CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

reset

Reset the FPF reasoning cycle to start fresh

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

76%Weight 40%Scale 1-5

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

The content is highly actionable with executable commands and templates across three reset variants, but its destructive and batch operations lack validation checkpoints, capping workflow clarity. Structure is clean though the verbose archive template could be split out.

Suggestions

Add a validation checkpoint before the Hard Reset, e.g. list files to be deleted and require explicit user confirmation before running `rm -rf`.

Verify the result after batch moves in Option 3 (e.g. `ls .fpf/knowledge/L1` to confirm hypotheses moved) to create a feedback loop.

Move the full session-archive template into a references file and keep SKILL.md as an overview to tighten conciseness and improve progressive disclosure.

DimensionReasoningScore

Conciseness

The body avoids concept over-explanation and stays actionable, but the inline session-archive template (Notes, Decision Status) is somewhat padded and could be trimmed, fitting anchor 4; it is not a 5 because not every token earns its place.

4 / 5

Actionability

All three options provide copy-paste-ready, executable bash (mkdir/mv/rm with `2>/dev/null || true`) and concrete report templates covering soft, hard, and decision resets, matching anchor 5's fully executable common-case coverage.

5 / 5

Workflow Clarity

Steps are numbered and sequenced, but the destructive Hard Reset (`rm -rf`) and batch Decision Reset lack validation/verification checkpoints, so per the guideline workflow clarity is capped at 3; it is not a 2 because a clear sequence is present.

3 / 5

Progressive Disclosure

No bundle files exist, and the body is well-organized with clear Option 1/2/3 headers for a single-purpose skill; the long inline archive template is the minor organization gap that keeps it at 4 rather than 5.

4 / 5

Total

16

/

20

Passed

Description

53%Weight 40%Scale 1-5

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 is clear and domain-specific but lacks an explicit 'Use when…' trigger and natural keyword variations, which caps both completeness and trigger quality. It is distinct within the FPF skill set yet generic enough to leave the 'when' ambiguous.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to start a fresh FPF reasoning cycle or clear accumulated hypotheses.'

Broaden trigger terms with natural synonyms such as 'clear', 'restart', or 'wipe the reasoning session' alongside 'reset'.

Mention the concrete reset variants (archive, delete, re-evaluate) to lift specificity above a single action.

DimensionReasoningScore

Specificity

"Reset the FPF reasoning cycle" names the domain and one concrete action (reset), matching anchor 3's '1-2 concrete actions but not comprehensive'; it is not a 2 because 'reset' is a concrete action rather than minimal/generic, and not a 4 because only one action is listed.

3 / 5

Completeness

The description gives a clear 'what' (reset the cycle) but no 'Use when…' trigger clause, so per the judging guideline completeness is capped at 3; 'to start fresh' only weakly implies 'when'.

3 / 5

Trigger Term Quality

"reset" and "start fresh" are natural user terms, but "FPF reasoning cycle" is technical jargon and synonyms/variations are absent, matching anchor 3; it lacks the broader keyword coverage of a 4.

3 / 5

Distinctiveness Conflict Risk

"Reset the FPF reasoning cycle" carves a clear FPF-specific niche with only minor overlap risk against other reset operations, fitting anchor 4; without an explicit trigger it falls short of a 5.

4 / 5

Total

13

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

NeoLabHQ/context-engineering-kit

Path

plugins/fpf/skills/reset/SKILL.md

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.