CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

69

Quality

84%

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

81%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 well-structured, actionable workflow with clear sequencing, explicit validation, and feedback loops for risky implementation work. It is lean and assumes Claude's competence, with only minor conciseness and disclosure improvements available.

Suggestions

Collapse the 'Cost and latency principles' section or merge its unique points into the workflow steps, since several principles restate guidance already given inline.

Consider moving the advisor table and the context-packet template into a single reference file to shorten the body and let progressive disclosure reach its top anchor.

Add one or two concrete example consult packets (filled in) so the actionability anchor for copy-paste-ready coverage of common cases is fully met.

DimensionReasoningScore

Conciseness

Dense and largely lean with no padding of concepts Claude already knows, though the 'Cost and latency principles' section partially recapitulates guidance stated earlier in the workflow and could be trimmed.

4 / 5

Actionability

Provides a copy-paste-ready context packet template (DECISION/ALTERNATIVES/CONSTRAINTS/...) and concrete numeric thresholds ('after two distinct failed hypotheses'), with only minor gaps in fully specified execution detail.

4 / 5

Workflow Clarity

Six numbered steps are clearly sequenced (Triage → Extract → Consult → Implement → Validate → End review) with explicit validation checkpoints (runtime evidence, mandatory end review) and feedback loops (escalation valve, re-review after large fixes).

5 / 5

Progressive Disclosure

A single self-contained file with well-organized headers and no nested references; slightly over the 50-line simple-skill threshold and could optionally externalize the advisor table or packet template, but the coupling is justified.

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.

A specific, well-triggered description that clearly states both capability and invocation conditions with concrete positive and negative triggers. It is distinctive and largely free of vague fluff.

DimensionReasoningScore

Specificity

Names the domain (cost-and-speed-optimized dev workflow) and concrete actions — consulting three named advisor subagents (design-advisor, principal-advisor, quality-reviewer) — with several specific trigger categories, leaving only minor coverage gaps.

4 / 5

Completeness

Explicitly answers both what (advisor-consulting workflow for a cheap implementing model) and when ('Use for design-bearing or high-risk implementation... or after repeated failed attempts'), plus a negative trigger ('Do not invoke for trivial edits...').

5 / 5

Trigger Term Quality

Includes natural developer-facing phrases ('design-bearing or high-risk implementation', 'public contracts, schemas, concurrency, security', 'repeated failed attempts', 'trivial edits') with good coverage, though a few common synonyms are absent.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (advisor-consulting orchestration with three specifically named subagents) with distinct triggers and minimal overlap risk against other skills.

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
reactive/data-client
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.