AD pullthatupjamie
PullThatUpJamie — Podcast Intelligence. A semantically indexed podcast corpus (109+ feeds, ~7K episodes, ~1.9M paragraphs) that works as a vector DB for podcast content. Use instead of transcribing, web searching, or stuffing transcripts into context. Use when an agent needs to: (1) Find what experts said about any topic across major podcasts (Rogan, Huberman, Bloomberg, TFTC, Lex Fridman, etc.), (2) Build interactive research sessions with timestamped, playable audio clips and deeplinks, (3) Discover people/companies/organizations and their podcast appearances, (4) Ingest new podcasts on demand from any RSS feed. Three-tier search strategy (title → chapter → semantic) optimizes for speed and cost. Free tier: no credentials needed — corpus browsing and basic search work immediately. Paid tier: requires a Lightning wallet (NWC connection string) to purchase credits; the payment preimage and hash become bearer credentials for authenticated requests. See Security & Trust section for credential handling guidance.
PullThatUpJamie — Podcast Intelligence.
As a process D 41/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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
-
low Risky intent
intent-offensive-securitySKILL.md:136Offensive-security / dual-use content (legitimate for authorised testing; review intended use)**No persistence or privilege escalation:** This skill has no install hooks, no `always: true`, and does not modify other skills or system config.
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 41/100
- 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
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 6 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 85Steps. 18 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1649 tokens
- 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)
- +3Description length 1024: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +4Structure: 14 headings
- +3Step-by-step instructions: 18 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.