atomise
Atom of Thoughts (AoT) reasoning - decompose complex problems into atomic units with confidence tracking and backtracking. For genuinely complex reasoning, not everyday questions. Triggers on: atomise, complex reasoning, decompose problem, structured thinking, verify hypothesis.
85
Quality
87%
Does it follow best practices?
Impact
73%
2.28xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
82%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 both purpose and trigger conditions. The explicit trigger terms and scope limitation ('not everyday questions') are strengths. Minor weaknesses include somewhat abstract capability language ('atomic units') and potential overlap with other reasoning-focused skills.
Suggestions
Add more concrete examples of what 'atomic units' means in practice (e.g., 'breaks problems into independent sub-questions, tracks confidence per step')
Differentiate more clearly from general reasoning skills by specifying unique capabilities like 'dependency graphs' or 'iterative refinement'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (complex reasoning) and some actions (decompose, confidence tracking, backtracking), but 'atomic units' is somewhat abstract and the full range of concrete actions is not comprehensively listed. | 2 / 3 |
Completeness | Clearly answers both what ('decompose complex problems into atomic units with confidence tracking and backtracking') and when ('For genuinely complex reasoning, not everyday questions. Triggers on:...'). | 3 / 3 |
Trigger Term Quality | Explicitly lists natural trigger terms users would say: 'atomise, complex reasoning, decompose problem, structured thinking, verify hypothesis' - these are specific and varied keywords that match user intent. | 3 / 3 |
Distinctiveness Conflict Risk | 'Complex reasoning' and 'structured thinking' could overlap with other reasoning or problem-solving skills. The 'Atom of Thoughts' naming and specific triggers like 'atomise' help, but 'decompose problem' is fairly generic. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill that efficiently teaches a complex reasoning methodology. It excels at conciseness (dense tables, no fluff), actionability (concrete thresholds, clear syntax), and workflow clarity (explicit phases with backtracking). The only minor weakness is that all content is inline rather than using progressive disclosure to separate advanced topics.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean and efficient. Every section earns its place with no unnecessary explanation of concepts Claude already knows. Tables and code blocks maximize information density. | 3 / 3 |
Actionability | Provides concrete command syntax, clear execution phases, specific confidence thresholds, and practical examples. The core loop, atom structure, and output format are all copy-paste ready. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with explicit phases (Setup, Iterate), clear decision points (atomicity gate, confidence thresholds), and explicit backtracking instructions when confidence drops below 0.5. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections and tables, but everything is in a single file. For a skill this comprehensive (~150 lines), some content like detailed examples or domain-specific verification guides could be split into referenced files. | 2 / 3 |
Total | 11 / 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
- NeverSight/skills_feed
- Commit
5342bca
- 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.