CtrlK
BlogDocsLog inGet started
Tessl Logo

protocol-quiet-in-groups

Enforces PROTOCOLS.md "stay quiet in group chats" deterministically. Blocks outbound messages in Discord/Telegram/Slack/etc group channels when the bot was not @mentioned and recently spoke.

52

Quality

57%

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/protocol-quiet-in-groups/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.

A compact, well-organized single-action skill with concrete parameters, held back by a vague "first few turns" clause, unclear AND/OR precedence, and a slightly redundant observation section. Tightening the trigger logic and trimming restated prose would push it higher.

Suggestions

Define the joining condition precisely (e.g., 'within the first 5 turns after joining') and add parentheses to make AND/OR precedence explicit, so the deterministic rule is unambiguous.

Trim the "What you'll see" section or merge it into the description, since it restates the blocking/bypass behavior already covered.

If any tunable threshold (3 turns, 1 minute, 50 fires) is meant to be adjustable, surface it as a named parameter so the guidance is directly actionable.

DimensionReasoningScore

Conciseness

The body is reasonably lean and avoids explaining platform basics, but the "What you'll see" section restates behavior already in the description and the rationale sentence is mild padding, so it is not fully tight.

2 / 3

Actionability

Concrete parameters are given (priority 90, 50 fires, last 3 turns, past minute, implementation file path), but there is no executable code or copy-paste-ready example, which is expected for a config-driven built-in interceptor but stops short of a 3.

2 / 3

Workflow Clarity

The blocking condition is mostly unambiguous, but "or is in the first few turns of joining" is vague and the AND/OR precedence is unclear, leaving a gap in the deterministic decision logic.

2 / 3

Progressive Disclosure

The skill is under 50 lines, self-contained with no needed external references, and organized into clear sections ("What you'll see", "Implementation"), meeting the simple-skill allowance for a top score.

3 / 3

Total

9

/

12

Passed

Description

57%

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, third-person, and distinct, but lacks an explicit "Use when..." trigger clause, which caps both completeness and trigger-term quality. Adding explicit invocation guidance would lift it from mid-range to strong.

Suggestions

Append an explicit 'Use when the agent is active in group chats (Discord, Telegram, Slack, etc.) and risks over-participating' clause to raise completeness and trigger-term quality.

Surface natural user phrasings such as 'group chat', 'bot talking too much', or 'stay quiet in channels' to broaden trigger-term coverage.

Optionally enumerate the concrete actions (block, bypass on @mention, short-circuit) so specificity reaches the multiple-actions anchor.

DimensionReasoningScore

Specificity

It names a concrete action ("Blocks outbound messages") and the domain (Discord/Telegram/Slack group channels) with trigger conditions, but lists a single action rather than the multiple concrete actions required for a 3.

2 / 3

Completeness

The "what" is clear (enforces the quiet rule by blocking outbound messages), but the "when to use" is only implied through the blocking conditions, so per the guidelines completeness is capped at 2 without an explicit "Use when" clause.

2 / 3

Trigger Term Quality

Natural terms like "group chats", "Discord/Telegram/Slack", and "@mentioned" appear, but coverage is partial and there is no explicit "Use when..." phrasing to surface common variations.

2 / 3

Distinctiveness Conflict Risk

It occupies a clear, narrow niche (group-chat quietness enforcement) with distinct triggers, making conflict with other skills unlikely; voice is third person ("Enforces", "Blocks").

3 / 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
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.