aif-explore

Enter explore mode to investigate ideas, systems, problems, and requirements before planning. Use explicit ultra mode when the user wants a durable adaptive research bundle with an index and only the justified C4, ADR, or dependency artifacts.

Quality

66%

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/aif-explore/SKILL.md

Quality

Content

66%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 a well-structured instruction skill with excellent workflow clarity and explicit validation gates, plus sound progressive disclosure to the ultra-format reference. Its main weakness is verbosity — duplicated token lists and large illustrative example blocks that could be trimmed.

Suggestions

Remove the duplicated compatibility-token enumeration from SKILL.md and point once to references/ULTRA-RESEARCH-FORMAT.md for the canonical list.

Trim the 'Handling Different Entry Points' ASCII example blocks to one compact illustration; the stance section already conveys the behavior.

Collapse the repeated language/marker-preservation paragraphs into a single concise rule with the exception list referenced once.

Dimension	Reasoning	Score
Conciseness	The ~500-line body is noticeably verbose: the compatibility-token list is duplicated between SKILL.md and the reference, the 'What You Might Do' / 'Handling Different Entry Points' ASCII example blocks are illustrative padding, and the stance prose repeats concepts Claude already grasps.	2 / 5
Actionability	Operational guidance is concrete and mostly executable — explicit config keys and paths, the 'Parse only a leading ultra token' rule, `git branch --show-current` branch-stem computation, `mkdir -p` skeleton, numbered save options, and full RESEARCH.md templates — with only minor abstract-stance gaps.	4 / 5
Workflow Clarity	Multi-step processes are clearly sequenced with explicit validation and feedback loops: the 6-step ultra bundle creation, the 4-check Research Coherence Gate with 'Correct or qualify mismatches... then re-run', and the 10-point Bundle Integrity Gate run before appending a session.	5 / 5
Progressive Disclosure	The ultra-format detail (C4/ADR/dependency templates, bundle layout) is correctly delegated to a clearly signaled one-level-deep `references/ULTRA-RESEARCH-FORMAT.md`, but the compatibility-token list is duplicated across both files and the regular-mode skeleton/save-prompt is fully inlined, leaving minor organization gaps.	4 / 5
	Total	15 / 20 Passed

Description

67%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 specific and answers both what and when, with a clear ultra-mode niche. It is held back by jargon-heavy trigger terms and an overall 'when' clause that could be more explicit.

Suggestions

Add a concrete 'Use when...' trigger phrase for the regular mode naming natural user intents (e.g., 'Use when exploring a vague idea, scoping a problem, or weighing options before planning').

Move or soften the C4/ADR/dependency-artifact jargon so the core trigger terms users actually say are not crowded out.

Add common synonyms (e.g., 'brainstorm', 'scope', 'compare options') to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — 'investigate ideas, systems, problems, and requirements' and the ultra-mode 'durable adaptive research bundle with an index and only the justified C4, ADR, or dependency artifacts' — but the actions stay somewhat abstract rather than fully comprehensive.	4 / 5
Completeness	States both what ('investigate ideas, systems, problems, and requirements') and when ('before planning'; 'Use explicit ultra mode when the user wants a durable adaptive research bundle'), but the overall-skill 'when' could be more explicit with concrete trigger phrases.	4 / 5
Trigger Term Quality	Includes natural terms like 'explore', 'investigate', 'ideas', 'problems', 'requirements', and 'before planning', but heavy jargon ('durable adaptive research bundle', 'C4, ADR, dependency artifacts') crowds out common synonyms a user would actually say.	3 / 5
Distinctiveness Conflict Risk	The ultra bundle niche (index + justified C4/ADR/dependency artifacts) and 'before planning' framing distinguish it from sibling skills, though 'investigate ideas, systems, problems' is broad enough to overlap with general exploration or planning skills.	4 / 5
	Total	15 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (506 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: lee-to/ai-factory
Path: skills/aif-explore/SKILL.md
Commit: e144f95

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.