CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-research-process

Systematic process for building comprehensive Claude Code skills using parallel research agents. Triggers on "research for skill", "build skill from docs", "create comprehensive skill", or when needing to gather extensive documentation from official sources before skill creation.

64

Quality

76%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/skill-research-process/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Discovery

89%

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 solid description that clearly communicates when to use the skill with explicit trigger phrases and a well-defined niche. Its main weakness is that the 'what' portion could be more specific about the concrete actions performed (e.g., spawning research agents, synthesizing findings, generating skill markdown). The trigger terms and completeness are strong points.

Suggestions

Add more specific concrete actions to the 'what' portion, e.g., 'Spawns parallel research agents to gather documentation, synthesizes findings, and generates structured SKILL.md files' to improve specificity.

DimensionReasoningScore

Specificity

Names the domain ('building comprehensive Claude Code skills') and mentions 'parallel research agents' and 'gather extensive documentation from official sources', but doesn't list multiple concrete actions beyond the general process description. It's more process-oriented than action-specific.

2 / 3

Completeness

Clearly answers both 'what' (systematic process for building comprehensive Claude Code skills using parallel research agents) and 'when' (explicit triggers listed with 'Triggers on...' clause and a contextual condition).

3 / 3

Trigger Term Quality

Includes natural trigger phrases like 'research for skill', 'build skill from docs', 'create comprehensive skill', and the contextual trigger 'gather extensive documentation from official sources'. These are terms a user would naturally say when needing this capability.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive niche — specifically about building Claude Code skills via parallel research agents from documentation sources. The trigger terms are specific enough ('research for skill', 'build skill from docs') that this is unlikely to conflict with general coding or documentation skills.

3 / 3

Total

11

/

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 well-structured meta-skill for building other skills through parallel research. Its strongest aspect is workflow clarity, with explicit quality gates, error recovery procedures, and a clear stage-based progression. However, actionability suffers because key details are deferred to unreferenced bundle files, and some sections (Vague Brief Detector, Agent Team Alternative) add bulk that could be better organized through progressive disclosure.

Suggestions

Include the referenced bundle files (agent-prompts.md, mcp-tools.md) or provide inline summaries of their key content so the skill is actionable without them.

Move the 'Vague Brief Detector' and 'Agent Team Alternative' sections into separate reference files to reduce SKILL.md length and improve progressive disclosure.

Replace the pseudocode-style Agent() calls with more concrete, executable examples showing actual tool invocation syntax.

DimensionReasoningScore

Conciseness

The skill is reasonably well-structured but includes some sections that could be tightened. The 'Vague Brief Detector' section is quite lengthy, and the 'Agent Team Alternative' section at the end adds significant length. Some tables and checklists repeat information (e.g., the Success Checklist largely restates the quality gates). However, it mostly avoids explaining concepts Claude already knows.

2 / 3

Actionability

The skill provides concrete steps with specific commands (init_skill.py, package_skill.py) and clear agent launch patterns, but many critical details are deferred to referenced files (agent-prompts.md, mcp-tools.md) that are not provided in the bundle. The pseudocode-style Task agent calls use placeholder syntax rather than fully executable examples. The process is more of a framework than copy-paste-ready instructions.

2 / 3

Workflow Clarity

The multi-stage workflow is clearly sequenced with explicit quality gates between each stage, including validation checklists and feedback loops (e.g., 'If categories overlap: merge before Stage 2', 'If citation missing: add source or mark NOT_VERIFIED'). The error recovery section provides concrete fallback strategies. The ASCII diagram at the top provides an excellent overview of the flow.

3 / 3

Progressive Disclosure

The skill references external files (agent-prompts.md, mcp-tools.md, gaps-analysis.md) with clear links, and the SKILL.md serves as an overview. However, no bundle files were provided, so we cannot verify these references resolve. The Agent Team Alternative section and the lengthy Vague Brief Detector could arguably be split into separate reference files rather than inline. The reference to agent-teams.md uses a deeply relative path that suggests potential navigation issues.

2 / 3

Total

9

/

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.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
Jamie-BitFlight/claude_skills
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.