AF agentic-delivery-skill
Create CompleteTech LLC delivery execution artifacts for approved agentic development engagements, including kickoff agendas, access checklists, project plans, milestone trackers, status updates, decision logs, risk/issue logs, change request intake, prototype review, evaluation reports, acceptance packets, launch readiness, monitoring, support, handoff, runbooks, quickstarts, closeout, post-launch review, and escalation procedures. Use after proposal/SOW or contract approval when Codex needs to run bounded agentic workflow delivery cleanly.
As a process F 25/100 · Will not run — References files that are not bundled: assets/logo.png
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
-
low Risky intent
intent-offensive-securityREADME.md:114Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Not required | Network access, credential access, persistence, privilege escalation, destructive file operations, background services, or project-system API calls. |
-
low Risky intent
intent-offensive-securitySKILL.md:113Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Not required | Network access, credential access, persistence, privilege escalation, destructive file operations, background services, or project-system API calls. |
Files scanned: 19. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: assets/logo.png
Process rating: all ten parameters 25/100
- 0Tools and files. 1 referenced file(s) missing: assets/logo.png
- 0Steps. Prose only: no discrete steps
- 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. 7 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2084 tokens
- 100Progress reporting. Reports progress
- low 10 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- +2Single-language instructions
- +3Description length 547: enough signal without eating the budget
- +4Structure: 11 headings
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +3All 2 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.