AB office-hour-legends
Legends - run a YC-style office hours session simulated by a specific YC partner or alumnus of your choice. Drop markdown persona files (identity.md, soul.md, skills.md, voice.md) into personas/<name>/ and this skill will load them, adopt the legend, and run the office-hours workflow through their lens. Supports Fathom transcript review - pull in a meeting recording and have the legend review your pitch, investor call, or customer conversation with timestamped feedback. Use when asked to "legends", "office hour legends", "office hours with <name>", "brainstorm with <legend>", "review my pitch", "review my transcript", or "what would <name> say about this".
As a process B 67/100 · Nearly there — 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 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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Broad scope
meta-agent-memory-dumppersonas/dalton-caldwell/identity.mdAgent memory / workspace files bundled with the skill (22) — likely a workspace dump with personal data or tokenspersonas/dalton-caldwell/identity.md, personas/dalton-caldwell/soul.md, personas/garry-tan/identity.md, personas/garry-tan/soul.md, personas/jessica-livingston/identity.md
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Bash Read Grep Glob Write Edit AskUserQuestion WebSearch WebFetch Bash(~/.claude/skills/bookface/bookface-search.sh:*) Bash(hn:*)
Files scanned: 60. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 67/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 17 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 4580 tokens
- 85Steps. 63 steps, 1 vague phrases
- 100Tools and files. Tools declared in frontmatter
- 100Failures and branches. 16 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- low 16 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (5 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
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 664: enough signal without eating the budget
- +4Structure: 25 headings
- +3Step-by-step instructions: 63 items
- +3Output format is stated explicitly
- +4Has examples (12 code blocks)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 95.