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.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

82%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.

The body is a highly actionable, idempotent onboarding workflow: every step checks state first, commands are executable with fallback paths, and user-facing messages are scripted. Its weaknesses are minor — a bit of inline YAML and commentary that could be trimmed or split out, and only implicit error-recovery guidance.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean check-then-act commands with little concept explanation, but includes minor padding ("faster for daily use since the pre-commit hook runs on every commit", "(This prompts for the value securely via stdin)") and a ~25-line inlined workflow YAML. This matches the efficient-with-minor-trimmables anchor rather than the every-token-earns-its-place anchor.	4 / 5
Actionability	Every step gives copy-paste-ready commands with fallbacks (npx, NO_NODE, NO_GH) and exact user-facing messages (e.g. `npm install -g @rely-ai/caliber`, `$CALIBER init --auto-approve --agent claude,cursor`, `gh secret set ANTHROPIC_API_KEY`), fully covering the common cases.	5 / 5
Workflow Clarity	Five explicitly sequenced steps each validate current state before acting (HOOK_ACTIVE/NO_HOOK, ACTION_EXISTS/NO_ACTION, score thresholds), giving clear checkpoints. Error-recovery loops are implicit rather than explicit (e.g. what to do if `hooks --install` or `refresh` fails), matching the most-checkpoints-present anchor; the destructive/batch cap does not apply since no destructive or batch operations are instructed.	4 / 5
Progressive Disclosure	A single-file skill with no bundle files and well-organized sections (Instructions, per-step headers, Summary, When to trigger/not to trigger). The inlined GitHub Action YAML is the one piece of content that arguably belongs in an assets/ file, a minor organization gap matching the good-structure anchor.	4 / 5
	Total	17 / 20 Passed

Description

87%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.

The description is well-crafted: concrete actions, explicit use-when triggers, third-person voice, and a distinct niche. It is concise while covering what the skill does and when it applies; the only minor gap is slightly broader action coverage of the full setup flow.

Dimension	Reasoning	Score
Specificity	"Sets up Caliber for automatic AI agent context sync. Installs pre-commit hooks so CLAUDE.md, Cursor rules, and Copilot instructions update automatically" names the domain plus several concrete actions and specific artifacts. It falls just short of comprehensive (the init, scoring, and refresh flows are unmentioned) and is clearly above the 1-2-concrete-actions anchor.	4 / 5
Completeness	It explicitly answers what ("Installs pre-commit hooks so CLAUDE.md, Cursor rules, and Copilot instructions update automatically on every commit") and when ("Use when Caliber hooks are not yet installed or when the user asks about keeping agent configs in sync") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Terms like "Caliber hooks", "pre-commit", "CLAUDE.md", "Cursor rules", "Copilot instructions", and "keeping agent configs in sync" are phrases users would naturally say. A few natural variations (e.g. "set up Caliber", "AI context") are missing, matching the good-but-not-comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	"Sets up Caliber" carves out a clear niche with product-specific triggers (Caliber hooks, agent config sync) that are unlikely to fire for any other skill.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

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: caliber-ai-org/ai-setup
Path: .agents/skills/setup-caliber/SKILL.md
Commit: f5dbc00

Reviewed: 14 days ago

Table of Contents

Discovery Implementation Validation

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.