SKILLEMALL.ai

AB reflect

Self-improvement through conversation analysis. Extracts learnings from corrections and success patterns, proposes updates to agent files or creates new skills. Philosophy: "Correct once, never again." Use when: (1) User explicitly corrects behavior ("never do X", "always Y"), (2) Session ending or context compaction, (3) User requests /reflect, (4) Successful pattern worth preserving.

ClawHub Agent Skills author: Steven Gonsalvez v2.1.0 19 files body ≈ 2 502 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process B 75/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, consistency

AnalyzerAI and agentsInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
A
97/100
safety, quality, tests
Safety 60%
95
Quality 40%
99
Run on models
none yet
Process rating
B
75/100
Nearly there
Inputs and preconditions w 11
0
When it triggers w 12
20
Consistency w 8
40
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

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
    • medium Broad scope meta-broad-allowed-tools SKILL.md:1
      Broad tool permissions pre-approved: Bash
      allowed-tools: Read Write Edit Grep Glob Bash

    Files scanned: 19. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 75/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 20When it triggers. No condition that starts the skill
    • 40Consistency. Frontmatter name (reflect) differs from the folder (reflect-learn)
    • 100Tools and files. Tools declared in frontmatter
    • 100Steps. 59 steps
    • 100Result and completion. Output format and completion criterion are stated
    • 100Failures and branches. 3 branches, has a failure section
    • 100Execution cost. Instruction body is 2502 tokens
    • 100Running it twice. Mutating operations check current state
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 11 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

    • +4Description does not say when NOT to use the skill (false activations)
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 3 example trigger phrases
    • +3Description length 389: enough signal without eating the budget
    • +4Structure: 34 headings
    • +3Step-by-step instructions: 59 items
    • +3Output format is stated explicitly
    • +4Has examples (14 code blocks)
    • +4Reference files are cited in the instructions (3 of 3)
    • +3All 4 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 99.

    External checks

    ClawHub: suspicious
    This skill has a coherent self-improvement purpose, but it can persistently change agent instructions, install a cross-session hook, and includes private developer session logs, so it needs careful review before installation.
    LLM: suspicious (high) · VirusTotal: benign · 10 Sept 2026