ds-baseline

Use when a quest needs to attach, import, reproduce, repair, verify, compare, or publish a baseline and its metrics.

Quality

83%

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

73%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.

The body is highly actionable with a clear, well-validated workflow and good progressive disclosure into reference files. Its main weakness is verbosity from heavy rule repetition across overlapping sections.

Suggestions

Consolidate the fast-path defaults, plan/checklist requirements, and route-order guidance so each rule appears in one canonical section instead of being restated in "Quick workflow", "Fast-path first", "Required plan and checklist", and "Workflow".

Link the two orphaned reference files (codebase-audit-checklist.md, memory-playbook.md) from the relevant sections, or remove them from the bundle if unused.

Convert prose reference cues like "read `references/route-selection.md`" into markdown links and group them in a dedicated references section for easier navigation.

Dimension	Reasoning	Score
Conciseness	The ~600-line body restates the same rules multiple times (e.g., fast-path defaults appear in "Quick workflow", "Fast-path first", "Required plan and checklist", and "Workflow"), producing noticeably padded sections even though it avoids explaining basics Claude already knows.	2 / 5
Actionability	Provides copy-paste-ready, executable commands throughout (e.g., `bash_exec(mode='detach', ...)`, `uv venv --python 3.11`, `artifact.confirm_baseline(...)`, `memory.list_recent(scope='quest', limit=5)`) with concrete paths and file contracts covering the common cases.	5 / 5
Workflow Clarity	Clear four-phase sequence (analysis -> setup -> execution -> verification) with explicit validation (verification mandatory before acceptance), feedback loops (one-retry bound, then repair/blocked/decision), checklists, and explicit exit criteria.	5 / 5
Progressive Disclosure	Six real one-level-deep reference files are signaled from the overview and detail is appropriately split out, but two of eight bundle files (codebase-audit-checklist.md, memory-playbook.md) are not linked from the body and references use prose "read X" cues rather than markdown links.	4 / 5
	Total	16 / 20 Passed

Description

92%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.

The description is specific, complete, and well-scoped, clearly stating both what the skill does and when to invoke it with concrete action verbs. Its only minor gap is the absence of synonyms or file-extension trigger variants.

Dimension	Reasoning	Score
Specificity	Lists seven concrete actions ("attach, import, reproduce, repair, verify, compare, or publish") on a concrete object ("a baseline and its metrics"), matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers both what (establishes a baseline and its metrics) and when ("Use when a quest needs to attach, import, reproduce, repair, verify, compare, or publish a baseline") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good keyword coverage with framework-natural verbs (attach, import, reproduce, repair, verify, compare, publish) and the term "baseline", but lacks synonyms or file-extension variants that would push it to a 5.	4 / 5
Distinctiveness Conflict Risk	Targets a narrow, distinct niche (baseline lifecycle within a quest framework) with specific triggers, so overlap with other skills is minimal.	5 / 5
	Total	19 / 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
skill_md_line_count	SKILL.md is long (609 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: OpenLAIR/dr-claw
Path: skills/ds-baseline/SKILL.md
Commit: d51b64e

Reviewed: 6 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.