CtrlK
BlogDocsLog inGet started
Tessl Logo
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

79%

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 ./skills/assess-energy-shock/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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.

This is a strong, highly actionable API skill: the curl example, parameter table, full response shape, and explicit error/degradation handling make it immediately executable. Its weaknesses are presentational: duplicated sentences, hardcoded time-sensitive dates, and long inlined interpretive prose that inflates token cost and would be better split into a reference file, which drags conciseness and progressive disclosure to the middle of the scale.

Suggestions

Remove the duplicated sentence "Missing or invalid LNG imports or nonpositive demand suppress gasSensitivity. Observed zero LNG imports remain valid." (it appears in both the oil-baseline and cover paragraphs) and consolidate that rule into the gas section.

Move the field-by-field response semantics (the long paragraphs on preCrisisBaseline, cover sources, and gasSensitivity) into a RESPONSE_FIELDS.md reference file, leaving SKILL.md as an overview with the worked example, errors, and key caveats.

Replace hardcoded window dates ("Feb 2025 to Jan 2026", "the 2026 Hormuz crisis") with relative phrasing ("the 12 months before the crisis reference month") or isolate them in a clearly labeled data-vintage note so the skill does not silently go stale.

DimensionReasoningScore

Conciseness

The body is information-dense with domain-specific semantics Claude could not know (basis fallbacks, bypass pipelines, cover caps), so it is not padded with known concepts, but it contains verbatim duplicated sentences ("Missing or invalid LNG imports or nonpositive demand suppress gasSensitivity. Observed zero LNG imports remain valid." appears twice), hardcoded time-sensitive dates ("Feb 2025 to Jan 2026", "the 2026 Hormuz crisis") outside any deprecated section, and multi-hundred-word paragraphs that could be tightened. This sits at "mostly efficient but could be tightened" rather than the minor-trimming of anchor 4.

3 / 5

Actionability

The skill provides a fully executable, copy-paste-ready curl example covering the common case (JP, hormuz_strait, 50%, both modes), a complete parameter table with shapes, defaults, and clamping rules, a full response JSON, and concrete error handling (401 missing key, 429 retry with backoff, flag-based degradation checks). This matches the anchor-5 example of executable commands covering common cases.

5 / 5

Workflow Clarity

The single action (call the endpoint) is unambiguous and checkpoints exist (error codes, checking dataAvailable/coverageLevel/degraded/limitations, "read assessment and limitations before calling the demand missing"), but the multi-step interpretation of the response is scattered across dense prose rather than an ordered sequence, leaving minor validation-sequencing gaps typical of anchor 4.

4 / 5

Progressive Disclosure

Section headers organize the document, but roughly 13 dense paragraphs of field-by-field response semantics (baselines, cover logic, gas sensitivity) are inlined in SKILL.md where they clearly belong in a separate reference file; the only references given are external URLs. This matches anchor 3 (content that should be separate is inline) rather than anchor 4's mostly-appropriate placement.

3 / 5

Total

15

/

20

Passed

Description

78%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-constructed: it states a concrete capability in third person and pairs it with an explicit "Use when" clause containing natural trigger phrases, satisfying both what and when. Its main gaps are limited action enumeration (one umbrella action) and missing common synonyms such as specific chokepoint names or LNG terminology that users might naturally say.

DimensionReasoningScore

Specificity

"Model oil or gas supply shock exposure for a country and chokepoint" names the domain and one concrete action with clear scope, but does not enumerate several specific actions like the anchor-4 example. It is more concrete than the generic anchor-2 "names the domain but actions are minimal".

3 / 5

Completeness

Explicitly answers both: what ("Model oil or gas supply shock exposure for a country and chokepoint") and when ("Use when the user asks how an energy disruption could affect fuel supply, strategic cover, or product deficits") with concrete trigger phrasing, matching the anchor-5 example structure.

5 / 5

Trigger Term Quality

Natural phrases users would say are present ("energy disruption", "fuel supply", "strategic cover", "product deficits"), but common synonyms and specifics are missing (chokepoint names like Hormuz, "strait closure", "LNG", "energy security"), so it falls short of comprehensive anchor-5 coverage while exceeding the sparse anchor-3 example.

4 / 5

Distinctiveness Conflict Risk

The scenario-modeling framing ("Model ... shock exposure") is a distinct niche, but trigger phrases like "energy disruption" and "chokepoint" overlap with closely related sibling skills the body itself names (monitor-energy-disruptions, check-chokepoint-status), keeping it at anchor 4 rather than a fully conflict-free 5.

4 / 5

Total

16

/

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.

Validation — 15 / 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

koala73/worldmonitor

Path

skills/assess-energy-shock/SKILL.md

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.