CtrlK
BlogDocsLog inGet started
Tessl Logo

building-trust-before-sensitive-advice

Use when you need to deliver sensitive political counsel to a new or distrustful leader. Builds trust gradually through demonstrated competence, acknowledged risk, and escalating from safe topics to dangerous internal politics.

71

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 body is a tight, well-structured instruction-only skill with a clear sequenced workflow and a verification section. It would reach the top band by adding an explicit error-recovery/feedback loop and slightly more concrete phrasing for the more abstract steps.

Suggestions

Add an explicit feedback loop in the workflow (e.g., if the leader deflects or reacts badly, return to safer topics and re-demonstrate value before re-attempting escalation).

Tighten the more abstract steps with a concrete example phrase or signal, mirroring the Jiang Ziya/King Wen pattern used in step 4.

Inline a brief validation gate within the Steps list (e.g., 'Confirm an explicit invitation has been received before moving from external matters to internal politics') rather than only in the post-hoc Verification section.

DimensionReasoningScore

Conciseness

Lean bullet steps with brief, purposeful glosses; no padding or explanation of concepts Claude already knows; every section earns its place.

5 / 5

Actionability

Concrete, directive steps with a worked example ("e.g., Jiang Ziya and King Wen"), but the guidance is strategic rather than literal copy-paste and a few steps leave the exact phrasing implicit.

4 / 5

Workflow Clarity

An explicit 8-step sequence with a gating step ("Wait for explicit invitation") and a final Verification checklist; missing an explicit validate-fix-retry feedback loop keeps it just below 5.

4 / 5

Progressive Disclosure

Under 50 lines with no need for external references, yet well-organized into clearly labeled sections (Steps, Key Principle, Warning, Expected Outcomes, Verification).

5 / 5

Total

18

/

20

Passed

Description

87%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 well-formed: it pairs an explicit 'Use when' trigger with a clear, multi-mechanism statement of what the skill does, and occupies a distinct niche. Minor gains would come from adding a couple more natural trigger synonyms.

DimensionReasoningScore

Specificity

Names the domain and several concrete mechanisms ("demonstrated competence", "acknowledged risk", "escalating from safe topics to dangerous internal politics"), but coverage is not exhaustive.

4 / 5

Completeness

Explicitly answers both what ("Builds trust gradually through...") and when ("Use when you need to deliver sensitive political counsel to a new or distrustful leader") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural phrases like "sensitive political counsel", "new or distrustful leader", and "build trust" align with what a user would say, though a few synonymous phrasings are missing.

4 / 5

Distinctiveness Conflict Risk

The narrow niche of sensitive political counsel to a distrustful leader is highly specific with minimal overlap risk against other skills.

5 / 5

Total

18

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
baojie/shiji-kb
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.