propose-hypotheses
Execute complete FPF cycle from hypothesis generation to decision
40
27%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/fpf/skills/propose-hypotheses/SKILL.mdQuality
Discovery
0%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 description is critically underspecified. It relies on the undefined acronym 'FPF' without explanation, provides no concrete actions, and lacks any 'Use when...' trigger guidance. A user or Claude selecting from multiple skills would have no way to understand what this skill does or when to apply it.
Suggestions
Define what 'FPF' stands for and list the specific concrete steps or actions involved in the cycle (e.g., 'Generates hypotheses, designs experiments, collects data, analyzes results, and recommends decisions').
Add an explicit 'Use when...' clause with natural trigger terms that users would actually say when they need this skill (e.g., 'Use when the user asks for hypothesis testing, experimental design, or data-driven decision making').
Replace jargon with plain language or at minimum expand the acronym so the description is self-contained and distinguishable from other analytical or decision-support skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description mentions 'FPF cycle' and 'hypothesis generation to decision' but does not explain what FPF stands for or list concrete actions. 'Execute complete FPF cycle' is abstract jargon without clarification of specific capabilities. | 1 / 3 |
Completeness | The 'what' is vague (execute an undefined FPF cycle) and there is no 'when' clause or explicit trigger guidance at all. Both components are very weak. | 1 / 3 |
Trigger Term Quality | 'FPF cycle' is unexplained technical jargon that users are unlikely to naturally say. 'Hypothesis generation' and 'decision' are generic terms that don't serve as distinctive trigger terms for this specific skill. | 1 / 3 |
Distinctiveness Conflict Risk | Without defining what FPF means, the description is indistinguishable from any analytical or decision-making skill. Terms like 'hypothesis generation' and 'decision' are extremely broad and could conflict with many other skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
55%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a well-structured multi-step workflow with clear sequencing, validation checkpoints, and a completion checklist, which is its strongest aspect. However, it critically depends on numerous external task files that are not provided in the bundle, making the actual execution logic incomplete and unverifiable. The content is moderately concise but could reduce repetition in the agent launch patterns.
Suggestions
Provide the referenced task files (tasks/init-context.md, tasks/generate-hypotheses.md, tasks/verify-logic.md, etc.) in the bundle, or inline the essential logic from each so the skill is self-contained.
Reduce repetition by defining the common agent launch pattern once (model, agent type, read-task-file convention) and referencing it in each step rather than repeating the full template.
Add a brief 'References' section at the end listing all external files with one-line descriptions of what each contains, so the dependency graph is clear at a glance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably structured but includes some repetitive patterns (every step repeats the agent launch format verbatim) and could be tightened. The prompt templates are somewhat verbose with repeated structural elements, though most content is necessary for the multi-step workflow. | 2 / 3 |
Actionability | The workflow provides concrete directory creation commands and clear prompt templates, but relies heavily on external task files (e.g., tasks/init-context.md, tasks/generate-hypotheses.md) that are not provided in the bundle. Without those files, the actual execution logic is opaque. The skill describes what to delegate but not what the delegated tasks actually do. | 2 / 3 |
Workflow Clarity | The multi-step process is clearly sequenced with numbered steps, explicit postconditions, wait-for-all synchronization points, file movement as validation checkpoints (L0→L1→L2 or invalid), conditional loops (Step 4), and a completion checklist. Each step specifies what to verify before proceeding. | 3 / 3 |
Progressive Disclosure | The skill references multiple external task files (tasks/init-context.md, tasks/generate-hypotheses.md, tasks/verify-logic.md, etc.) but none are provided in the bundle. There are no bundle files at all, making the references unresolvable. The skill is also a monolithic document with no signposted navigation to supporting materials that actually exist. | 1 / 3 |
Total | 8 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- NeoLabHQ/context-engineering-kit
- Commit
dedca19
- 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.