deep-think-maximum-cognitive-effort-protocol-mq8kvw92

Use this plugin when the user wants a maximum-effort reasoning workflow for a complex, high-stakes, or ambiguous task.

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/community/deep-think-maximum-cognitive-effort-protocol-mq8kvw92/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.

The skill's workflow is clearly sequenced with strong validation checkpoints, but it is verbose, mixes concrete checklists with abstract prompting, and does not integrate its single reference file into the body.

Suggestions

Cut redundant /reason distinctions to one location and trim aphoristic labels ('Karpathy Doctrine', 'Council of Experts') to tighten conciseness.

Replace abstract self-prompts ('Would you stake your reputation on this?') with specific, checkable criteria to improve actionability.

Either link the references/ attribution file from the body or move a detailed phase (e.g., the AUDIT or verification protocol) into a referenced file so progressive disclosure is intentional rather than incidental.

Dimension	Reasoning	Score
Conciseness	The body is well-structured but verbose, with redundant /reason distinctions (a callout plus a closing section) and aphoristic padding ('Karpathy Doctrine', 'Council of Experts') that could be tightened, fitting the 'mostly efficient but includes some unnecessary explanation' anchor.	2 / 3
Actionability	It offers some concrete checklists (5-step Pre-Action Verification Protocol, audit questions) but much of the guidance is abstract prompting ('Would you stake your reputation on this?'), matching the 'some concrete guidance but incomplete' anchor.	2 / 3
Workflow Clarity	An explicit 8-phase sequence with a complexity gate, per-step verification, a Work→Verify→Self-Correct loop, and an 80% confidence stop provides clear sequencing, feedback loops, and checklists; irreversible actions are covered by verification so it is not capped at 2.	3 / 3
Progressive Disclosure	The body is sectioned into clear phases, but it is a single >50-line file and the one bundle file (an attribution note) is not signaled or linked from the body, fitting the 'some structure but references not clearly signaled; content that should be separate is inline' anchor.	2 / 3
	Total	9 / 12 Passed

Description

67%

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 has an explicit when-trigger and names its domain, but is light on concrete actions and trigger-term coverage, and risks overlapping with lighter-weight reasoning skills.

Suggestions

List concrete actions the workflow performs (e.g., 'research, gap analysis, multi-perspective debate, adversarial review') to raise specificity above a domain-only statement.

Add natural trigger variations users actually say (e.g., 'hard problem', 'high-stakes decision', 'when being wrong is expensive') instead of the jargon 'maximum-effort reasoning workflow'.

Sharpen distinctiveness by contrasting effort/scope with lighter reasoning skills directly in the description (e.g., 'for tasks where /reason is not enough').

Dimension	Reasoning	Score
Specificity	Names the domain ('maximum-effort reasoning workflow') but lists no concrete actions such as research, gap analysis, or adversarial review, matching the 'names domain and some actions, but not comprehensive' anchor rather than the multi-action anchor at 3.	2 / 3
Completeness	An explicit 'Use this plugin when...' trigger is present (so not capped at 2) and the what (a reasoning workflow) is stated, satisfying both halves; the what is thin but both are explicitly answered.	3 / 3
Trigger Term Quality	It includes some natural terms a user might say ('complex', 'high-stakes', 'ambiguous task') but leans on jargon ('maximum-effort reasoning workflow') and misses common variations, fitting the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	'Complex, high-stakes, or ambiguous task' is somewhat specific yet overlaps with general reasoning skills such as /reason, so it could trigger for the wrong skill and does not establish a clearly distinct niche.	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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: nexu-io/open-design
Path: plugins/community/deep-think-maximum-cognitive-effort-protocol-mq8kvw92/SKILL.md
Commit: f2760fd

Reviewed: about 16 hours 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.