autoresearch-create

Set up and run an autonomous experiment loop for any optimization target. Gathers what to optimize, then starts the loop immediately. Use when asked to "run autoresearch", "optimize X in a loop", "set up autoresearch for X", or "start experiments".

Quality

89%

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

85%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 well-structured, actionable skill body with clear sequencing, explicit validation for its autonomous batch loop, and clean organization. Minor opportunities exist to tighten motivational prose and provide a complete measure.sh example.

Suggestions

Trim motivational filler (e.g., 'Invest time making it excellent', 'The best ideas come from deep understanding, not from trying random variations') to improve token efficiency.

Add a minimal complete .auto/measure.sh example showing the shebang, set -euo pipefail, and a METRIC output line, complementing the prose description.

The 'loop forever / NEVER STOP' guidance is restated in both the opening line and the Loop Rules closing; consolidate to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient and assumes Claude's competence (no explanations of git, bash, or basic concepts), but a few motivational/padded lines like 'Invest time making it excellent' and 'The best ideas come from deep understanding, not from trying random variations' could be trimmed.	4 / 5
Actionability	Concrete commands ('git checkout -b autoresearch/<goal>-<date>', 'mkdir -p .auto') and a fully executable checks.sh example are given, but .auto/measure.sh is described in prose without a complete copy-paste example, leaving a minor gap.	4 / 5
Workflow Clarity	A clear numbered Setup sequence (1-5) is followed by explicit validation checkpoints (checks.sh runs after each passing benchmark, cannot keep failed checks, checks_failed logging) and feedback loops (confidence score, 'Don't thrash', annotate failures), which is critical for this autonomous batch operation.	5 / 5
Progressive Disclosure	The skill is a single self-contained SKILL.md with no bundle files; content is well-organized into clearly headed sections (Tools, Session files table, Setup, Loop Rules, Ideas Backlog, User Messages) with no nested references, making navigation easy.	5 / 5
	Total	18 / 20 Passed

Description

95%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, concise description that explicitly answers both 'what' and 'when' with concrete, natural trigger phrases and a clearly distinct niche. The only minor gap is that its listed actions are stages of a single workflow rather than multiple independent capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain ('autonomous experiment loop for any optimization target') and several concrete actions ('Set up and run', 'Gathers what to optimize', 'starts the loop immediately'), but they are phases of one workflow rather than distinct discrete capabilities, so it falls just below a 5.	4 / 5
Completeness	Clearly states what it does ('Set up and run an autonomous experiment loop... Gathers what to optimize, then starts the loop immediately') and when to use it ('Use when asked to...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Explicit, natural trigger phrases users would actually say are listed: 'run autoresearch', 'optimize X in a loop', 'set up autoresearch for X', and 'start experiments', covering synonyms and phrasings comprehensively.	5 / 5
Distinctiveness Conflict Risk	The 'autoresearch' / autonomous experiment loop niche is distinct, and the trigger phrases are specific to it, giving minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: davebcn87/pi-autoresearch
Path: skills/autoresearch-create/SKILL.md
Commit: 4182079

Reviewed: 2 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.