CC billable-time-stephane-boghossian
When your bar comes asking "show me how you billed AI-assisted work" — and ABA 512, Florida 24-1, California, New York, and DC all have opinions out — you need an artifact that survives review. billable-time produces it. From your Claude Code session logs, it drafts reviewable time entries plus a printable HTML audit packet with: SHA-256 chain of evidence (source files + matter.yml + active disclosure pack + verifiable artifact self-hash), attorney identity and signature block, a bar-opinion disclosure pack with starter language for five jurisdictions, and content-aware deterministic narratives derived from filename and tool shape — never from prompt text by default. The tool refuses to bill on its own. --strict mode refuses to ship the artifact if any audit invariant fails (broad routes, missing attorney, missing/unverified disclosure). Comes as a Node CLI and a self-contained browser version (no backend; JSONL never leaves the page). 15 invariant tests verify the contract. AGPL-3.0.
When your bar comes asking "show me how you billed AI-assisted work" — and ABA 512, Florida 24-1, California, New York, and DC all have opinions out — you…
As a process C 59/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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
- 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-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Bash Read Edit Write
Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "triggers"
Process rating: all ten parameters 59/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 60Failures and branches. 2 branches
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 44 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2040 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (7 tags): a typed call is more reliable
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)
- +3Description length 999: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Structure: 9 headings
- +3Step-by-step instructions: 44 items
- +4Has examples (1 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.