CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

web-research-fallback

Research current web information with source-first search and controlled browser fallback

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./resources/skills/research/web-research-fallback/SKILL.md
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 body is an exemplary lean, well-structured behavioral skill: a clear trigger section, a sequenced procedure with fallback handling and cross-checking, sharp pitfalls, and a verification checklist, all with no wasted tokens. The only minor gap is the absence of one or two concrete examples (e.g., a sample query or a findings-recording format) that would make the guidance fully copy-paste ready.

DimensionReasoningScore

Conciseness

The ~28-line body is lean and directive with zero padding — every line instructs ('Open the source directly and extract the relevant passage, date, and URL rather than relying on a search snippet') and it explains nothing Claude already knows. This matches the 'lean and efficient; assumes Claude's competence' anchor; there is no over-explanation to justify a lower score.

5 / 5

Actionability

Each procedure step gives concrete, executable direction for an instruction-only skill ('Search with a focused query and use result metadata to select likely authoritative pages'), so the guidance is mostly executable with only minor gaps. It falls short of anchor 5 because there are no specific examples covering common cases (e.g., a sample focused query or a format for recording what each page established).

4 / 5

Workflow Clarity

The six steps are clearly sequenced and include an explicit error-recovery feedback loop ('If a page fails, try a primary-source alternative or a narrower route before broadening'), an inline validation step ('Cross-check unstable or consequential claims'), and a dedicated Verification checklist — matching the anchor for explicit validation steps with feedback loops. This is not a destructive or batch operation, so no cap applies.

5 / 5

Progressive Disclosure

The skill is under 50 lines with well-organized sections (When to Use, Procedure, Pitfalls, Verification) and needs no external references — no references/scripts/assets bundle exists and none are mentioned in the body. Per the rubric's simple-skill guideline, this qualifies for a 5 with just well-organized sections.

5 / 5

Total

19

/

20

Passed

Description

50%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 states a clear capability and a distinctive methodology, but it is missing any explicit 'when to use' trigger guidance and lacks natural trigger-term variations, which leaves every dimension at the mid-level. Adding a 'Use when...' clause with concrete trigger phrases and more natural user keywords would lift completeness, trigger terms, and distinctiveness together.

Suggestions

Add an explicit trigger clause, e.g., 'Use when a task needs current public information, primary sources, or when a site cannot be reliably read from search snippets alone' — this directly addresses the missing 'when' that caps completeness at 3.

Include natural trigger terms users would actually say, such as 'look up', 'latest', 'up-to-date', or 'find current info on <topic>', to broaden trigger-term coverage beyond the single word 'research'.

Sharpen the capability list with 1-2 more concrete actions (e.g., 'opens sources directly, extracts passages with dates and URLs, cross-checks claims') to raise specificity from domain-plus-two-methods to several enumerated actions.

DimensionReasoningScore

Specificity

Names the domain ('Research current web information') and two method phrases ('source-first search', 'controlled browser fallback'), matching the anchor for 1-2 concrete actions without comprehensive coverage. It falls short of anchor 4 because it does not enumerate several specific actions (e.g., opening sources directly, extracting passages, cross-checking claims).

3 / 5

Completeness

The 'what' is fairly clear (research current web information with a source-first method), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per judging guidelines caps completeness at 3. Not score 2 because the 'what' is concrete rather than vague.

3 / 5

Trigger Term Quality

Relevant keywords like 'Research', 'web', 'search', 'browser', and 'current' are present, but common natural variations users would actually say ('look this up', 'latest', 'up-to-date', 'find current info on') are missing, matching the 'some relevant keywords but missing common variations' anchor. It is not score 4 because the natural-phrase coverage is thin beyond the single word 'research'.

3 / 5

Distinctiveness Conflict Risk

The method phrasing ('source-first search and controlled browser fallback') gives it a niche, but the leading trigger 'Research current web information' would overlap with any generic web-search or browsing skill, matching the 'somewhat specific but could still overlap with similar skills' anchor. Not score 4 because there are no distinct trigger phrases to separate it from a basic web-search skill.

3 / 5

Total

12

/

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

odysseus-dev/odysseus

Path

resources/skills/research/web-research-fallback/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.