propose-hypotheses

Execute complete FPF cycle from hypothesis generation to decision

Quality

31%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./plugins/fpf/skills/propose-hypotheses/SKILL.md

Quality

Content

62%

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 parallel execution patterns, earning strong marks for workflow clarity. However, its actionability is limited by heavy reliance on external task files that aren't provided, and the agent launch mechanism lacks concrete invocation syntax. The content is moderately concise but could be tightened by reducing repetitive boilerplate across steps.

Suggestions

Provide the referenced task files (tasks/init-context.md, tasks/generate-hypotheses.md, etc.) as bundle files, or inline the essential logic so the skill is self-contained and actionable.

Specify the concrete syntax for launching sub-agents (e.g., the exact tool call or command) rather than the abstract 'Launch fpf-agent with sonnet[1m] model' pattern.

Reduce boilerplate repetition across steps by defining the agent launch pattern once and referencing it, or use a more compact format for the repeated prompt structures.

Dimension	Reasoning	Score
Conciseness	The skill is reasonably efficient but has some redundancy—each step repeats the same agent launch pattern with similar boilerplate. The completion checklist at the end partially duplicates the workflow steps. However, it doesn't over-explain concepts Claude already knows.	2 / 3
Actionability	The workflow provides concrete directory creation commands and specific file paths, but the core logic is delegated to external task files (e.g., tasks/init-context.md, tasks/generate-hypotheses.md) that are not provided. The prompts are templates rather than fully executable instructions, and the agent launch mechanism ('Launch fpf-agent with sonnet[1m] model') lacks concrete invocation syntax.	2 / 3
Workflow Clarity	The multi-step process is clearly sequenced with numbered steps, explicit postconditions, conditional loops (Step 4), parallel execution patterns (Steps 5-7), wait-and-verify checkpoints after each parallel step, and a feedback loop at Step 9 if the user disagrees with the decision. The workflow handles error recovery paths (invalid hypotheses moved to invalid/) and has clear completion criteria.	3 / 3
Progressive Disclosure	The skill references multiple external task files (tasks/init-context.md, tasks/generate-hypotheses.md, etc.) which is good progressive disclosure in principle, but none of these bundle files are provided, making it impossible to verify they exist or are correctly structured. The SKILL.md itself is somewhat long but the content is appropriately workflow-level rather than deeply detailed.	2 / 3
	Total	9 / 12 Passed

Description

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 underdeveloped. It relies on the unexplained acronym 'FPF' without defining it, lists no concrete actions, includes no natural trigger terms, and lacks any 'Use when...' guidance. It would be nearly impossible for Claude to correctly select this skill from a pool of available skills.

Suggestions

Define what 'FPF' stands for and list the specific concrete actions involved in each phase of 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 users would say, such as specific problem domains, methodologies, or task types this skill applies to.

Replace jargon with plain language or supplement it with common synonyms so users who don't know the acronym 'FPF' can still trigger the skill appropriately.

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 cycle' is vague and abstract without defining what specific steps or operations are performed.	1 / 3
Completeness	The description weakly addresses 'what' (execute FPF cycle) without clarity, and completely lacks a 'when' clause or any explicit trigger guidance for when Claude should select this skill.	1 / 3
Trigger Term Quality	'FPF cycle' is unexplained jargon that users are unlikely to naturally say. 'Hypothesis generation' and 'decision' are generic terms that don't provide clear, natural trigger keywords a user would use when needing this skill.	1 / 3
Distinctiveness Conflict Risk	Without defining what FPF is, the description is too ambiguous to distinguish from other analytical, decision-making, or hypothesis-testing skills. Terms like 'hypothesis generation' and 'decision' are extremely broad and could overlap with many skills.	1 / 3
	Total	4 / 12 Passed

Validation

81%

Warnings & errors only

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: 3711edf

Reviewed: 20 days ago

Table of Contents

Discovery Implementation Validation

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.