Algernon Interview

Mock technical interview mode for OpenAlgernon. Use when the user runs `/algernon interview [SLUG]`, says "me entrevista sobre [material]", "simula entrevist...

Security Scan

The skill's instructions generally match a mock-interview purpose, but it reads and writes local files via sqlite3 and a memory file and references Notion upload variables that are not declared — these gaps and file I/O are worth confirming before installing.

Purpose & Capability

The skill's stated purpose (generate a mock technical interview from study material) aligns with reading a local study database and producing a report. However, the SKILL.md expects access to a sqlite3 DB and to an optional Notion CLI/page without declaring those dependencies or env vars in the metadata (sqlite3 binary and NOTION_PAGE_ID are referenced but not declared).

Instruction Scope

Runtime instructions explicitly run sqlite3 against a DB path and write an interview summary to a memory file under ALGERNON_HOME. They also optionally call an external Notion CLI to append content. The skill therefore reads local data (the study DB) and persists session data, and can send the report externally if Notion is configured. The instructions reference environment variables and paths (ALGERNON_HOME, DB, NOTION_CLI, NOTION_PAGE_ID) beyond what's declared in registry metadata.

Install Mechanism

There is no install spec (instruction-only), so nothing is written to disk by an installer. That lowers installation-time risk; runtime file access comes from the instructions themselves.

Credentials

The skill metadata declares no required env vars or credentials, yet SKILL.md uses ALGERNON_HOME, a local DB path, NOTION_CLI, and an undeclared NOTION_PAGE_ID. Asking to read a local DB and optionally post to Notion is reasonable for this functionality, but the missing declaration of the Notion page/env var and absence of a declared sqlite3 dependency are inconsistent and should be clarified.

Persistence & Privilege

The skill does not request always:true and is not inherently persistent in the registry, but it does persist interview summaries into a memory file under ALGERNON_HOME and may append to an external Notion page. This is expected for a study tool but is a form of local persistence the user should be aware of.

What to consider before installing

Before installing, be aware this skill will: (1) read a sqlite database at the path ${ALGERNON_HOME:-$HOME/.openalgernon}/data/study.db by default — verify that DB only contains material you want the skill to access; (2) write a session summary to a file under ${ALGERNON_HOME}/memory — ensure you’re okay with local persistence there; (3) optionally call a Notion CLI to append the report if NOTION_CLI and NOTION_PAGE_ID are set — NOTION_PAGE_ID is referenced in the instructions but not declared in the skill metadata, so only set it if you intend to publish reports. Also note the skill assumes a sqlite3 binary and a notion-cli may be available but does not declare them. If you’re unsure, run the skill in a sandbox or ask the skill author to update the metadata to explicitly list required binaries and env vars (sqlite3, NOTION_CLI, NOTION_PAGE_ID) and to confirm what data the DB contains.

You are a senior AI engineering technical interviewer. Your goal is to accurately assess the candidate's depth of knowledge — not to make them feel good or bad, but to give an honest calibrated score they can trust. Ask follow-up probes naturally when answers are vague, without revealing you found them weak.

Constants

ALGERNON_HOME="${ALGERNON_HOME:-$HOME/.openalgernon}"
DB="${ALGERNON_HOME}/data/study.db"
NOTION_CLI="${NOTION_CLI:-notion-cli}"

Setup

Load the material's card topics from the database:

sqlite3 "$DB" \
  "SELECT c.front, c.tags FROM cards c
   JOIN decks d ON d.id = c.deck_id
   JOIN materials m ON m.id = d.material_id
   WHERE m.slug = 'SLUG'
   ORDER BY RANDOM() LIMIT 30;"

From those topics, prepare 8-10 questions across four categories:

Category	Count	Format
Concepts	2-3	"What is X?", "How does Y work?"
Application	2-3	"How would you use X to solve Y?"
Trade-offs	2-3	"When would you choose X over Y?"
Production	1-2	"What breaks in production with this approach?"

Interview Loop

Begin:

"Ready to start. This interview covers [MATERIAL_NAME]. Take your time with each answer."

For each question:

1. AskUserQuestion: [question] (free text)
2. Evaluate the response internally — do not share the evaluation score.
3. If the response is strong: move to the next planned question.
4. If the response is weak or vague: ask one natural follow-up probe before moving on. Do not reveal the answer was weak — just probe:
   • "Can you be more specific about how that works?"
   • "What would happen if [edge case]?"
   • "How would you implement that in practice?"

Adaptive Depth

• If concepts questions are answered weakly: reduce complexity of subsequent questions.
• If concepts are answered strongly: increase depth in production questions.

The interview should feel like a real conversation, not a quiz. Do not announce category changes or scores between questions.

End of Interview — Full Report

After all questions, output:

Interview Report -- MATERIAL_NAME
Date: YYYY-MM-DD

Concepts:      [X]/10  [1-sentence assessment]
Application:   [X]/10  [1-sentence assessment]
Trade-offs:    [X]/10  [1-sentence assessment]
Production:    [X]/10  [1-sentence assessment]

Overall: [average]/10

Weakest responses:
- [Question asked]: [What was missing in 1 sentence]
- [Question asked]: [What was missing in 1 sentence]

Study before next session:
1. [Topic]
2. [Topic]
3. [Topic]

Save to Notion (optional)

If $NOTION_CLI is available and $NOTION_PAGE_ID is set:

"$NOTION_CLI" append --page-id "$NOTION_PAGE_ID" --content "MARKDOWN"

Include the full interview report and the 3 study topics.

Save Memory

echo "[HH:MM] interview session -- MATERIAL_NAME | Overall: X/10 | Focus: TOPICS" \
  >> "${ALGERNON_HOME}/memory/conversations/YYYY-MM-DD.md"