ac-complexity-assessor

Assess feature and project complexity. Use when estimating effort, determining spec pipeline type, calculating cost estimates, or planning resource allocation.

Quality

84%

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

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 overview with a concrete quick start, output schema, and clearly defined complexity levels and pipelines. Main gaps are the undefined quick-start variables, a pseudocode cost formula, and a generic factors section that adds little actionable information.

Suggestions

Define the Quick Start inputs concretely (e.g., show how project_dir is constructed or what file layout the assessor expects) so the example is copy-paste executable.

Replace the pseudocode cost formula with either the actual call into the script's estimation API or concrete default values for avg_tokens_per_feature, cost_per_token, session_overhead, and base_cost.

Trim or make specific the 'Complexity Factors' section by linking each factor to the thresholds or weights actually used in scripts/complexity_assessor.py.

Dimension	Reasoning	Score
Conciseness	The body is efficient and skill-specific (thresholds, pipelines, output schema) with no explanations of concepts Claude already knows. Not 5 because the 'Complexity Factors' section lists generic labels like 'Implementation difficulty' and 'Unfamiliar technologies' without thresholds or how they feed the assessment.	4 / 5
Actionability	The Quick Start is near-executable and the output JSON is concrete, but `project_dir` is undefined and the cost formula is pseudocode with undefined variables (avg_tokens_per_feature, cost_per_token, base_cost). Minor gaps, so not fully copy-paste ready.	4 / 5
Workflow Clarity	The single-action usage (instantiate assessor, await assess_project, read output) is unambiguous via Quick Start. Below 5 because there is no guidance on what input format the assessor expects or how to interpret/act on the recommendations.	4 / 5
Progressive Disclosure	Sections are well-organized at overview altitude, and the single bundle reference 'scripts/complexity_assessor.py' is a real file, one level deep, and clearly signaled under API Reference. No content needs splitting into separate files.	5 / 5
	Total	17 / 20 Passed

Description

83%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 with explicit third-person capability statements and a well-formed 'Use when' clause covering four concrete triggers. Its only weaknesses are a slightly abstract core action and a few missing natural synonyms.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("estimating effort", "determining spec pipeline type", "calculating cost estimates", "planning resource allocation") alongside the core "Assess feature and project complexity". Not 5 because the core action remains abstract and the concrete outputs (complexity levels, hour estimates) are never named.	4 / 5
Completeness	Explicitly answers both what ("Assess feature and project complexity") and when ("Use when estimating effort, determining spec pipeline type, calculating cost estimates, or planning resource allocation") with four concrete trigger phrases, matching the top anchor pattern.	5 / 5
Trigger Term Quality	Includes natural phrases users would say such as "estimating effort", "cost estimates", and "resource allocation". Missing common synonyms like "how long will this take" or "how complex is this project", so it falls short of comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	Clear niche around complexity assessment and spec pipeline selection with distinct triggers. Minor overlap risk with generic estimation or planning skills keeps it below the top anchor.	4 / 5
	Total	17 / 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: fernandezbaptiste/Skrillz
Path: skills/ac-complexity-assessor/SKILL.md
Commit: 93ed392

Reviewed: 13 hours 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.