CtrlK
BlogDocsLog inGet started
Tessl Logo

setup-caliber

Sets up Caliber for automatic AI agent context sync. Installs pre-commit hooks so CLAUDE.md, Cursor rules, and Copilot instructions update automatically on every commit. Use when Caliber hooks are not yet installed or when the user asks about keeping agent configs in sync.

75

Quality

92%

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 1-3

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

An actionable, well-sequenced setup workflow with executable commands, state-based validation checkpoints, and lean prose that assumes Claude's competence. The only minor risk is the final offered git commit/push, which lacks an explicit success verification step.

DimensionReasoningScore

Conciseness

Lean and efficient: concrete bash snippets, terse if/then branches, and no padding explaining what Caliber or Node.js is; the few asides ('~500ms per invocation', 'faster for daily use') are decision-relevant rather than filler.

3 / 3

Actionability

Fully executable throughout — exact install commands, the complete GitHub Action YAML to write, and literal gh/git commands; copy-paste ready with no pseudocode.

3 / 3

Workflow Clarity

Steps 1–5 are explicitly sequenced with a consistent check-first-then-act pattern and state-checkpoint branches (HOOK_ACTIVE/NO_HOOK, ACTION_EXISTS/NO_ACTION) that function as validation gates.

3 / 3

Progressive Disclosure

A single self-contained file organized into clearly labeled steps and sections with no nested or external references; appropriate for a setup skill whose content should stay inline.

3 / 3

Total

12

/

12

Passed

Description

85%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.

A strong, specific description with explicit what-and-when guidance and a distinct Caliber niche. The main weakness is trigger-term breadth: triggers are somewhat narrow and state-based rather than covering the natural phrasings a user would actually say.

Suggestions

Broaden trigger terms to natural user phrasings such as 'agent config sync', 'keep CLAUDE.md up to date', or 'AI coding assistant rules' so the skill surfaces for more varied requests.

Consider adding a positive 'Use when setting up Caliber for the first time' trigger alongside the existing negative 'hooks are not yet installed' state check.

DimensionReasoningScore

Specificity

Lists multiple concrete actions in third person — 'Sets up Caliber', 'Installs pre-commit hooks', 'update automatically on every commit' — matching the multiple-specific-actions anchor rather than the domain-only level 2.

3 / 3

Completeness

Explicitly answers both what (sets up Caliber, installs hooks, syncs CLAUDE.md/Cursor/Copilot) and when via an explicit 'Use when Caliber hooks are not yet installed or when the user asks about keeping agent configs in sync' clause.

3 / 3

Trigger Term Quality

Includes relevant triggers ('keeping agent configs in sync', 'Caliber hooks are not yet installed') but coverage is narrow and state-based, missing common natural-language variations users might say; not the sparse level 1 nor the broad level 3.

2 / 3

Distinctiveness Conflict Risk

Targets a clear Caliber-specific niche with triggers tied to the named product, making it unlikely to fire for an unrelated skill.

3 / 3

Total

11

/

12

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
caliber-ai-org/ai-setup
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.