research-curator

Orchestrate research entry lifecycle in ./research/ — create, batch-import, refresh stale entries, and validate structure. Use when asked to add a tool, research a URL, document a library, refresh research, validate entries, or given any tool or library URL. Supports --batch (parallel multi-URL), --rerun (refresh one or all entries), and --validate (structural check with auto-fix of error-severity issues).

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

81%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 orchestrator with strong validation feedback loops and clean reference navigation. Its main weakness is token efficiency from duplicating diagrams as prose and repeating the validation gate across modes.

Suggestions

Drop the numbered-prose restatement of each Mermaid diagram (e.g., Rerun Mode's 'Single Entry Rerun'/'All Entries Rerun' steps restate the diagram); keep one authoritative form per procedure.

Extract the repeated validation gate (fix script → validator → error/pass branching) into a single shared 'Validation Gate' subsection or reference and link to it from each mode.

Move the full per-mode output-format templates into a dedicated reference file, keeping only a one-line summary inline, to slim the main body.

Dimension	Reasoning	Score
Conciseness	Mostly actionable procedure rather than padding, but each Mermaid diagram is restated as numbered prose and the validation gate (fix script → validator → error/pass branch) is repeated across Default, Rerun-single, Rerun-all, and Validate. Not a 4 because the duplication is noticeable; not a 2 because the content is substantive, not fluff.	3 / 5
Actionability	Fully executable guidance: exact Agent-tool prompts, concrete `uv run … validate_research.py main --json {file}` commands, and copy-paste output format templates covering each mode's common cases.	5 / 5
Workflow Clarity	Authoritative sequenced Mermaid diagrams with explicit validate→fix→retry feedback loops and a pre-relay quality checklist; validation checkpoints are present for batch/destructive operations, so the cap does not apply.	5 / 5
Progressive Disclosure	Real one-level-deep references (entry-template, validation-rules, batch-mode, duplicate-detection) are well-signaled with a closing Reference Links navigation section, but the body inlines three full diagrams and full output templates. Not a 5 because the main file is heavy with inlined procedural detail; not a 3 because references are clearly signaled and one level deep.	4 / 5
	Total	17 / 20 Passed

Description

96%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.

A strong, third-person description that concretely states capabilities and gives explicit, natural trigger phrases for when to use the skill. The only soft spot is minor overlap risk on the broadest triggers ("add a tool", "document a library").

Dimension	Reasoning	Score
Specificity	Names the domain and lists multiple concrete actions — "create, batch-import, refresh stale entries, and validate structure" — with comprehensive coverage. Not a 4 because the action list is complete rather than having minor gaps.	5 / 5
Completeness	Explicitly answers both what ("Orchestrate research entry lifecycle … create, batch-import, refresh … validate") and when ("Use when asked to …") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases — "add a tool, research a URL, document a library, refresh research, validate entries, or given any tool or library URL" — covering synonyms (tool/library/URL). Not a 4 because the natural-term coverage is broad rather than missing a few.	5 / 5
Distinctiveness Conflict Risk	Clear research-curation niche in ./research/ with distinct URL/tool/library triggers, but "add a tool" and "document a library" carry minor overlap risk with general documentation skills. Not a 5 because of that residual overlap; not a 3 because the niche is clearly staked.	4 / 5
	Total	19 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (527 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: Jamie-BitFlight/claude_skills
Path: .claude/skills/research-curator/SKILL.md
Commit: c337daf

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.