skill-decision-support

Present options with trade-offs for informed decision-making — use when choosing between approaches

Quality

71%

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 ./.claude/skills/skill-decision-support/SKILL.md

Quality

Content

77%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 highly actionable and workflow-clear, with concrete templates and a well-sequenced 5-phase process supported by checkpoints and worked examples. Its main weaknesses are verbosity from repeated templates/restated principles and a monolithic structure with no progressive disclosure via reference files.

Suggestions

Collapse the three Common Patterns examples into one representative worked example and reference the shared template, cutting substantial redundant length to improve conciseness.

Move the detailed presentation templates and worked examples into a reference file (e.g., references/templates.md) and keep SKILL.md as a lean overview with one-level-deep links, improving progressive_disclosure.

Trim or merge the restatement sections (Best Practices, Red Flags, Quick Reference, Bottom Line) into a single concise checklist to reduce token cost without losing guidance.

Dimension	Reasoning	Score
Conciseness	The body is well-organized but ~440 lines for an essentially single-process skill, with three near-duplicate worked examples in Common Patterns and multiple restatement sections (Best Practices, Red Flags, Quick Reference, Bottom Line) that re-cover the same core idea; it is mostly efficient in structure but includes clear redundancy that could be trimmed, fitting anchor 3 better than the 'minor instances' of anchor 4 or the concept-explanation padding of anchor 2.	3 / 5
Actionability	The skill provides complete, copy-paste-ready markdown templates with explicit fields (Pros/Cons with ✅/❌, Effort, Risk, Reversibility, Recommendation, Quick Comparison table) plus three fully worked concrete examples (caching, TypeScript vs JS, auth fix), so specific examples cover the common cases per the anchor 5.	5 / 5
Workflow Clarity	A clearly sequenced 5-phase process (Context → Generate → Analyze → Present → Support) with explicit checkpoints (AskUserQuestion in Phase 1, "Which option would you like to proceed with?" in Phase 4), a feedback loop (Phase 5 deep-dive on request), and checklists (Red Flags, Quick Reference) meets the anchor 5 for clear sequence with validation and feedback loops; this is an interactive skill so the destructive-batch cap does not apply.	5 / 5
Progressive Disclosure	Section structure is clear with logical headers (better than the minimal-structure anchor 2), but the skill is a 440-line monolith with no reference files, and the lengthy worked examples and detailed templates are content that could be split into separate reference files; the under-50-line simple-skill exception does not apply, so it sits at anchor 3 rather than the well-split anchor 4.	3 / 5
	Total	16 / 20 Passed

Description

66%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 well-formed: third-person, concise, and explicit about both what the skill does and when to use it. Its main weaknesses are a single core action (limiting specificity) and a somewhat abstract trigger clause that leaves moderate overlap risk with adjacent skills.

Suggestions

Expand the 'when' clause with concrete user utterance phrases (e.g., "use when the user says 'what are my options', 'help me decide', or asks for alternatives/trade-offs") to lift completeness and trigger-term quality toward 5.

Add a brief disambiguating boundary in the description (e.g., "not for open-ended research or implementation") to reduce conflict risk with flow-probe/flow-tangle-style skills.

Consider adding one more concrete capability verb (e.g., "compare" or "recommend") so the action list reads as several specific actions rather than one.

Dimension	Reasoning	Score
Specificity	"Present options with trade-offs for informed decision-making" names the domain and one concrete action with a clear modifier (trade-offs), matching the anchor that lists 1-2 concrete actions without comprehensive coverage; it is more specific than the generic anchor 2 ("Processes PDF files") but does not list the several distinct actions required for a 4.	3 / 5
Completeness	It explicitly states both what ("Present options with trade-offs for informed decision-making") and when ("use when choosing between approaches"), so the missing-trigger cap of 3 does not apply; the when-clause is a slightly abstract condition rather than the concrete user-utterance trigger phrases shown in the anchor 5 example, placing it at 4.	4 / 5
Trigger Term Quality	Natural user-facing terms are present ("options", "trade-offs", "decision-making", "choosing between approaches"), giving good keyword coverage; it falls short of a 5 because common synonyms like "alternatives", "choices", "pros and cons", and "help me decide" are missing.	4 / 5
Distinctiveness Conflict Risk	Options-presentation is a recognizable niche, but the description's trigger "choosing between approaches" is broad and overlaps with research and implementation skills (the body itself disambiguates these), so conflict risk is more than minor (not 4) yet the niche is more specific than the very-broad anchor 2 ("Helps with document files").	3 / 5
	Total	14 / 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: nyldn/claude-octopus
Path: .claude/skills/skill-decision-support/SKILL.md
Commit: bc76e7c

Reviewed: ~24 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.