CtrlK
BlogDocsLog inGet started
Tessl Logo

calibrate-claim-confidence

When the agent's epistemic state (GCCRF) indicates low empowerment and falling certainty, hedges out confident absolutes ("definitely", "always", "100%") in outgoing messages.

47

Quality

50%

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/calibrate-claim-confidence/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%

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

The content is short and reasonably organized but largely descriptive: it explains the interceptor's behavior and points to a source file rather than giving executable, actionable guidance. Adding concrete steps or examples and trimming the conceptual framing would improve it.

Suggestions

Add a concrete example of an input message and its hedged output to raise actionability.

Replace the conceptual explanation of GCCRF empowerment with a brief operational trigger condition.

Provide any verification step or fallback behavior to give the simple workflow more structure.

DimensionReasoningScore

Conciseness

The body is mostly lean, but explains the GCCRF empowerment concept and includes a mildly promotional line ('canonical example of state-binding') that could be tightened, matching the level-2 anchor.

2 / 3

Actionability

It gives a concrete source-file path and a firing limit, but provides no executable code or commands and describes the interceptor rather than instructing, matching the level-2 anchor of incomplete concrete guidance.

2 / 3

Workflow Clarity

The single action (rewrite messages into hedged language) is fairly clear, but the body is observational ('What you'll see') rather than procedural and lacks any sequencing or validation checkpoint, sitting at level 2.

2 / 3

Progressive Disclosure

At under 50 lines with no external references needed, the body is split into well-organized sections (What you'll see, Implementation) with no nested references, qualifying for level 3 under the simple-skills guideline.

3 / 3

Total

9

/

12

Passed

Description

42%

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 distinctive and states a concrete action, but leans on internal framework jargon (GCCRF, empowerment) rather than natural user trigger terms, and omits an explicit 'Use when...' clause. Tightening the trigger language to user-facing terms would raise completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause framed in user-facing language to lift completeness to 3.

Replace internal jargon ('GCCRF', 'epistemic state', 'empowerment') with natural trigger terms a user would actually say.

List multiple concrete actions if applicable (e.g., soften hedges, flag unsupported claims) to strengthen specificity.

DimensionReasoningScore

Specificity

It names a concrete action ('hedges out confident absolutes') and the domain (outgoing messages / GCCRF state), but lists a single action rather than multiple concrete actions, matching the level-2 anchor rather than level 3.

2 / 3

Completeness

It clearly states what the skill does, and gives a when-condition ('when... indicates low empowerment and falling certainty'), but lacks an explicit user-facing 'Use when...' trigger, which caps completeness at 2 per the judging guidelines.

2 / 3

Trigger Term Quality

Trigger terms are internal jargon ('GCCRF', 'epistemic state', 'low empowerment', 'falling certainty') rather than natural language a user would say, matching the level-1 anchor for technical jargon.

1 / 3

Distinctiveness Conflict Risk

It targets a narrow, unique niche (hedging absolutes based on GCCRF empowerment) with triggers unlikely to overlap with other skills, matching the level-3 anchor.

3 / 3

Total

8

/

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
Bitterbot-AI/bitterbot-desktop
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.