AB kirk-content-pipeline
Create KSVC-validated Twitter content from research PDFs. Content types: long threads, quick takes, breaking news, shitposts, personal commentary, victory laps. Triggers on "create content", "write thread", "make a post", "shitpost", or when working with PDFs in /Users/Shared/ksvc/pdfs. REQUIRED STEPS - (1a) Explore agents to scan PDFs, (1b) RLM for deep extraction, (1c) Cross-doc synthesis with rlm-multi, (2) KSVC holdings check (preliminary), (3) write data backbone, (4a) AUDIT with RLM verification, (4a.5) Gemini web cross-validation for FAIL/UNSOURCED inferences, (4b) Final holdings verification (ALL 7 models), (4c) Stylize with kirk-mode skill, (4d) humanizer pass, (5) save draft, (6) chart decision & generation.
Create KSVC-validated Twitter content from research PDFs.
As a process B 72/100 · Nearly there — weak spots: inputs and preconditions, execution cost
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 0
✓ No critical or high findings
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 17301 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 72/100
- 10Execution cost. Instruction body is 17301 tokens: crowds the task out of the window
- 30Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 85Steps. 221 steps, 2 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 20 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
- +4Description does not say when NOT to use the skill (false activations)
- -4Absolute local paths (C:\Users, /home/…): not portable
- -253 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +3Description length 727: enough signal without eating the budget
- +4Structure: 96 headings
- +3Step-by-step instructions: 221 items
- +3Output format is stated explicitly
- +4Has examples (69 code blocks)
- +4Reference files are cited in the instructions (3 of 5)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.