clickhouse-autoresearch-campaign

Run a ClickHouse query optimization campaign on one git branch using pi-autoresearch, dynamic lanes and hypotheses, baseline result capture, correctness checks, and stagnation-aware lane/campaign review.

Quality

72%

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 ./tools/query-performance-ai/query_performance_ai/sandboxed_autoresearch_agent/pi_plugin/skills/clickhouse-autoresearch-campaign/SKILL.md

Quality

Content

77%

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

The body is highly actionable with concrete commands, SQL, and a well-checkpointed workflow including validation and feedback loops. Its main weakness is length: dense ClickHouse profiling reference material lives inline rather than in a separate reference file.

Suggestions

Move the 'Adapter capabilities' reference material (EXPLAIN variants, system.* table catalog, ProfileEvents meanings, source-exploration tips) into a references file such as references/profiling.md, leaving a concise pointer in SKILL.md.

Confirm orchestration.md is bundled alongside SKILL.md, or fold its essential reasoning rules inline so the skill is self-contained.

Tighten the 'Adapter capabilities' section to the decisions that affect hypothesis formation, and let the SQL examples live in the external reference.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and largely free of concept-explanation fluff, but at ~260 lines it keeps substantial reference material inline (EXPLAIN variants, system-table catalog, profiling SQL) that competes for context and could be tightened.	2 / 3
Actionability	Provides copy-paste-ready bash commands with enumerated flags, concrete SQL snippets, and exact file paths — e.g. 'python3 ../../scripts/ch_campaign_init.py --workspace .clickhouse-autoresearch --query-id <id>'.	3 / 3
Workflow Clarity	The setup sequence is numbered with a feedback loop for baseline timeout (range narrowing) and explicit validation checkpoints — correctness backpressure via autoresearch_checks.py and an escalation check after every keep — plus a runtime-responsibilities checklist.	3 / 3
Progressive Disclosure	References to 'orchestration.md' are clearly signaled one level deep, but a large block of reference-style material (adapter capabilities, profiling tables, source-code exploration) is inline rather than split out, and the referenced sibling file is absent from the bundle.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 distinctive, naming concrete campaign actions and a clear niche. It is held back by missing 'when to use' guidance and trigger terms that are more internal jargon than natural user phrasing.

Suggestions

Add an explicit 'Use when…' clause, e.g. 'Use when optimizing a slow ClickHouse query on a dedicated branch, or when the user asks to tune ClickHouse query performance.'

Soften jargon in the trigger portion: surface natural phrasings like 'ClickHouse query performance', 'slow query tuning', or 'optimize a ClickHouse query' alongside 'pi-autoresearch'.

Trim 'stagnation-aware lane/campaign review' from the description to a user-facing summary and keep such internal mechanics for the body.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'baseline result capture, correctness checks, and stagnation-aware lane/campaign review' alongside running the campaign — matching the multi-action anchor.	3 / 3
Completeness	Clearly states what the skill does but has no 'Use when…' clause or equivalent explicit trigger guidance, so per the guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	Contains relevant keywords ('ClickHouse query optimization') but leans on jargon ('pi-autoresearch', 'stagnation-aware lane/campaign review') a user would rarely say, and omits common variations like 'optimize my ClickHouse query'.	2 / 3
Distinctiveness Conflict Risk	The narrow framing — 'ClickHouse query optimization campaign on one git branch using pi-autoresearch' — carves a distinct niche unlikely to trigger for unrelated skills.	3 / 3
	Total	10 / 12 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: PostHog/posthog
Path: tools/query-performance-ai/query_performance_ai/sandboxed_autoresearch_agent/pi_plugin/skills/clickhouse-autoresearch-campaign/SKILL.md
Commit: 256d8ee

Reviewed: about 13 hours 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.