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.
71
64%
Does it follow best practices?
Impact
73%
2.28xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./data/skills-md/0xdarkmatter/claude-mods/atomise/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 does a good job of covering both what the skill does and when to use it, including helpful negative scoping. However, the trigger terms lean toward methodological jargon rather than natural user language, and the capability description is somewhat abstract. The skill could conflict with other general reasoning or problem-decomposition skills.
Suggestions
Add more natural user-language trigger terms that people would actually say, such as 'break this down', 'think through this step by step', 'multi-step problem', or 'analyze this complex situation'.
Make the capabilities more concrete by listing example problem types or domains where this excels, e.g., 'logic puzzles, multi-constraint optimization, causal analysis'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (complex reasoning/problem decomposition) and some actions (decompose into atomic units, confidence tracking, backtracking), but the actions are somewhat abstract and methodology-focused rather than concrete task-oriented actions. | 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, with explicit trigger terms listed). The negative scope ('not everyday questions') is a helpful addition. | 3 / 3 |
Trigger Term Quality | Includes explicit trigger terms like 'atomise', 'complex reasoning', 'decompose problem', 'structured thinking', 'verify hypothesis', but these are more methodological/technical terms than what users would naturally say. Users are more likely to say things like 'break this down', 'think step by step', 'analyze this carefully', or describe the actual problem domain. | 2 / 3 |
Distinctiveness Conflict Risk | The terms 'complex reasoning', 'structured thinking', and 'decompose problem' could overlap with other reasoning or problem-solving skills. However, the specific methodology name 'Atom of Thoughts (AoT)' and terms like 'atomise' and 'confidence tracking' provide some distinctiveness. | 2 / 3 |
Total | 9 / 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 reasoning framework skill with clear workflow sequencing and good use of tables for reference. Its main weaknesses are the lack of concrete worked-through examples (showing actual atoms being created and verified for a real problem) and some redundancy between sections (the 'Remember' section largely restates earlier content). The pseudo-command interface is creative but without implementation backing, the actionability is limited to being a thinking framework rather than an executable tool.
Suggestions
Add one complete worked example showing the full atom decomposition, verification, and contraction cycle for a real problem (e.g., the security or debugging example), with actual atom table entries at each phase.
Remove the 'Remember' section which restates content already covered in the body, and trim the 'Honest Caveat' paragraph—Claude doesn't need to be told that self-assigned confidence scores aren't calibrated probabilities.
Consider splitting domain-specific verification strategies (--math, --code, --security, --design) into a separate reference file with concrete verification techniques for each domain.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good use of tables and structured formatting, but includes some unnecessary content like the 'Honest Caveat' explanation about heuristic confidence, the anti-patterns section restating obvious things, and the 'Remember' section which largely repeats earlier content. The comparison to chain-of-thought in the intro is also unnecessary context for Claude. | 2 / 3 |
Actionability | The execution guide provides a clear process and the output format is well-specified, but the core mechanism is conceptual rather than executable—there's no actual code, no real implementation of the atom data structure, and the '/atomise' command is a pseudo-command with no backing implementation. The examples section shows invocations but not actual worked-through examples with real atoms. | 2 / 3 |
Workflow Clarity | The multi-step process is clearly sequenced with Phase 0 (Setup) and Phase 1+ (Iterate) stages, explicit validation checkpoints (confidence thresholds triggering backtracking), a clear feedback loop (verify -> contract -> evaluate -> backtrack if needed), and well-defined termination conditions. The core loop diagram is immediately understandable. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and headers, but it's entirely monolithic—everything lives in one file with no references to supporting materials. A worked example, detailed domain-specific verification guides, or the atom schema could be split into separate files. For a skill of this length (~150 lines), some separation would improve navigability. | 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.
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
aa009ea
- 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.