BC nex-deliverables
Client deliverable tracking and project management system for web agencies, design studios, marketing firms, and freelancers managing multiple simultaneous projects and client relationships. Track diverse project deliverables (websites, landing pages, logos, branding guidelines, copywriting, design assets, email campaigns, SEO optimization work, maintenance tasks, testing, documentation) through their complete lifecycle with flexible status tracking (planned, in progress, review, delivered, approved, rejected) and automatic timestamp recording. Monitor deadlines with visual urgency indicators and automatically highlight overdue items for immediate attention. Manage workload across all active clients with built-in statistics on overall delivery rates, average time-to-delivery, overdue percentages, and workload distribution. Generate professional, customizable client status update emails automatically, summarizing what's currently open, what's been recently delivered, and what's overdue to maintain transparency. Search deliverables by title, client name, deliverable type, or priority level with full-text search capabilities. Set priorities (urgent, high, normal, low) and focus on high-priority work. Support for custom deliverable types beyond presets. Perfect for Belgian agency operators who need to stay meticulously organized, communicate transparently with clients about progress, and track project commitments systematically. All deliverable data remains secure and private on your machine.
As a process C 62/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, running it twice
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 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.
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.
How to improve
- Shorten the description to 1024 characters.
- 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 Dangerous commands
cmd-shell-rcsetup.sh:84Writes to a shell startup fileecho " Add this to your ~/.bashrc or ~/.zshrc"
Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1513 chars, limit 1024 - note
description-budgetdescription takes 1513 of the ~15000-char shared budget for all skills
Process rating: all ten parameters 62/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 30 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2096 tokens
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 1513: 120–800 characters recommended
- +2Single-language instructions
- +4Structure: 22 headings
- +3Step-by-step instructions: 30 items
- +3Output format is stated explicitly
- +4Has examples (13 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 57.