CtrlK
BlogDocsLog inGet started
Tessl Logo

avoid-hallucinating-specifics

Common mistake — stating specific facts (API endpoints, library versions, config options, function signatures) with false confidence when uncertain. Always flag uncertainty rather than guessing specifics.

66

Quality

80%

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 ./memory_data/skills/avoid-hallucinating-specifics/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

100%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise, well-organized, and gives concrete actionable guidance with specific placeholder examples and a clear anti-pattern. As a simple instruction-only skill it satisfies the workflow-clarity and progressive-disclosure exceptions for a top score.

DimensionReasoningScore

Conciseness

The body is lean and bullet-driven with no padding or explanation of concepts Claude already knows; every line earns its place, matching the 'lean and efficient' anchor.

3 / 3

Actionability

Concrete, specific directives are given ("say so explicitly", "verify against official documentation", use `<version>`/`<your-endpoint>` placeholders) with a concrete anti-pattern; for an instruction-only skill this is actionable with specific examples, so code absence is not penalized.

3 / 3

Workflow Clarity

This is a simple single-purpose skill whose single action (flag uncertainty / use placeholders rather than guess) is unambiguous, which per the simple-skills note lets workflow clarity score 3; no destructive or batch operations require validation checkpoints.

3 / 3

Progressive Disclosure

The skill is under 50 lines with no need for external references and is organized into clearly labeled sections (High-risk categories, Prevention, Anti-pattern), meeting the simple-skills exception for a score of 3.

3 / 3

Total

12

/

12

Passed

Description

60%Weight 40%Scale 1-3

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 specific about what facts are risky and what to do, but it lacks an explicit 'Use when...' trigger clause and natural user-facing trigger terms, limiting its completeness and trigger quality. It is also a cross-cutting meta-skill whose broad uncertainty trigger risks overlap with other skills.

Suggestions

Add an explicit trigger clause such as 'Use when you are unsure about a specific API endpoint, version, config option, or function signature and might be tempted to guess.'

Include natural user-facing trigger phrasing (e.g., 'verify a fact', 'when you're unsure', 'don't guess') to broaden trigger-term coverage.

Narrow the trigger to reduce conflict risk, e.g. tying it specifically to producing code-facing specifics (endpoints, signatures, versions) rather than uncertainty in general.

DimensionReasoningScore

Specificity

The description lists multiple concrete fact categories ("API endpoints, library versions, config options, function signatures") plus concrete prescriptive actions ("flag uncertainty rather than guessing specifics"), matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

The 'what' is clearly stated, but the 'when' is only implied via the embedded phrase "when uncertain" rather than an explicit 'Use when...' trigger clause, which per the guidelines caps completeness at 2.

2 / 3

Trigger Term Quality

It includes some relevant keywords ("specific facts", "API endpoints", "uncertain") but lacks natural user-facing trigger phrasing a person would actually say, and misses common variations like "when you're unsure" or "verify a fact".

2 / 3

Distinctiveness Conflict Risk

The hallucinate-specifics niche is somewhat specific, but the broad uncertainty trigger ("when uncertain") could overlap with many other skills, so it does not reach the clear-distinct-trigger level of 3.

2 / 3

Total

9

/

12

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.

Validation15 / 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
aiming-lab/MetaClaw
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.