CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

smooth

Count what slowed the agents down in this project over the last day, week or month (default day), and leave one fix for the friction that recurred most, on a smooth/<date> branch you keep or drop. Run it nightly from a scheduled task. Costs one Sonnet call on a day with a fix, none otherwise.

Quality

91%

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

SKILL.md
Quality
Evals
Security

Quality

Content

100%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.

An exemplary minimal skill body: exact command with arguments, defaults, execution mode, failure handling, and output expectation in three sentences. Bundle structure is clean, with a single verified entry point and implementation details hidden one level deep.

DimensionReasoningScore

Conciseness

Three lean sentences where every token earns its place; even the foreground requirement justifies itself ('a scheduled run may end before a background job does') and nothing explains concepts Claude already knows.

5 / 5

Actionability

Fully executable: the exact command '${CLAUDE_SKILL_DIR}/scripts/smooth.sh <window>', the valid argument values ('day', 'week' or 'month'), the default (none named → 'day'), the working directory, the execution mode, failure handling ('It fails → show its error and stop'), and the end state ('show its output as it printed it').

5 / 5

Workflow Clarity

A single unambiguous action with an explicit failure checkpoint and a defined end state, satisfying the simple-skill exception; the risky work (making the fix) is safely delegated to the script, which leaves it on a throwaway smooth/<date> branch rather than the checked-out branch.

5 / 5

Progressive Disclosure

Under 50 lines with no need for external references; the body references exactly one real bundle entry point (scripts/smooth.sh, verified present) and the helper scripts (project.sh, count.sh, trend.sh) are correctly kept one level inside that entry script rather than surfaced.

5 / 5

Total

20

/

20

Passed

Description

78%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 description: concrete, honest about cost and behavior, and clearly differentiated. Its main gaps are the absence of an explicit 'Use when...' trigger clause and a second-person phrase that costs it a specificity point.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('Count what slowed the agents down... over the last day, week or month', 'leave one fix for the friction that recurred most, on a smooth/<date> branch', 'Costs one Sonnet call') which is comprehensive coverage, but the second-person 'a smooth/<date> branch you keep or drop' triggers the required 1-point specificity penalty.

4 / 5

Completeness

The 'what' is fully explicit (count friction over a window, leave one fix on a dated branch), and the 'when' is explicitly stated via 'Run it nightly from a scheduled task', which qualifies as equivalent trigger guidance; however it describes deployment cadence rather than concrete 'Use when...' trigger phrases.

4 / 5

Trigger Term Quality

Contains the natural phrases a user would say for this need ('slowed the agents down', 'friction', 'nightly', 'scheduled task'), giving good keyword coverage; a few natural synonyms (e.g., 'blocked', 'interruptions', 'speed up') are missing.

4 / 5

Distinctiveness Conflict Risk

A clear niche ('Count what slowed the agents down in this project', 'smooth/<date> branch', 'one Sonnet call') with distinct triggers and minimal conflict risk against other skills.

5 / 5

Total

17

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

saadshahd/moo.md

Path

hunch/skills/smooth/SKILL.md

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.