CtrlK
BlogDocsLog inGet started
Tessl Logo

shh

Keep it down — use terse, clear, and action-first responses for the rest of the session. Remove filler and tangents, preserve technical precision, track multi-step progress, and end with one concrete next action. Use when the user wants compact communication; disable with `stop ssh` or `normal mode`.

72

Quality

88%

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

The canonical home for this skill is shh in choegyumin/agent-skills

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

A well-crafted, actionable style skill with concrete examples and clear validation checkpoints that practices what it preaches. Minor conciseness slack in the compression-theory paragraphs and room for structural refinement keep it from a perfect score.

Suggestions

Tighten the tokenizer/caveman paragraphs (e.g. "Never ADD word to sound caveman...") to the core rule — the token-count justification repeats the same point across multiple sentences.

Consider pulling the long "Style" subsections (caveman compression rules) into a separate reference file so SKILL.md stays a lean overview, improving progressive disclosure.

The "Rules" list mixes behavior rules with workflow rules; grouping them under clearer sub-headers (Tone vs Workflow) would aid skim navigation.

DimensionReasoningScore

Conciseness

The skill is mostly lean and models its own brevity principle via efficient bad/good pairs, but the extended tokenizer/caveman paragraphs (e.g. "Never ADD word to sound caveman...") over-explain token-count tradeoffs that could be trimmed.

4 / 5

Actionability

Highly actionable with concrete bad/good examples featuring real paths and commands (src/auth.ts:42, npm install jsonwebtoken, npm test -- auth.spec.ts) plus explicit rule lists covering the common cases.

5 / 5

Workflow Clarity

Multi-step processes are clearly sequenced with numbered steps and an explicit Pre-send checklist that acts as a validation/feedback loop; rule #2 and #5 reinforce state-tracking, satisfying the checkpoint anchor.

5 / 5

Progressive Disclosure

Single self-contained file with no bundle references and well-organized sections (Persistence, Style, Rules 1-9, When to break, Pre-send check, Boundaries); at ~170 lines it exceeds the simple-skill 50-line exception, and some dense Style subsections could conceptually be split, so it sits just below a 5.

4 / 5

Total

18

/

20

Passed

Description

88%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.

A strong, concrete description that clearly states both capability and trigger conditions with an explicit disable mechanism. Minor gaps in trigger-term synonyms and modest overlap risk with general style skills keep it just below a perfect score.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Remove filler and tangents, preserve technical precision, track multi-step progress, and end with one concrete next action" — covering the behavior comprehensively, matching the anchor for listing multiple specific concrete actions.

5 / 5

Completeness

Explicitly answers both what (terse, action-first responses with the listed behaviors) and when ("Use when the user wants compact communication") with concrete trigger phrases and a disable path.

5 / 5

Trigger Term Quality

Includes natural-ish triggers ("Use when the user wants compact communication", "Keep it down", "terse") but misses common synonyms a user might say ("concise", "brief", "shorter answers"), so coverage is good but not exhaustive.

4 / 5

Distinctiveness Conflict Risk

Carves a distinct compact-communication niche with specific triggers and a disable command, but as a broad communication-style skill it has minor overlap risk with other style-modifying skills.

4 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
choegyumin/agent-skills
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.