into a single shared reference section, since Default, Rerun, and Batch modes all use nearly identical sequences.
Move the detailed Output Format section to a separate reference file — the orchestrator only needs to know the format exists and where to find it, not carry ~60 lines of output templates inline.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at ~400+ lines. It includes extensive relay rules, pre-relay checklists, detailed mermaid diagrams, and repetitive instructions across modes (e.g., the analysis agent spawning pattern is repeated nearly identically in Default, Rerun, and Batch modes). Much of this could be consolidated or referenced. The 'Agent Result Relay Rules' section explains concepts Claude can infer from a compact table. | 1 / 3 |
Actionability | The skill provides highly concrete, executable guidance: exact bash commands for validation/lint/commit/push, specific agent tool parameters with prompt templates, precise mermaid flowcharts for decision routing, and detailed output format templates. Every mode has copy-paste ready invocations and clear parameter specifications. | 3 / 3 |
Workflow Clarity | Multi-step processes are exceptionally well-sequenced with mermaid flowcharts as authoritative procedures, explicit validation checkpoints (pre-relay quality checklist), error handling branches (e.g., 'If agent returns status: failed, relay the exact failure reason and stop'), and feedback loops (validate → fix → re-validate pattern in validate mode). Wave spawning includes concurrency limits and sequential ordering for write-race prevention. | 3 / 3 |
Progressive Disclosure | The skill references external files well (entry-template.md, frontmatter-generation.md, validation-rules.md, batch-mode.md) and delegates to agents appropriately. However, the main SKILL.md itself is monolithic — the relay rules, output formats, and repetitive mode details could be split into references. The inline content is far too long for an orchestrator overview, undermining the progressive disclosure pattern it partially implements. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (628 lines); consider splitting into references/ and linking | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- Jamie-BitFlight/claude_skills
- Commit
4e61312
- 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.