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

76%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/ds-decision/SKILL.md

Quality

Content

70%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 content is well-structured with an explicit, checkpointed decision workflow and concrete artifact call signatures, but it is longer than necessary and fails to surface its bundled reference files. Tightening redundant sections and linking the references would materially improve it.

Suggestions

Deduplicate the action vocabulary: list canonical actions once in 'Allowed actions' and have the workflow reference that list instead of re-listing mappings and heuristics separately.

Link the bundled references from the body, e.g. under a 'References' section pointing to research-route-criteria.md and strategic-decision-template.md, so progressive disclosure is explicit rather than implicit.

Trim restated criteria lists (the route-selection and package-selection criteria overlap heavily) into one canonical list referenced where needed.

Dimension	Reasoning	Score
Conciseness	The ~390-line body restates the same action vocabulary in multiple sections (Allowed actions, workflow mapping, route heuristics) and repeats criteria lists, so while mostly efficient it includes noticeable redundancy that could be tightened.	3 / 5
Actionability	Provides concrete canonical actions, explicit `artifact.*` call signatures, verdict-to-action mappings, and a referenced JSON template, giving mostly executable guidance with minor gaps where full argument lists are omitted.	4 / 5
Workflow Clarity	A clear six-step workflow with explicit validation checkpoints (baseline-reuse completion checks, timeout expiry handling with self-resolve, quest-completion approval gating) and error-recovery feedback loops, matching the top anchor.	5 / 5
Progressive Disclosure	Two reference files exist (research-route-criteria.md, strategic-decision-template.md) but the body never links to or signals them, so most detail is inlined and navigation is only weakly implied rather than clearly structured.	3 / 5
	Total	15 / 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.

The description is concrete and trigger-rich, clearly stating both the capability and the activation conditions with domain-specific vocabulary. Its main weakness is mild overlap risk from generic transition words rather than any vagueness.

Dimension	Reasoning	Score
Specificity	Names the decision-transition domain and several concrete actions ("go, stop, branch, reuse-baseline, write, finalize, reset, or user-decision transition"), with only minor coverage gaps, matching the 'several specific actions; minor gaps' anchor.	4 / 5
Completeness	Explicitly answers both what ("explicit ... transition with reasons and evidence") and when ("Use when the quest needs...") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural trigger words users would say ("go", "stop", "branch", "reset", "finalize") plus an explicit "Use when" clause, giving good keyword coverage though a few natural synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	A clearly niched control skill with distinct decision-transition vocabulary and minimal overlap risk, though broad terms like "go/stop" could slightly overlap with general routing skills, keeping it just below the top anchor.	4 / 5
	Total	17 / 20 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: 4b35756

Reviewed: 5 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.