CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

add-redis-iris

Add Redis Iris to an existing AI agent in any framework (LangGraph, LangChain, OpenAI Agents SDK, Google ADK, Pydantic AI, CrewAI, or a plain loop). Use when the user asks to add Iris, Redis Agent Memory, Agent Playbooks, Context Gateway, Intent Router, or Lens to their agent, or asks which Iris product their agent needs. Detects the framework and routes to the product skill.

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

90%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 exceptionally tight, actionable router skill: dense tables, exact commands, copy-paste config for both deployment modes, and explicit guardrails in the Rules section. The sequence is clear with install-time validation and error recovery; the only structural improvement would be moving the iris.toml profile reference detail into a bundle reference file and adding an explicit post-wiring verification step.

DimensionReasoningScore

Conciseness

'Inspect, install, route. Do not rewrite the agent.' sets a maximally lean tone, and the body sustains it: framework detection and symptom-to-product mapping are compressed into tables, and every sentence carries product-specific facts ('Only the `iris` CLI reads `iris.toml`; the app reads env vars') that Claude cannot know. No padding or explanation of known concepts, matching anchor 5.

5 / 5

Actionability

Fully executable throughout: 'uv add redis-iris', the prerelease retry flag, the confirmation command 'uv run python -c "import redis_iris; print(redis_iris.__version__)"', exact import/package names in the detection table, named real APIs ('redis_iris.integrations.langgraph.attach'), and copy-paste TOML profiles covering both the cloud and self-managed common cases. Matches anchor 5.

5 / 5

Workflow Clarity

A clear numbered sequence (Find the agent → Detect the framework → Find what it lacks → Install → Route) with decision rules ('If unclear, ask once', 'convert one loop at a time') and an install validation checkpoint plus a retry loop ('If resolution fails on pre-releases, retry with --prerelease=allow'). It stops short of anchor 5 because verification after wiring the products into the agent is only implicitly delegated ('Follow each product skill') rather than stated as a checkpoint.

4 / 5

Progressive Disclosure

Good structure: short purposeful sections, and product detail is delegated one level deep to named product skills ('see each product skill'), which is the skill's disclosure mechanism. It is not anchor 5 because there are no bundle reference files at all and roughly 25 lines of iris.toml profile and env-var override reference material sit inline in what is otherwise a lean router; it is above anchor 3 because most content is appropriately placed for the router's job.

4 / 5

Total

18

/

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.

A strong description: it states what the skill does, enumerates the supported frameworks and products, and gives an explicit, trigger-rich 'Use when' clause in third person. The only softness is that a few natural user synonyms for the products (memory, tracing, cache) are not covered.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Add Redis Iris to an existing AI agent in any framework', 'Detects the framework and routes to the product skill' — with all seven frameworks and all six products enumerated. The core verb 'add' is broad, leaving minor gaps in coverage, which matches anchor 4 better than the comprehensive anchor 5.

4 / 5

Completeness

Explicitly answers both questions: what ('Add Redis Iris to an existing AI agent... Detects the framework and routes to the product skill') and when ('Use when the user asks to add Iris, Redis Agent Memory, ... or asks which Iris product their agent needs') with concrete trigger phrases. This matches anchor 5; it is not anchor 4 because the 'when' clause is already explicit and specific, not merely present.

5 / 5

Trigger Term Quality

'Use when the user asks to add Iris, Redis Agent Memory, Agent Playbooks, Context Gateway, Intent Router, or Lens to their agent' covers the natural product names a user would say. A few natural synonyms are missing (e.g. 'add memory to my agent', 'tracing'/'observability' for Lens, 'semantic cache'), so it falls just short of anchor 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

A clear niche — the Redis Iris product suite for AI agents — with distinctly named triggers (Iris, Agent Memory, Playbooks, Context Gateway, Intent Router, Lens) that no generic skill would claim. Minimal conflict risk, matching anchor 5.

5 / 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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

redis/agent-skills

Path

plugins/redis-development/skills/add-redis-iris/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.