CtrlK
BlogDocsLog inGet started
Tessl Logo

anti-sycophancy

Eliminate sycophantic agreement patterns in AI responses. Challenge user claims independently, avoid agreement bias, and state evidence before deference.

60

Quality

71%

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/AI-Agents-Safe-Coding-Skills/skills/anti-sycophancy/SKILL.md

The canonical home for this skill is anti-sycophancy in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 concise, well-structured, and gives an executable workflow with an explicit feedback loop for user disagreement. It is a strong, efficient skill body with no significant weaknesses.

DimensionReasoningScore

Conciseness

The body is lean with no padding or explanation of what sycophancy is; every line instructs an action and assumes Claude's competence.

5 / 5

Actionability

Provides a concrete 4-step procedure and a specific pushback decision rule (categorise as new evidence vs repeated opinion, then update or restate), with only minor gaps in worked examples.

4 / 5

Workflow Clarity

The Process is a clearly sequenced 4-step flow plus an explicit feedback loop for disagreement (a/b/c), which serves as the validation checkpoint; no destructive/batch cap applies.

5 / 5

Progressive Disclosure

A simple single-purpose skill under 50 lines with no need for external references; the three well-organized sections (When to Use, Process, Limitations) satisfy the simple-skill exception.

5 / 5

Total

19

/

20

Passed

Description

51%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 clearly states what the skill does with several concrete actions, but omits any explicit 'when to use' trigger guidance and relies on abstract jargon rather than natural user phrasing. Adding a 'Use when...' clause with everyday trigger terms would lift the two lowest dimensions.

Suggestions

Add a 'Use when...' clause naming natural trigger phrases users would actually say (e.g. when a user asserts something questionable, when you find yourself agreeing too readily).

Replace abstract jargon like 'sycophantic agreement patterns' with concrete user-facing terms such as 'pushing back on user claims' or 'independent fact-checking'.

State the trigger context explicitly so the what and when are both answered, moving completeness from 3 toward 5.

DimensionReasoningScore

Specificity

Names three concrete behaviors ('Challenge user claims independently', 'avoid agreement bias', 'state evidence before deference'); slightly short of the comprehensive multi-action coverage of a 5.

4 / 5

Completeness

The 'what' is clearly stated but there is no 'Use when...' clause or equivalent 'when' guidance, which the rubric caps at 3.

3 / 5

Trigger Term Quality

Phrases like 'sycophantic agreement patterns' and 'agreement bias' are abstract jargon a user would rarely say; no natural trigger keywords are present.

2 / 5

Distinctiveness Conflict Risk

The anti-sycophancy niche is fairly distinct from typical coding skills, though its behavioral posture could overlap with general critical-thinking skills, leaving minor conflict risk.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.