ds-decision

Use when the quest needs an explicit go, stop, branch, reuse-baseline, write, finalize, reset, or user-decision transition with reasons and evidence.

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, checkpointed workflow and concrete artifact calls, but it is verbose and re-hosts content that already lives in the bundled references without linking to them. Tightening the prose and signaling the two reference files would lift the weaker dimensions.

Suggestions

Replace the duplicated route-criteria and decision-record-shape prose (sections 3.2 and 4) with one-line pointers to references/research-route-criteria.md and references/strategic-decision-template.md, keeping only the canonical verdict/action lists inline.

Trim the 'Interaction discipline' and 'Tool discipline' sections to the few non-obvious rules, since the shared interaction/tool contract is already injected by the system prompt and restating it bloats the skill.

Cut overlapping criteria enumerations (section 3.2 lists criteria twice, and section 3.1 repeats the outline rubric) to a single consolidated list, reducing token cost without losing guidance.

Dimension	Reasoning	Score
Conciseness	The ~388-line body is thorough but heavy, restating route-selection heuristics and criteria lists that overlap the bundled reference and explaining meta-discipline (interaction/tool contract) that the shared system prompt already injects; it earns its place for most decisions but could be tightened.	2 / 3
Actionability	It provides concrete, copy-pasteable artifact calls (e.g. `artifact.record(payload={'kind': 'decision', ...})`, `artifact.submit_idea(mode='create', ...)`), a canonical verdict/action vocabulary, and an exact decision-record schema, so guidance is executable rather than abstract.	3 / 3
Workflow Clarity	The six-step Workflow (State the question → Collect evidence → Choose verdict/action → State reason → Request user input → Record durably) is explicitly sequenced, with the terminal durable-record step and quest-completion approval serving as validation checkpoints before exit.	3 / 3
Progressive Disclosure	Two real reference files exist (research-route-criteria.md, strategic-decision-template.md) but the body never signals or links them; their content (route criteria, decision-record shape) is instead duplicated inline, so structure exists but navigation/signaling is missing.	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 concise, third-person, and explicitly answers both what and when, with strong natural trigger terms and a distinct decision-transition niche. It is a strong, well-targeted description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete decision-transition actions ('go, stop, branch, reuse-baseline, write, finalize, reset, or user-decision transition') plus the qualifiers 'with reasons and evidence', naming specific capabilities rather than vague language.	3 / 3
Completeness	Opens with an explicit 'Use when the quest needs...' trigger and pairs it with the concrete actions ('go, stop, branch...'), so it clearly answers both what it does and when to invoke it.	3 / 3
Trigger Term Quality	Uses natural, user-sayable terms — 'go, stop, branch, reset, finalize' — that mirror how someone would phrase a transition request, with good coverage of the common verbs.	3 / 3
Distinctiveness Conflict Risk	The scoped vocabulary of quest-state transitions ('reuse-baseline', 'finalize', 'reset', 'user-decision') carves a clear niche unlikely to trigger for other skills, even if some terms are domain-specific.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: OpenLAIR/dr-claw
Path: skills/ds-decision/SKILL.md
Commit: 6da7f7c

Reviewed: about 8 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.