result-to-claim

Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing. Codex MCP evaluates results against intended claims and routes to next action (pivot, supplement, or confirm). Use after experiments finish — before writing the paper or running ablations.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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.

A thorough, well-sequenced verdict-gate workflow with strong validation checkpoints and concrete tool calls. Its main weakness is conciseness — the body is long with prose and commentary that could be trimmed — and some wiki-routing guidance remains pseudocode-like.

Suggestions

Trim philosophical prose and inline bash commentary (e.g., the 'DRIVES, not ACQUIT' aside and Policy B notes) to tighten conciseness toward a lean operational reference.

Replace the pseudocode-style wiki routing block ('for each claim resolved by this verdict...') with concrete, copy-paste-ready commands or a single parameterized script invocation.

Factor the repeated helper-resolution bash preamble (shared between Step 1.5 and Step 5) into a referenced helper script to reduce duplication and improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The ~300-line body is mostly operational but carries philosophical prose ('a deterministic gate DRIVES, it does not ACQUIT') and lengthy inline bash commentary that could be tightened; not a 4 because several explanatory passages pad rather than instruct.	3 / 5
Actionability	Provides a concrete Codex MCP call with model/config, a full prompt template, and exact research_wiki.py CLI flags; not a 5 because the wiki routing block uses pseudocode-style control flow ('for each claim resolved by this verdict') and unfilled placeholders.	4 / 5
Workflow Clarity	Steps 1 through 5 are clearly sequenced with explicit validation checkpoints (1.5 evidence pre-check, 3.5 integrity audit), feedback loops (re-run after supplementary experiments), and a fail-closed fallback chain with routing checklist.	5 / 5
Progressive Disclosure	Well-sectioned body with clearly signaled one-level-deep references to shared-references/*.md via markdown links; not a 5 because no bundle files exist and the repeated helper-resolution bash blocks could be factored out, leaving minor organization gaps.	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.

A strong, specific description that cleanly states both capability and trigger context with concrete routing actions. Trigger-term coverage is solid but narrow to the research workflow, leaving minor room for synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'judge what claims the results support, what they don't, and what evidence is still missing', 'evaluates results against intended claims', and 'routes to next action (pivot, supplement, or confirm)' — giving comprehensive coverage of the skill's behavior.	5 / 5
Completeness	Explicitly answers both what (judge/evaluate/route claims) and when ('Use when experiments complete', 'Use after experiments finish — before writing the paper or running ablations') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrases appear ('Use when experiments complete', 'Use after experiments finish — before writing the paper or running ablations') but coverage is confined to the research domain and misses common synonyms; not a 5 because no broader/natural variations are present.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — a verdict-bearing post-experiment claim gate with distinct triggers (after experiments, before paper/ablations) — making it unlikely to fire for unrelated skills.	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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 3 suspicious	Warning

	Total	13 / 16 Passed

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
Path: skills/result-to-claim/SKILL.md
Commit: f4f20f9

Reviewed: 1 day 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.