evaluating-peace-negotiations

Use when assessing whether to enter peace talks or risk signaling weakness. Evaluates adversary incentives, ally perceptions, and negotiation leverage to determine if peace overtures will succeed or backfire.

Quality

59%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./kg/ontology/ontology-v1/skus/procedural/skill_161/SKILL.md

Quality

Content

56%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 skill is lean, well-structured into clear sections, and includes a verification block, which supports conciseness, workflow clarity, and progressive disclosure. Its main weakness is actionability: the steps read as prompts to think rather than concrete methods for actually executing the assessment.

Suggestions

Add a concrete method for each step, e.g. a short list of signals to check or a worked mini-example showing how a real adversary goal maps to a go/no-go recommendation.

Insert an explicit validation gate between assessment and recommendation, e.g. 'Do not recommend negotiation unless all four warning signs are ruled out.'

Give one short example of the alternative coalition-building path so Claude can mirror the concrete steps rather than just the three bullet points.

Dimension	Reasoning	Score
Conciseness	The body is short and assumption-respecting, laying out steps and warning signs without explaining what peace negotiations are; only minor phrasing could be trimmed, so it is efficient with negligible over-explanation.	4 / 5
Actionability	Guidance is high-level and abstract ('Assess adversary's goal', 'Predict adversary's behavior') with no concrete method, data sources, or worked example telling Claude how to execute the assessment, so it is closer to the minimal-hints anchor than the some-concrete-guidance anchor.	2 / 5
Workflow Clarity	A clear numbered Analysis Steps sequence is present and a dedicated Verification section provides checkpoints, but the decision flow has no explicit validation gate between 'assess' and 'recommend' and no error-recovery loop, so it sits above a rough sequence but below fully gated workflows.	3 / 5
Progressive Disclosure	This is a single-file, under-50-line skill with no external references needed; content is organized into clearly labeled sections (Analysis Steps, Warning Signs, Alternative Approach, Verification), which per the simple-skill guidance is sufficient for a top progressive_disclosure score.	5 / 5
	Total	14 / 20 Passed

Description

62%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 both what the skill does and when to use it with a natural 'Use when' trigger, giving it solid completeness and distinctiveness. It is held back from the top band by moderate specificity and incomplete trigger-term coverage (missing synonyms like 'ceasefire' or 'diplomacy').

Suggestions

Add concrete trigger synonyms users would naturally say, e.g. 'ceasefire', 'settlement talks', or 'diplomatic off-ramp', alongside 'peace talks'.

Enumerate a few more specific analytic actions (e.g. 'maps adversary goals to settlement terms', 'checks for propaganda exploitation of talks') to lift specificity.

Tighten the distinctiveness by pairing the trigger with a negative boundary, e.g. 'Use for negotiation-entry decisions, not for drafting treaty terms.'

Dimension	Reasoning	Score
Specificity	Names the domain (peace negotiations) and a few concrete analytic actions ('Evaluates adversary incentives, ally perceptions, and negotiation leverage'), but the actions are conceptual assessments rather than a comprehensive list of operations, leaving coverage incomplete.	3 / 5
Completeness	Both 'what' (evaluates incentives, perceptions, leverage to judge success/backfire) and 'when' ('Use when assessing whether to enter peace talks or risk signaling weakness') are present and concrete; the 'when' is explicit and reasonably specific, so it sits above the clear-but-weak-when anchor at 3 but is not as comprehensively triggered as a 5.	4 / 5
Trigger Term Quality	It opens with 'Use when assessing whether to enter peace talks' which is a natural trigger phrase, but the rest leans on specialized phrasing ('risk signaling weakness', 'negotiation leverage') and omits common synonyms users might say ('ceasefire', 'settlement', 'diplomacy'), so coverage is partial.	3 / 5
Distinctiveness Conflict Risk	The peace-negotiation framing is a fairly distinct niche unlikely to fire for unrelated skills, with only minor overlap risk against broader diplomatic or conflict-analysis skills; it is mostly distinct rather than fully carve-out specific.	4 / 5
	Total	14 / 20 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: baojie/shiji-kb
Path: kg/ontology/ontology-v1/skus/procedural/skill_161/SKILL.md
Commit: 6b836e3

Reviewed: 12 days 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.