interview-debrief
Skill2 starsChanged 8 months agoMITView on GitHub
This skill should be used when the user says "I just interviewed", "debrief", "thank-you email", "how did my interview go", or "post-interview". Analyzes interview performance, reads signals, extracts lessons, and drafts a personalized thank-you — all in one flow. Supercharged with ~~transcription and ~~email.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- tusshaarpd/skillstheir own version, first seen Nov 16, 2026
- jin2004-cmd/codex-practical-skillstheir own version, first seen Nov 1, 2026
- ZoolCoder/scoutjobstheir own version, first seen Nov 1, 2026
- osamabinjannat/remote-hiring-skillstheir own version, first seen Oct 25, 2026
- ficilcom/otame4-work-skillstheir own version, first seen Aug 28, 2026
- jackhendon/pm-skillstheir own version, first seen Mar 1, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- ZoolCoder/scoutjobs★ 4same name
- ficilcom/otame4-work-skills★ 3same name
- jin2004-cmd/codex-practical-skills★ 1same name
- osamabinjannat/remote-hiring-skills★ 1same name
- jackhendon/pm-skills★ 0same name
- tusshaarpd/skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository13 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- coffee-chatSkill
- company-researchSkill
- discoverSkill
- fit-analysisSkill
- follow-upSkill
- interview-prepSkill
- mock-interviewSkill
- negotiateSkill
- offer-analysisSkill
- personalizeSkill
- pipeline-statusSkill
- write-applicationSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 10 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
10
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 30
Before asking the user anything, check if ~~transcription is connected.
- Distinctive: line 31
If yes: query recent meetings for interviews at the target company.
- Distinctive: line 32
If a transcript exists, pull it — this replaces most of the questions below.
- Distinctive: line 36
Ask these one at a time. Wait for each answer before asking the next.
- Distinctive: line 37
After gathering context, briefly confirm what you heard before analyzing.
- Distinctive: line 78
If something went poorly: address briefly with additional context
- Distinctive: line 121
If ~~transcription is connected:
- Distinctive: line 125
If ~~email is connected:
- Distinctive: line 126
Create email draft (don't send — user reviews first)
- Distinctive: line 143
Never sycophantic — confident gratitude, not gushing
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/interview-debrief
If you see unfamiliar
~~placeholders, see CONNECTORS.md.
Usage
/interview-debrief <company name>
/interview-debrief I just finished my Google PM interviewOne skill for everything after a formal interview: analyze performance, extract lessons, and draft the thank-you.
Inputs
Auto-detect from ~~transcription (if available)
Before asking the user anything, check if ~~transcription is connected. If yes: query recent meetings for interviews at the target company. If a transcript exists, pull it — this replaces most of the questions below. Tell the user: "I found your interview transcript. Let me analyze it."
Ask the user (if no transcript found)
Ask these one at a time. Wait for each answer before asking the next. After gathering context, briefly confirm what you heard before analyzing.
- "Which company and role was this for?"
- "What round? (phone screen, technical, HM, final)"
- "Who did you interview with? (name and role if known)"
- "What went well? What moment felt strongest?"
- "What stumbled? Any question that caught you off guard?"
- "Did they mention next steps or timeline?"
Also load
- output/[company]/interview-prep.md — what was prepared
- knowledge/stories/ — check if prepared stories were used effectively
- knowledge/frameworks/writing-framework.md — for thank-you tone
Produce
1. Performance Analysis
- Strong moments: what worked and why
- Weak moments: what didn't land and why
- Missed opportunities: stories or points you should have made
2. Signal Reading
- What their questions reveal about their concerns
- What their reactions suggest about your fit
- Likelihood of advancing (be honest)
3. Gap Analysis
- Questions you weren't prepared for → note for future prep
- Stories that didn't land → refine or replace
- Topics they probed deeply → they care about this
4. Next Round Prep
- What to expect in the next stage
- What to emphasize based on what resonated
- What to address based on concerns
5. Thank-You Email
- Subject line: specific, not generic
- Concise (~100-150 words)
- Reference one specific moment from the conversation
- Reinforce the strongest point from the interview
- If something went poorly: address briefly with additional context
- Close with enthusiasm for next steps
Two versions:
- Email (slightly more formal)
- LinkedIn message (shorter, if you connected)
Output Format
## Interview Debrief: [Company] — [Round]
### Performance
**Strong:** [what worked]
**Weak:** [what didn't land]
**Missed:** [stories you should have used]
### Signal Reading
**Their concerns:** [what their questions revealed]
**Your fit:** [honest assessment]
**Likelihood of advancing:** [High/Medium/Low — with reasoning]
### For Next Round
- Emphasize: [what resonated]
- Address: [concerns to get ahead of]
---
## Thank-You Email
**Subject:** [specific subject line]
[Full email text — ready to send]
---
**LinkedIn version:**
[Shorter message text]If Connectors Available
If ~~transcription is connected:
- Auto-pull transcript for moment-by-moment analysis
- Reference specific things discussed in the thank-you
If ~~email is connected:
- Create email draft (don't send — user reviews first)
- Tell user: "Draft created — review and send when ready."
If Something Goes Wrong
- User can't remember details: Work with what they have. Note: "Your debrief will be more useful with specifics — jot notes right after interviews."
- Interview clearly went badly: Be honest but constructive. Focus on what's actionable for next time.
- No interview-prep.md exists: Analyze without comparing to prepared material.
After Output
- "Track this interview?
/pipeline-status update [company] [round]" - "Have another interviewer to thank? Tell me their name"
- "Expecting another round?
/interview-prepto prep for it"
Rules
- Be honest, not reassuring — if it went badly, say so
- Focus on actionable improvements, not dwelling on mistakes
- Thank-you must feel personal, not templated
- Never sycophantic — confident gratitude, not gushing
- Reference specific conversation moments, not generic pleasantries
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

