ark-research
Research technical solutions by searching the web, examining GitHub repos, and gathering evidence. Use when exploring implementation options or evaluating technologies.
69
62%
Does it follow best practices?
Impact
68%
1.65xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/research/SKILL.mdQuality
Discovery
67%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description is structurally sound with a clear 'what' and 'when' clause, which is its strongest aspect. However, the actions described are somewhat generic ('gathering evidence', 'searching the web') and the trigger terms could be more comprehensive to cover the natural language users would employ when needing technical research assistance. It would benefit from more specific actions and broader keyword coverage.
Suggestions
Add more specific concrete actions such as 'compare libraries, evaluate dependencies, review API documentation, benchmark alternatives'
Expand trigger terms to include natural user phrases like 'compare libraries', 'find a package', 'tech stack decision', 'look up docs', 'which framework should I use'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (technical research) and some actions ('searching the web', 'examining GitHub repos', 'gathering evidence'), but these are somewhat general and not highly concrete — e.g., 'gathering evidence' is vague. It doesn't list specific outputs or detailed operations. | 2 / 3 |
Completeness | Clearly answers both 'what' (research technical solutions by searching the web, examining GitHub repos, gathering evidence) and 'when' (use when exploring implementation options or evaluating technologies) with an explicit 'Use when...' clause. | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'searching the web', 'GitHub repos', 'implementation options', 'evaluating technologies', but misses common user phrases like 'compare libraries', 'find a package', 'look up documentation', 'tech stack', 'alternatives', or 'best practices'. | 2 / 3 |
Distinctiveness Conflict Risk | The description is somewhat specific to technical research and web searching, but 'exploring implementation options' and 'evaluating technologies' could overlap with general coding assistance or architecture skills. The mention of GitHub repos and web searching helps differentiate it, but the scope is still fairly broad. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a reasonably structured research workflow skill that provides clear sequencing and a useful output template. However, it leans toward describing what Claude would naturally do (search the web, read READMEs, ask users for help) rather than adding novel, high-value constraints or techniques. The skill would benefit from tighter focus on what's truly non-obvious and from adding validation checkpoints.
Suggestions
Remove guidance Claude already knows (e.g., 'look for README documentation', 'ask the user to paste content') and focus on project-specific conventions like the evidence threshold and output format.
Add a validation checkpoint before presenting results — e.g., a checklist to verify source diversity, recency, and relevance before finalizing the recommendation.
Make the '2-3 datapoints' requirement more concrete with specific criteria for what counts as a valid datapoint and how to assess source quality.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but includes some unnecessary explanation. Steps like 'Handle Blocked Content' with example prompts and the general advice to 'look for README documentation, code examples' are things Claude already knows. The output format template is useful but slightly verbose. | 2 / 3 |
Actionability | Provides some concrete guidance (git clone commands, directory structure, output format template) but much of the content is procedural advice rather than executable instructions. The bash commands are simple and the 'evidence requirements' are more guidelines than actionable steps. | 2 / 3 |
Workflow Clarity | Steps are clearly numbered and sequenced, and there's a good example usage walkthrough at the end. However, there are no validation checkpoints — no step to verify research quality before presenting, no feedback loop for when sources conflict, and no explicit criteria for when research is 'sufficient' beyond the vague '2-3 datapoints' guideline. | 2 / 3 |
Progressive Disclosure | For a skill of this size (~80 lines) covering a single task domain, the content is well-organized with clear sections, appropriate depth, and no need for external file references. The structure flows logically from process to output format to example. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- mckinsey/agents-at-scale-ark
- Commit
fc5746e
- 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.