SKILLEMALL.ai
GitHub ↗ RU Sign in

DD precc

Predictive Error Correction for Claude Code — corrects bash commands before execution, predicts token costs via a trained ML oracle, and captures opt-in counterfactual telemetry

Not recommendedcritical or high security findings · low grade D
ClawHub Claude Code author: Yijun Yu v0.3.111 MIT-0 2 files body ≈ 1 385 tokens Open the sourceclawhub.ai↗ analyzed 8 d ago

Predictive Error Correction for Claude Code — corrects bash commands before execution, predicts token costs via a trained ML oracle, and captures opt-in…

As a process D 48/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureGitHubSoftware developmenttype 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
D
74/100
safety, quality, tests
Safety 60%
77
Quality 40%
69
Run on models
none yet
Process rating
D
48/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

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

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 2

  • high Dangerous commands cmd-pipe-to-shell SKILL.md:101
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    curl -fsSL https://peria.ai/install.sh | bash
Medium and low: 1
  • medium Broad scope meta-requests-env-secret SKILL.md:1
    Skill asks the runtime to inject credential env vars into its sandbox: PRECC_LICENSE_KEY — verify each one is needed for the stated purpose
    required_environment_variables: PRECC_LICENSE_KEY

Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • note frontmatter-key unknown frontmatter key "emoji"
  • note frontmatter-key unknown frontmatter key "homepage"
  • note frontmatter-key unknown frontmatter key "os"
  • note frontmatter-key unknown frontmatter key "env"
  • note frontmatter-key unknown frontmatter key "dependencies"
  • note frontmatter-key unknown frontmatter key "links"

Process rating: all ten parameters 48/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 20When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
  • 100Steps. 22 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1385 tokens
  • 100Running it twice. No mutating operations
  • 100Progress reporting. Reports progress

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
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 177: enough signal without eating the budget
  • +4Structure: 13 headings
  • +3Step-by-step instructions: 22 items
  • +4Has examples (5 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.

External checks

ClawHub: suspicious
The skill is not proven malicious, but it asks users to run a mutable remote installer that adds a persistent Claude hook capable of rewriting future Bash commands and using broad local history/context data.
LLM: suspicious (high) · 12 Sept 2026