advisor-workflow

Cost-and-speed-optimized development workflow for a cheap fast implementing model consulting expensive advisor subagents (design-advisor, principal-advisor, quality-reviewer). Use for design-bearing or high-risk implementation - new/changed public contracts, schemas, state/lifecycle, concurrency, security, persistence, compatibility - or after repeated failed attempts. Do not invoke for trivial edits or solely because a change touches multiple files.

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

77%

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

The body is highly actionable with a clear, validated multi-step workflow and concrete templates, though it carries some restatement across its spend-policy and cost-principles sections. As a 75-line monolithic skill with no bundle files, it is well-organized but does not exploit progressive disclosure.

Suggestions

Tighten conciseness: collapse the 'Cost and latency principles' section into inline references to the spend policy and workflow steps, or trim it to only the principles not already stated, to remove restatement.

Add progressive disclosure: extract the consult-packet format template and/or the escalation-valve detail into a reference file (e.g. references/packet-format.md) and link to it from the workflow, keeping SKILL.md as a tighter overview.

Deduplicate the 'never repeat an approach without new evidence' guidance so it is stated once authoritatively and only back-referenced in the failed-attempts override and escalation valve.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence with no concept over-explanation, but the 'Cost and latency principles' section largely restates the spend policy and earlier step guidance, and 'never repeat an approach without new evidence' recurs across steps — tightening opportunities remain; not a 3 because of this restatement, not a 1 because no padding or basic-concept explanation is present.	2 / 3
Actionability	Provides a concrete consult-packet template (DECISION/ALTERNATIVES/CONSTRAINTS/...), precise routing rules, explicit thresholds ("after two distinct failed hypotheses"), and concrete tool flags ("run_in_background: true"); not a 2 because guidance is specific and immediately executable rather than pseudocode or abstract.	3 / 3
Workflow Clarity	Six numbered steps are clearly sequenced with explicit validation (step 5 runtime evidence: build/tests/dev server/browser), an escalation-valve feedback loop, and re-review/re-validate loops; not a 2 because validation checkpoints are explicit rather than implicit.	3 / 3
Progressive Disclosure	Sections are well organized (Advisers table, numbered Workflow, Cost principles) but the skill is a 75-line monolith with no reference files and inline detail (packet format, escalation valve) that could be split out; not a 3 because the under-50-line carve-out does not apply and nothing is split to one-level-deep references, not a 1 because structure is clear with no nested references.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 specific, trigger-rich, and explicitly covers both what the skill does and when to use it, with clear negative triggers for distinctiveness. Voice is appropriately third person with no first/second person.

Dimension	Reasoning	Score
Specificity	Names concrete actions ("consulting expensive advisor subagents (design-advisor, principal-advisor, quality-reviewer)") and multiple specific trigger scenarios, matching the 'lists multiple specific concrete actions' anchor; not a 2 because the actions and scenarios are comprehensive rather than partial.	3 / 3
Completeness	Explicitly answers what ("Cost-and-speed-optimized development workflow...") and when ("Use for..." / "Do not invoke for trivial edits...") with explicit triggers both directions; not a 2 because the 'when' is stated explicitly, not merely implied.	3 / 3
Trigger Term Quality	Uses natural developer terms a user would actually say — "design-bearing", "high-risk implementation", "schemas", "concurrency", "security", "repeated failed attempts" — giving good coverage; not a 2 because common variations are well represented rather than missing.	3 / 3
Distinctiveness Conflict Risk	A clear niche (advisor-consulting workflow) with distinct triggers plus an explicit negative trigger ("Do not invoke for trivial edits or solely because a change touches multiple files") makes conflict with other skills unlikely; not a 2 because the niche and exclusions are specific.	3 / 3
	Total	12 / 12 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: reactive/data-client
Path: .cursor/skills/advisor-workflow/SKILL.md
Commit: e823560

Reviewed: 1 day 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.