CD automate-feishu-invoice-approval
Scaffold, configure, validate, run, and maintain a Feishu/Lark invoice approval bot that uses Codex vision, validates buyer headers, blocks risky individual-seller equipment invoices and inconsistent tax amounts, auto-selects the closest expense category, drafts the approval reason, sends an interactive confirmation card, and submits only after the original uploader confirms. Use for building or troubleshooting Feishu invoice-to-approval workflows, invoice risk gates, approval form mappings, dry-run tests, card callbacks, and duplicate protection.
Scaffold, configure, validate, run, and maintain a Feishu/Lark invoice approval bot that uses Codex vision, validates buyer headers, blocks risky…
As a process D 35/100 · Unfinished process — References files that are not bundled: scripts/setup-lark.sh, scripts/run.sh
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- The text references files that are not there: add them or drop the references.
- 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
✓ No critical or high findings
Medium and low: 2
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Read Write Edit Bash Glob Grep
-
low Exfiltration
read-dotenvreferences/setup.md:28Reads a .env filecp .env.example .env
Files scanned: 29. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: scripts/setup-lark.sh - warning
missing-refreference to a missing file: scripts/run.sh
Process rating: all ten parameters 35/100
- 0Tools and files. 2 referenced file(s) missing: scripts/setup-lark.sh, scripts/run.sh
- 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
- 30Running it twice. 2 mutating operations with no state check
- 100Steps. 28 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1063 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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 553: enough signal without eating the budget
- +4Structure: 5 headings
- +3Step-by-step instructions: 28 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.