uncertainty-acknowledgment

Use this skill when you are not sure about a fact, have outdated knowledge, or the question is contested. Explicitly communicate the level of confidence instead of asserting uncertain things as fact.

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

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 a lean, well-organized instruction skill that gives concrete calibrated-language templates, clear triggers for admitting uncertainty, and explicit prohibitions. It matches the rubric's simple-skill guidance across all dimensions.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient with no padding or explanation of concepts Claude already knows; every line (calibrated phrasings, when to say "I don't know", and the "Never" list) earns its place.	3 / 3
Actionability	It provides concrete, copy-paste-ready phrasing templates ("X is Y", "X is likely Y", "X may be Y, but I'm not certain") plus explicit triggers and prohibitions, which is fully actionable for an instruction-only skill.	3 / 3
Workflow Clarity	As a simple single-purpose skill, the single action (acknowledge uncertainty with calibrated language) is unambiguous and organized into clearly labeled sections (Calibrated language, When to say "I don't know", Never).	3 / 3
Progressive Disclosure	The skill is under 50 lines with no need for external references and no bundle files, and its well-organized sections satisfy the simple-skill progressive-disclosure criterion.	3 / 3
	Total	12 / 12 Passed

Description

65%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 clearly covers both what the skill does and when to use it with an explicit trigger, and occupies a distinct niche. It is weakened by second-person voice and by naming only one concrete action rather than a comprehensive set.

Suggestions

Rewrite the trigger in third person to avoid the voice penalty, e.g. "Use when unsure about a fact, knowledge may be outdated, or a topic is contested."

Name more concrete actions to lift specificity, e.g. "State confidence levels with calibrated phrasing, decline to answer when evidence is unreliable, and avoid presenting speculation as fact."

Add common user phrasings as trigger terms such as "I don't know", "unsure", or "how confident" to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain and a single action ("Explicitly communicate the level of confidence instead of asserting uncertain things as fact") but lists no comprehensive set of concrete actions, and the second-person phrasing "when you are not sure about a fact" triggers the voice penalty, reducing it from a base of 2 to 1.	1 / 3
Completeness	It explicitly answers both what ("Explicitly communicate the level of confidence...") and when ("Use this skill when you are not sure about a fact, have outdated knowledge, or the question is contested") with an explicit trigger clause.	3 / 3
Trigger Term Quality	It includes relevant natural phrases ("not sure about a fact", "outdated knowledge", "the question is contested") but misses common variations a user would actually say like "I don't know", "unsure", or "how confident are you".	2 / 3
Distinctiveness Conflict Risk	The niche of calibrated confidence communication is distinct, and the triggers (uncertain facts, outdated knowledge, contested topics) are specific enough to be unlikely to fire for unrelated skills.	3 / 3
	Total	9 / 12 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: aiming-lab/MetaClaw
Path: memory_data/skills/uncertainty-acknowledgment/SKILL.md
Commit: 922caf3

Reviewed: 9 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.