skill-research-process

Builds comprehensive Claude Code skills using parallel research agents — categorization, parallel documentation gathering, anti-hallucination checkpoints, and final validation. Use when building a skill from official docs, when "research for skill" or "create comprehensive skill" is requested, or when extensive multi-source documentation gathering is needed before skill creation.

Quality

85%

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 well-structured process skill: staged workflow with mandatory validation gates, error-recovery feedback loops, and properly bundled one-level-deep references. Weaknesses are limited to redundant restatement of the gates in two checklist sections, malformed MCP tool names, and one external reference link that does not resolve.

Suggestions

Remove the redundancy between the three quality gates, the Key Principles table, and the Success Checklist — consolidate Gate 2's citation rules into a single authoritative location and reference it from the checklist to cut tokens.

Fix the malformed MCP tool names in the MCP Tool Selection table ('mcp**exa**\*', 'mcp**Ref**\*') so they render and match the real tool identifiers documented in references/mcp-tools.md.

Replace or remove the broken './../../../plugins/plugin-creator/skills/claude-skills-overview-2026/resources/agent-teams.md' link with a path that resolves (e.g. a copy under references/ or a stable documented path), keeping all references one level deep.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence and explains nothing basic, but the Success Checklist and Key Principles table largely restate the three quality gates (e.g. 'Every factual claim has citation with access date' appears in both Gate 2 and the checklist), and the agent-teams section runs long. Not a 5 because this duplication could be trimmed; not a 3 because the excess is duplication rather than unnecessary concept explanation.	4 / 5
Actionability	Concrete commands are given (init_skill.py and package_skill.py invocations, the Agent launch pattern, the required citation format), and agent prompts are delegated to a real file. Not a 5 because the MCP tool names are malformed ('mcpexa\', 'mcpRef\') and the Agent/subagent examples are illustrative rather than copy-paste ready; not a 3 because the guidance is otherwise executable with only minor gaps.	4 / 5
Workflow Clarity	Three stages are clearly sequenced, each ending in an explicit quality gate (Gate 2 marked 'MANDATORY before Stage 3'), with checklists, a validation script, and an Error Recovery section providing feedback loops (check agent output → resume or re-launch with narrower scope). This matches the anchor for clear sequence with explicit validation, feedback loops, and checklists.	5 / 5
Progressive Disclosure	The body is a well-organized overview with clearly signaled one-level-deep references (references/agent-prompts.md, references/mcp-tools.md, references/gaps-analysis.md — all real files), matching good structure. Not a 5 because the Agent Teams link ('./../../../plugins/plugin-creator/skills/claude-skills-overview-2026/resources/agent-teams.md') does not resolve within the skill bundle, breaking navigation.	4 / 5
	Total	17 / 20 Passed

Description

88%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 description: third-person voice, specific action list, and an explicit 'Use when' clause with multiple natural trigger phrases. The only weakness is modest overlap risk with generic skill-creation skills and a few missing natural synonyms.

Dimension	Reasoning	Score
Specificity	The description lists multiple specific concrete actions — 'categorization, parallel documentation gathering, anti-hallucination checkpoints, and final validation' — covering the full build workflow, matching the comprehensive-coverage anchor. It is not a 4 because no meaningful capability of the process is left uncovered.	5 / 5
Completeness	Both questions are explicitly answered: the first sentence states what the skill does, and 'Use when building a skill from official docs, when "research for skill" or "create comprehensive skill" is requested...' gives concrete when-triggers. This matches the anchor for explicit what AND when with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrases are present ('building a skill from official docs', 'research for skill', 'create comprehensive skill', 'skill creation'), giving good keyword coverage. It is not a 5 because common user variations such as 'write a skill', 'skill building', or 'documentation research' are missing.	4 / 5
Distinctiveness Conflict Risk	The 'parallel research agents' / anti-hallucination framing carves a clear niche, but 'create comprehensive skill' could also fire for a general skill-creator skill, giving minor overlap risk with closely related skills. Not a 5 because of that overlap; not a 3 because the research-driven framing is distinctly identifiable.	4 / 5
	Total	18 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: Jamie-BitFlight/claude_skills
Path: .claude/skills/skill-research-process/SKILL.md
Commit: 3e0b2af

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.