SKILLEMALL.ai
RU Sign in

AB pg

Tunes, designs, and operates PostgreSQL: slow queries, indexes, schemas, migrations, vacuum, locks, replication, backups. Use when writing Postgres SQL or psql, designing tables and indexes, reading an EXPLAIN plan, running DDL or a migration against a live table, or when a query suddenly got slow, a table keeps growing while rows stay flat, autovacuum cannot keep up, "too many clients already" appears, a replica lags, deadlocks and lock waits pile up, pg_wal fills the disk, or an upgrade, a restore, or a partitioning plan is on the table. Covers connection pooling and PgBouncer, full-text, trigram and pgvector search, JSONB, roles and row-level security, PITR, extensions, and managed Postgres (RDS, Aurora, Cloud SQL, Neon, Supabase). Not for cross-engine SQL portability or ORM-level modeling.

ClawHub Agent Skills author: Iván v1.0.3 MIT-0 30 files body ≈ 4 977 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process B 66/100 · Nearly there — weak spots: inputs and preconditions, progress reporting

GeneratorPostgreSQLSupabaseInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
92/100
safety, quality, tests
Safety 60%
99
Quality 40%
81
Run on models
none yet
Process rating
B
66/100
Nearly there
Inputs and preconditions w 11
0
Progress reporting w 2
0
When it triggers w 12
50
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 1

    ✓ No critical or high findings

    Medium and low: 1
    • low Risky intent intent-offensive-security backup-restore.md:45
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | Ransomware / malicious operator | Immutable or write-once storage for archives; credentials that can write but not delete |

    Files scanned: 30. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "slug"
    • note frontmatter-key unknown frontmatter key "homepage"
    • note frontmatter-key unknown frontmatter key "changelog"

    Process rating: all ten parameters 66/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 50When it triggers. No condition that starts the skill
    • 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 70Execution cost. Instruction body is 4977 tokens
    • 100Steps. 70 steps
    • 100Failures and branches. 3 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Running it twice. Mutating operations check current state
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 13 top-level sections: this looks like several domains in one skill

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +3Description length 804: 120–800 characters recommended
    • +4No input/output examples
    • +1No license
    • +2Single-language instructions
    • +4Description says when NOT to use the skill
    • +4Structure: 13 headings
    • +3Step-by-step instructions: 70 items
    • +3Output format is stated explicitly

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.

    External checks

    ClawHub: clean
    This is a coherent PostgreSQL operations skill with disclosed local preference storage and safety-oriented database guidance, though users should be mindful of logging and saved memory.
    LLM: benign (high) · VirusTotal: · 25 Jul 2026