CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ai-architecture-review

Reviews RAG flows, context assembly, model routing, structured outputs, safety filters, provenance, fallbacks, evals, cost, and latency. Use during retrieval or answer generation changes.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.cursor/skills/ai-architecture-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 lean, well-structured review checklist that earns its tokens with repo-specific guardrails (protected surfaces, eval-canary requirements, confirmation boundaries) rather than generic explanation. The main gaps are a few what-not-how verification bullets and unstated error-recovery loops within the checklist steps.

Suggestions

For the vaguer checklist bullets, add the concrete check or command: e.g. how to inspect routing rules via RAG_PROVIDER_MODE, or which script/test verifies schema conformity and safety filters.

State what to do when a check fails (e.g. flag the finding in the PR review comment vs. block the change), giving each checklist step an explicit feedback loop.

Trim the opening sentence, which duplicates the frontmatter description's trigger information.

DimensionReasoningScore

Conciseness

The body is an info-dense checklist with repo-specific paths, env vars, and file pointers rather than explanations of concepts Claude already knows. Minor trimming is possible (the opening sentence restates the description, and the protocol prose in section 0 could be tightened), matching anchor 4 rather than the every-token-earns-its-place anchor 5.

4 / 5

Actionability

Gives concrete, executable guidance: exact files ('AGENTS.md # RAG ranking protection', 'docs/rag-behaviour/', 'ragRankingPatterns in scripts/pr-policy.mjs'), env vars ('RAG_PROVIDER_MODE', 'OPENAI_ANSWER_TIMEOUT_MS'), and concrete artifacts to produce ('Write a PR RAG impact: line', 'post one Review record comment'). Some checklist bullets (e.g. hybrid search, safety filters) state what to verify but not how, keeping it below anchor 5.

4 / 5

Workflow Clarity

A clear numbered checklist sequence with real checkpoints: read-before-editing gates, 'Flag the touch to the user before editing', a required live eval-canary before/after pair ('Offline-green alone is not enough'), and the provider-confirmation boundary. It falls short of anchor 5 because recovery/error-handling loops are not spelled out for each check.

4 / 5

Progressive Disclosure

The skill is under 50 lines, has no bundle files, and is organized into well-labeled sections (protocol, protected surfaces, three numbered review areas) — per the rubric's simple-skill exception, well-organized sections alone merit a 5 here. External file references (AGENTS.md, docs/) are repo artifacts, clearly signaled and one level deep.

5 / 5

Total

17

/

20

Passed

Description

75%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 solid description that clearly scopes an AI/RAG architecture review domain with an explicit 'Use during...' trigger clause. Its main limitation is reliance on a single generic verb ('Reviews') over an enumerated object list, and thinner trigger-phrase coverage than the strongest examples.

Suggestions

Vary the verbs to name distinct concrete actions, e.g. 'Reviews RAG flows and retrieval ranking, audits context assembly and model routing, validates structured outputs and safety filters, traces provenance, and benchmarks evals, cost, and latency.'

Enrich the when-clause with concrete trigger phrases users would naturally say: 'Use when changing retrieval, RAG pipeline, LLM integration, prompt/context assembly, or answer generation code, or when the user mentions RAG, retrieval quality, hallucinations, or citations.'

Add common synonyms such as 'retrieval-augmented generation', 'RAG pipeline', 'LLM integrations', and 'grounding' to improve natural-keyword coverage.

DimensionReasoningScore

Specificity

Lists ~10 concrete review targets ('RAG flows, context assembly, model routing, structured outputs, safety filters, provenance, fallbacks, evals, cost, and latency'), giving broad domain coverage. It stays at 4 rather than 5 because the single generic verb 'Reviews' provides less concrete action differentiation than anchor-5 examples that use multiple specific verbs.

4 / 5

Completeness

Explicitly answers both what ('Reviews RAG flows, context assembly, ... cost, and latency') and when ('Use during retrieval or answer generation changes'). The when-clause is clear but terse and less trigger-rich than anchor 5's 'concrete trigger phrases', so 4 fits best.

4 / 5

Trigger Term Quality

Includes natural phrases users would plausibly say such as 'RAG flows', 'retrieval', 'answer generation', 'model routing', and 'evals'. Common synonyms and variations ('RAG pipeline', 'retrieval-augmented generation', 'LLM', 'context engineering') are missing, matching anchor 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

The RAG/LLM architecture-review niche ('RAG flows', 'model routing', 'provenance', 'evals') is well distinguished from most skills. There is minor overlap risk with a generic code-review or RAG-implementation skill, matching anchor 4 rather than the minimal-conflict anchor 5.

4 / 5

Total

16

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

referenced_paths_exist

Referenced path issues: 1 possibly missing (scripts/pr-policy.mjs)

Warning

Total

14

/

16

Passed

Repository

BigSimmo/PsychSift

Path

.cursor/skills/ai-architecture-review/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.