autonomous-investigation

The protocol behind every investigation skill. Use when AI research must proceed without you: search-plan gate, Fact/Inference/Assumption labels, confidence stacking, diffable outputs.

Quality

81%

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

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable protocol with clear workflows; its weaknesses are minor rhetorical padding and three in-text references whose target files are missing from the bundle.

Suggestions

Add the missing bundle files (template.md, examples/protocol-in-action.md, examples/protocol-in-action-industrial.md) so the signaled progressive disclosure is actually delivered.

Trim the aphorisms and "Why it teaches" asides, or consolidate them into a single short rationale line per clause.

Verify the sibling-skill reference paths (../intelligence-collection-disciplines/SKILL.md, ../workshop-facilitation/SKILL.md) resolve from the bundle's installed location.

Dimension	Reasoning	Score
Conciseness	The body is dense and purposeful rather than explaining known concepts, but aphorisms ("Research without a decision is a hobby", "an opinion wearing a badge") and repeated "Why it teaches:" asides are rhetorical padding that could be trimmed.	2 / 3
Actionability	Concrete, specific, copy-paste-ready guidance throughout — "hard cap (usually 3)", "3-bullet plan", "exactly 4 numbered next options", and an 8-step agent procedure — fully actionable for an instruction-only protocol skill.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced with explicit validation checkpoints (search-plan gate, question-budget gate, Final Step block) and error-recovery guidance, matching the clear-sequence-with-checkpoints anchor.	3 / 3
Progressive Disclosure	References are well-signaled in text with one-level-deep link descriptions, but the referenced files (template.md, examples/protocol-in-action.md, examples/protocol-in-action-industrial.md) do not exist in the bundle, so the split is promised but not delivered.	2 / 3
	Total	10 / 12 Passed

Description

85%

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 with an explicit use-when trigger and concrete named mechanisms; its only weakness is leaning on protocol-internal vocabulary that users are unlikely to voice verbatim.

Suggestions

Add user-natural phrasing to the trigger, e.g. "Use when running competitive scans, market research, or any investigation on a schedule or without you present".

Soften jargon by glossing at least one term in plain language (e.g. "Fact/Inference/Assumption labels (tell facts from the AI's guesses)").

Dimension	Reasoning	Score
Specificity	Lists multiple concrete named mechanisms — "search-plan gate, Fact/Inference/Assumption labels, confidence stacking, diffable outputs" — rather than vague language, matching the multiple-specific-actions anchor.	3 / 3
Completeness	Clearly answers both what ("The protocol behind every investigation skill") and when via an explicit "Use when…" clause, satisfying the both-what-and-when anchor.	3 / 3
Trigger Term Quality	"Use when AI research must proceed without you" is a natural trigger, but the feature list ("confidence stacking", "diffable outputs") relies on the protocol's internal jargon rather than terms a user would naturally say, so common variations are missing.	2 / 3
Distinctiveness Conflict Risk	The niche — research that proceeds without the user — is clearly distinct from interactive skills and unlikely to trigger for the wrong skill.	3 / 3
	Total	11 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 3 missing, 2 suspicious	Warning

	Total	14 / 16 Passed

Repository: deanpeters/Product-Manager-Skills
Path: skills/autonomous-investigation/SKILL.md
Commit: 9971018

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.