reset

Reset the FPF reasoning cycle to start fresh

Quality

36%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/fpf/skills/reset/SKILL.md

Quality

Discovery

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 extremely terse and relies on unexplained jargon ('FPF reasoning cycle') without defining what it means, what concrete actions are taken, or when the skill should be triggered. It fails to provide the information Claude would need to reliably select this skill from a pool of available options.

Suggestions

Explain what the 'FPF reasoning cycle' is and what 'resetting' it concretely involves (e.g., clearing state, reinitializing variables, restarting a workflow).

Add a 'Use when...' clause with natural trigger terms, such as 'Use when the user wants to start over, clear reasoning state, or restart the FPF analysis process.'

Include natural language keywords a user might actually say, such as 'start over', 'clear state', 'restart reasoning', or 'fresh start'.

Dimension	Reasoning	Score
Specificity	The description mentions a single vague action ('reset') tied to a domain-specific term ('FPF reasoning cycle') without explaining what that means or what concrete actions are performed.	1 / 3
Completeness	It vaguely addresses 'what' (reset something) but provides no 'when' clause or explicit trigger guidance. Both dimensions are very weak.	1 / 3
Trigger Term Quality	'FPF reasoning cycle' is technical jargon that a user is unlikely to naturally say. There are no common variations or natural language trigger terms included.	1 / 3
Distinctiveness Conflict Risk	The term 'FPF reasoning cycle' is niche enough that it's unlikely to conflict with many other skills, but the description is too vague to clearly define its boundaries.	2 / 3
	Total	5 / 12 Passed

Implementation

64%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill provides clear, actionable guidance with three well-differentiated reset options and executable commands. However, it is more verbose than necessary—particularly the session archive template—and lacks validation/confirmation steps for the destructive hard reset option. The structure is decent but could benefit from trimming and adding safety checks.

Suggestions

Add an explicit confirmation checkpoint before the hard reset (Option 2), e.g., 'Confirm with user before executing rm -rf commands' to address the missing validation for destructive operations.

Trim the session archive markdown template to a minimal example—Claude can generate the full format from a concise schema rather than a fully expanded example.

Consider adding a verification step after reset operations (e.g., 'List remaining files in .fpf/knowledge/ to confirm reset was successful').

Dimension	Reasoning	Score
Conciseness	The skill includes some useful detail but is verbose for what is essentially a few file operations. The lengthy markdown template example and the session archive example could be significantly trimmed. The three options are reasonable but the inline archive template is overly detailed.	2 / 3
Actionability	Provides fully executable bash commands and concrete markdown templates. Each option has copy-paste ready commands and clear file paths. The user report template is specific and actionable.	3 / 3
Workflow Clarity	Steps are clearly sequenced for Option 1 (archive, move, report), but the hard reset (Option 2) involves destructive batch deletion with no validation or confirmation checkpoint. Missing feedback loops for destructive operations caps this at 2 per the rubric.	2 / 3
Progressive Disclosure	The content is reasonably structured with three clearly labeled options, but everything is inline in a single file. The lengthy archive template could be referenced externally. No bundle files exist to offload detail, and the skill is somewhat long for a single reset operation.	2 / 3
	Total	9 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: NeoLabHQ/context-engineering-kit
Commit: dedca19

Reviewed: 1 day 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.