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).
87
85%
Does it follow best practices?
Impact
Pending
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 description that clearly communicates what the skill does (manage research entries with four distinct modes), when to use it (explicit trigger phrases covering common user requests), and where it operates (./research/ directory). It uses third person voice, is concise yet comprehensive, and provides enough specificity to distinguish it from other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: create, refresh, validate research entries, plus describes four distinct modes (default single URL, batch multiple URLs, rerun stale entries, validate with structural check and auto-fix). | 3 / 3 |
Completeness | Clearly answers both 'what' (manage research entries — create, refresh, validate with four 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: 'add a tool', 'document this', 'research this', 'refresh this research', 'validate research entries', 'tool URL'. These cover a good range of natural language variations. | 3 / 3 |
Distinctiveness Conflict Risk | Targets a clear niche: managing research entries in a specific directory (./research/) with specific modes and URL-based workflows. The combination of 'research entries', tool URLs, and the specific modes makes it unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
70%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, highly actionable orchestration skill with excellent workflow clarity and progressive disclosure. Its primary weakness is significant verbosity — the content could likely be cut by 40-50% without losing any actionable information. The Mermaid diagrams duplicate the textual workflows, relay rules are over-specified with example tables, and identical patterns (wave spawning, agent invocation) are repeated across modes rather than defined once and referenced.
Suggestions
Consolidate the Mermaid diagrams and textual step-by-step instructions — use one or the other per mode, not both, to eliminate redundant content
Define the wave spawning pattern (up to 5 agents, wait for wave completion) once in a shared section and reference it from batch/rerun/validate modes instead of repeating it three times
Condense the Agent Result Relay Rules section — the tables with 'Never relay as' examples are excessive; a brief rule statement per item would suffice since Claude understands the concept of preserving specificity
Remove the generic preamble about Mermaid diagrams being authoritative instructions — this meta-instruction is repeated and Claude understands how to follow flowcharts
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~350+ lines. It repeats the same patterns multiple times (e.g., wave spawning of 5 agents is described in batch, rerun, and validate modes identically). The relay rules section, while useful, is overly detailed with tables that could be condensed. The Mermaid diagrams duplicate the textual step-by-step instructions that follow them, effectively doubling the content. The preamble about treating Mermaid diagrams as authoritative is repeated conceptually multiple times. | 1 / 3 |
Actionability | The skill provides highly concrete, executable guidance throughout: exact agent tool parameters with specific prompts, precise bash commands for validation/lint/commit/push, specific file paths, exact output format templates, and detailed error handling instructions. Every mode has copy-paste ready agent invocation patterns and clear parameter specifications. | 3 / 3 |
Workflow Clarity | Each mode has an authoritative Mermaid flowchart plus detailed step-by-step instructions with explicit validation checkpoints (pre-relay quality checklist, file existence verification, error handling with stop conditions). The validate mode includes a clear feedback loop: detect errors → spawn fix agents → verify → report. Decision points are explicit with clear branching logic. | 3 / 3 |
Progressive Disclosure | The skill maintains a clear overview structure with well-signaled one-level-deep references to entry-template.md, validation-rules.md, batch-mode.md, and specific agent files. Each mode section provides a summary with a link to the full reference. The Reference Links section at the bottom provides a clean index of all referenced files and agents. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- Jamie-BitFlight/claude_skills
- Commit
b9f32ec
- 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.