rethink

Challenge system assumptions against accumulated evidence. Triages observations and tensions, detects patterns, generates proposals. The scientific method applied to knowledge systems. Triggers on "/rethink", "review observations", "challenge assumptions", "what have I learned".

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.

A highly actionable, well-sequenced workflow with concrete code, templates, and validation gates. Its weaknesses are conceptual padding that hurts conciseness and a monolithic structure with no progressive disclosure into reference files.

Suggestions

Remove or condense the Philosophy and 'The Meta-Layer' sections; the immune-system metaphor is stated twice and restates what the workflow already implies.

Split the detailed phase specifications (e.g. the Phase 3 pattern-types table, Phase 4 proposal structure, and Edge Cases) into one-level-deep reference files referenced from a leaner overview, since the skill is far over the 50-line simple-skill threshold.

Tighten repeated prose such as 'The system is not sacred. Evidence beats intuition.' which the operational guidance already enforces.

Dimension	Reasoning	Score
Conciseness	The operational phases are efficient and actionable, but the Philosophy section, the repeated immune-system metaphor, and 'The Meta-Layer' provide conceptual padding Claude does not need and could be tightened.	2 / 3
Actionability	Provides executable bash with cross-platform stat fallback, copy-paste markdown templates for observation/methodology/changelog notes, concrete output formats, and decision tables — fully copy-paste ready.	3 / 3
Workflow Clarity	Sequences a clear six-phase workflow with explicit approval gates ('Wait for user confirmation before proceeding to 1d', 'NEVER auto-implement proposals'), quality-gate checklists, and batch handling for large backlogs.	3 / 3
Progressive Disclosure	No bundle files exist and the ~650-line body keeps detailed phase specs, pattern tables, and edge cases inline; it is well-sectioned but content that could live in one-level-deep reference files is not split out.	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.

A strong description: third-person, concrete actions, explicit natural triggers, and a clear distinctive niche. It answers what and when without fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Triages observations and tensions, detects patterns, generates proposals') rather than vague language, matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	Clearly states both what it does (triage, pattern detection, proposal generation) and when to use it via an explicit 'Triggers on' clause, satisfying the what-AND-when anchor.	3 / 3
Trigger Term Quality	Explicitly surfaces natural user phrases ('Triggers on "/rethink", "review observations", "challenge assumptions", "what have I learned"') giving good coverage of terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Carves a distinct niche (operational learning loop / methodology review) with specific triggers unlikely to collide with unrelated skills.	3 / 3
	Total	12 / 12 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 (658 lines); consider splitting into references/ and linking	Warning
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

	Total	13 / 16 Passed

Repository: agenticnotetaking/arscontexta
Path: skill-sources/rethink/SKILL.md
Commit: 2acfd5c

Reviewed: 3 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.