evaluate-sdlc-layers

Validate and iterate on the SDLC Layer Separation Architecture implementation across the check categories defined in its Evaluation Checklist — cross-references, doc completeness, knowledge-explorer layer filters, research entry metadata, integration points, and plan consistency. Produces a structured findings report and optionally applies safe fixes. Use when validating a first-pass implementation, before claiming layer work complete, auditing layer docs or schema, or running --dry-run to preview findings without changes.

Quality

81%

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

75%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 evaluation skill: a concrete checklist with runnable commands, explicit evidence requirements, a defined report format, and a fix/re-run iteration loop. The main gaps are dependence on an "attached plan" that is not bundled with the skill, some repetition of file paths across sections, and references that point outside the skill directory.

Suggestions

Replace the "attached plan" dependency in section 6 with a concrete, bundled source (e.g., a plan file path or a checklist of expected deliverables) so the consistency check is self-contained.

Consolidate the file paths repeated across sections 1, 2, and 5 into a single expected-files table to cut redundancy and token cost.

Move the "Experiments" section (external git clone URL) into a reference file or drop it, and point the References section at bundled, one-level-deep files where possible.

Dimension	Reasoning	Score
Conciseness	The body is a lean checklist of concrete paths and commands with an explicit output format; every section earns its place. Not 5 because paths are repeated across sections 1, 2, and 5, and the "Experiments" section (git clone URL for a side repo) is tangential to the evaluation workflow.	4 / 5
Actionability	Mostly executable: exact file paths to check, runnable commands ("uv run research/knowledge-explorer.py list --layer 0"), and grep-based evidence instructions. Not 5 because "compare File and Directory Changes table to actual files" depends on an "attached plan" that is not bundled or accessible, and a few checks ("references layer model") specify phrases but no command.	4 / 5
Workflow Clarity	Clear sequence: six ordered check categories with PASS/FAIL/SKIP recording, a specified report format, and an explicit feedback loop ("Re-run: After fixes, re-run evaluation to confirm improvements"). Not 5 because checkpoint guidance for distinguishing SKIP vs FAIL vs a crashed check is thin, and the plan-consistency check hinges on an external artifact.	4 / 5
Progressive Disclosure	Well-organized sections (Arguments, Evaluation Checklist, Output Format, Iteration, References) with each check category clearly separated; the skill ships no bundle files, so structure stands on its own. Not 5 because the References section points to repo-external paths ("../../../plugins/development-harness/...") rather than one-level-deep bundled references, which cannot be verified from the skill directory.	4 / 5
	Total	16 / 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 that names its niche, enumerates the specific check categories, states the outputs (findings report, optional safe fixes), and provides an explicit "Use when..." trigger clause. The only weakness is a slightly abstract opening verb and a few missing natural synonyms.

Dimension	Reasoning	Score
Specificity	Enumerates concrete actions across six check categories ("cross-references, doc completeness, knowledge-explorer layer filters, research entry metadata, integration points, and plan consistency"), plus "Produces a structured findings report and optionally applies safe fixes". Not 5 because the opening "Validate and iterate on the ... implementation" is somewhat abstract and delegates the actual check detail to the body's Evaluation Checklist.	4 / 5
Completeness	Explicitly answers both: what ("Validate and iterate on the SDLC Layer Separation Architecture implementation across the check categories ... Produces a structured findings report and optionally applies safe fixes") and when ("Use when validating a first-pass implementation, before claiming layer work complete, auditing layer docs or schema, or running --dry-run") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural usage phrases are present ("validating a first-pass implementation", "before claiming layer work complete", "auditing layer docs or schema", "running --dry-run") and match how a user would phrase the need. Not 5 because common synonyms like "review the layers", "check the docs", or "lint" are absent.	4 / 5
Distinctiveness Conflict Risk	A clear niche ("SDLC Layer Separation Architecture") with domain-specific triggers (layer docs, schema auditing, --dry-run previews) makes it highly distinguishable from generic validation or documentation skills; minimal conflict risk.	5 / 5
	Total	18 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 3 suspicious	Warning
referenced_paths_exist	Referenced path issues: 2 missing, 2 deeper-than-1-level	Warning

	Total	13 / 16 Passed

Repository: Jamie-BitFlight/claude_skills
Path: .claude/skills/evaluate-sdlc-layers/SKILL.md
Commit: 3e0b2af

Reviewed: 3 days 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.