CtrlK
BlogDocsLog inGet started
Tessl Logo

reset

Reset the FPF reasoning cycle to start fresh

44

Quality

43%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./plugins/fpf/skills/reset/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

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 reset procedures with three well-differentiated options (soft, hard, decision reset). Its main weaknesses are verbosity in the session archive template, which Claude could generate dynamically, and the lack of a confirmation/validation step before the destructive hard reset operation. The structure is decent but could be tighter.

Suggestions

Add an explicit confirmation checkpoint before the hard reset (Option 2) — e.g., 'Confirm with user before executing rm -rf commands' — to prevent accidental data loss.

Trim the session archive markdown template to a minimal skeleton; Claude can fill in contextual details like hypothesis counts and file lists at runtime without a verbose example.

Consider adding a post-reset validation step (e.g., verify directory state after reset) to close the feedback loop.

DimensionReasoningScore

Conciseness

The skill includes some useful detail but is verbose for what is essentially a set of file operations. The lengthy markdown template example for the session archive could be trimmed significantly, and the state-at-reset section with example hypothesis counts is padding that Claude can generate contextually.

2 / 3

Actionability

Provides fully executable bash commands and concrete markdown templates for each reset option. The file paths, directory structures, and commands are copy-paste ready with no ambiguity about what to do.

3 / 3

Workflow Clarity

Steps are clearly sequenced for the soft reset (archive → move → report), but the hard reset option lacks any validation or confirmation checkpoint before permanently deleting data. For a destructive batch operation like `rm -rf`, the absence of a verification step should cap this at 2.

2 / 3

Progressive Disclosure

The content is reasonably organized with three clear options, but everything is inline in a single file. The session archive template and detailed examples could be split into a reference file. No bundle files are provided, so there's no external structure to leverage, but the content length (~80 lines of substantive material) would benefit from some separation.

2 / 3

Total

9

/

12

Passed

Description

22%

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 too terse and lacks the detail needed for effective skill selection. It names a domain-specific concept (FPF reasoning cycle) without explaining what it is, lists only one vague action ('reset'), and provides no explicit trigger guidance for when Claude should select this skill.

Suggestions

Add a 'Use when...' clause specifying trigger scenarios, e.g., 'Use when the user asks to reset, restart, or clear the FPF reasoning cycle, or wants to begin a new analysis from scratch.'

Explain what the FPF reasoning cycle is and what 'resetting' it concretely involves (e.g., clearing state, reinitializing parameters, discarding prior conclusions).

Include natural trigger term variations such as 'restart', 'clear', 'reinitialize', 'new cycle', 'begin again' to improve matching.

DimensionReasoningScore

Specificity

The description mentions a single vague action ('reset') tied to a domain-specific term ('FPF reasoning cycle') without explaining what that entails concretely. No specific capabilities or actions are listed beyond 'reset' and 'start fresh'.

1 / 3

Completeness

The description partially addresses 'what' (reset the FPF reasoning cycle) but provides no explicit 'when' clause or trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also weak, so this scores a 1.

1 / 3

Trigger Term Quality

It includes 'reset' and 'start fresh' which are somewhat natural terms a user might say, and 'FPF reasoning cycle' is a specific domain term. However, it lacks common variations or alternative phrasings users might use (e.g., 'clear', 'restart', 'begin again').

2 / 3

Distinctiveness Conflict Risk

The term 'FPF reasoning cycle' is fairly specific and niche, which reduces conflict risk. However, 'reset' and 'start fresh' are generic enough that they could overlap with other reset/restart skills if any exist.

2 / 3

Total

6

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
NeoLabHQ/context-engineering-kit
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.