Tessl • The management layer for AI agent skills

SkillPublic

assess-energy-shock

Model oil or gas supply shock exposure for a country and chokepoint. Use when the user asks how an energy disruption could affect fuel supply, strategic cover, or product deficits.

Quality

82%

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

Quality

Content

88%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.

An exemplary API-skill body: complete, copy-paste-ready request/response documentation with honest, specific caveats about data coverage and model limitations. Its only real weakness is structural - everything lives in the single SKILL.md, including long semantic caveat paragraphs that could be offloaded to a reference file.

Suggestions

Move the extended gasSensitivity semantics and storage-ratio caveats into a one-level-deep reference file, keeping only the operational rules inline.

Trim redundant caveat sentences such as 'A recent response does not make observations current.' where the same point is already implied by the empty-dates rule.

Consider adding a second brief worked example for a gas-only scenario, since the single example covers 'both' mode only.

Dimension	Reasoning	Score
Conciseness	Dense, API-specific content with essentially no padding or explanations of known concepts; only minor trimming possible in the stacked caveat sentences (e.g., 'A recent response does not make observations current.') and the storage-ratio paragraph.	4 / 5
Actionability	Fully executable: exact endpoint, auth header with example value, complete parameter table with shapes, defaults, and clamping rules, full response JSON, a JMESPath example, and a copy-paste curl worked example covering the common case.	5 / 5
Workflow Clarity	A simple single-action skill where the single action (authenticated GET with query params) is unambiguous, with explicit error-handling feedback (401 fix, 429 retry with backoff, retry when dataAvailable/coverageLevel flags show unavailable data).	5 / 5
Progressive Disclosure	No bundle files exist; the single-file body (~104 lines) is well-organized into clear, ordered sections with an external References list. Not 5 because all content is inline (the dense gas-semantics caveat paragraphs could live in a reference file) and the under-50-line simple-skill exception does not strictly apply.	4 / 5
	Total	18 / 20 Passed

Description

70%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.

A strong, well-scoped description that explicitly covers both what the skill does and when to use it in third person. Its main gaps are missing the most salient natural trigger terms (Hormuz, LNG, strait closure) and listing only one capability when the skill actually computes multiple concrete outputs.

Suggestions

Add the natural trigger phrases users actually say, such as 'Hormuz', 'strait closes', or 'LNG disruption', to the 'Use when' clause.

Enumerate the concrete outputs computed (e.g., product deficits, effective cover days) to raise specificity beyond the single 'Model exposure' action verb.

Include an example question phrasing like 'what happens if Hormuz closes?' to make the when-clause more concrete.

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete action ('Model oil or gas supply shock exposure for a country and chokepoint') but does not list the several specific outputs it computes (deficits, cover days, product losses), matching '1-2 concrete actions, not comprehensive'.	3 / 5
Completeness	Explicitly answers both what ('Model oil or gas supply shock exposure...') and when ('Use when the user asks how an energy disruption could affect fuel supply, strategic cover, or product deficits'). Not 5 because the when-clause leans on technical terms ('strategic cover', 'product deficits') rather than concrete trigger phrases.	4 / 5
Trigger Term Quality	Good coverage of natural terms ('oil', 'gas', 'supply shock', 'chokepoint', 'energy disruption', 'fuel supply', 'product deficits'), but misses common user phrasings like 'Hormuz', 'strait closes', and 'LNG'.	4 / 5
Distinctiveness Conflict Risk	Clear niche (chokepoint shock scenario modeling) that the body explicitly differentiates from sibling skills; minor residual overlap with 'monitor-energy-disruptions' and 'check-chokepoint-status' on the shared phrase 'energy disruption'.	4 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: koala73/worldmonitor
Path: skills/assess-energy-shock/SKILL.md
Revision: 8fe2327

Reviewed: 5 days ago

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.

assess-energy-shock

Table of Contents

Is this your skill?