follow-up
Skill2 starsChanged 8 months agoMITView on GitHub
This skill should be used when the user says "follow up on [company]", "I haven't heard back", "I got rejected", "didn't get the role", "nudge [company]", or "rejection from [company]". Handles stalled applications and rejections: draft follow-up messages, process rejections gracefully, keep doors open. Supercharged with ~~email. For post-interview thank-yous, use /interview-debrief. For networking follow-ups, use /coffee-chat.
25 other projects use a version of this.
Adopted by
Most recently taken up by
- bjoern621/claude-skillstheir own version, first seen Nov 16, 2026
- pantheon-org/tekhnetheir own version, first seen Nov 15, 2026
- Celorus/celorus-plugintheir own version, first seen Nov 15, 2026
- Jakeschincariol/whale-skilltheir own version, first seen Nov 8, 2026
- Jakeschincariol/closer-skilltheir own version, first seen Nov 8, 2026
- digitalgym/aipathway-standardstheir own version, first seen Nov 4, 2026
Used with
Projects with it also use call-prep and pipeline.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
AnthropicSkillcall-prep
Prepare for a customer or prospect call using Common Room signals. Triggers on 'prep me for my call with [company]', 'prepare for a meeting with [company]', 'what should I know before talking to [company]', or any call preparation request.
Also in 3 projects that use this
jwilgerSkillpipeline
Autonomous build-phase orchestrator with 8-stage per-slice pipeline (decompose, slice readiness review, implement via TDD pairs, three-stage code review, address feedback, mutation testing, push/CI, merge/flag). Manages slice queue (walking skeleton first, dependency ordering), dispatches TDD pairs with capability detection, enforces 5 binary quality gates with 3-cycle rework budgets and human escalation, maintains audit trail, and respects strict controller boundaries (never writes code, delegates all creative work). Supports three autonomy levels (conservative/standard/full). Use when running factory mode, orchestrating build phases, managing slice queues, or coordinating TDD pairs with review gates. Triggers on: "run the pipeline", "factory mode", "build phase", "slice queue", "quality gates", "autonomous build". NOT for: individual TDD (use tdd), standalone code reviews (use code-review), CI-only workflows (use ci-integration).
Also in 3 projects that use this
Other versions25 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 25
- n24q02m/better-email-mcp★ 38same name
- n24q02m/email★ 38same name
- Jakeschincariol/closer-skill★ 33same name
- etrebels/claude-code-growth-os★ 23same name
- alejopijuan/Claude-Code-Agency-Co-Founder★ 19same name
- Jakeschincariol/whale-skill★ 15same name
- pantheon-org/tekhne★ 10same name
- zime-skills/global★ 8same name
- zime-skills/zime-skills★ 8same name
- noticedso/skills★ 2same name
15 more not listed
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
- interview-debriefSkill
- interview-prepSkill
- mock-interviewSkill
- negotiateSkill
- offer-analysisSkill
- personalizeSkill
- pipeline-statusSkill
- write-applicationSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
15 rules. 0 are common, 15 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 21 edited versions we read keep these.
15
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 36
If available: output/[company]/fit-analysis.md, interview-prep.md
- Distinctive: line 41
After applying, no response: follow up after 5-7 business days
- Distinctive: line 42
After no response to first follow-up: one more nudge after ~5 days
- Distinctive: line 43
After two follow-ups with no response: stop.
- Distinctive: line 73
DO NOT ask why you were rejected or push back
- Distinctive: line 111
If ~~email is connected:
- Distinctive: line 112
Create as email draft (don't send — user reviews first)
- Distinctive: line 137
When the user has accepted an offer and needs to exit other processes gracefully.
- Distinctive: line 139
Ask: "Which companies do you need to withdraw from?"
- Distinctive: line 147
Leave the door open for the future
- Distinctive: line 154
Never: "I just wanted to check in" or "I hope this finds you well"
- Distinctive: line 155
Always lead with value or new information in follow-ups
- Distinctive: line 156
If application is likely dead, say so honestly
- Distinctive: line 158
Never say "it wasn't meant to be" or "everything happens for a reason"
- Distinctive: line 160
Always end with forward momentum
“Common” is measured: kept by at least 6 in 10 of the 21 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
/follow-up
If you see unfamiliar
~~placeholders, see CONNECTORS.md.
Usage
/follow-up <company name>
/follow-up I haven't heard back from Stripe
/follow-up I got rejected from GoogleTwo modes: nudge stalled applications, or process a rejection gracefully.
Inputs
- Which company/role
- Whether this is a FOLLOW-UP (no response) or REJECTION (got a no)
- pipeline-data.md — current status and timeline
- knowledge/profile.md — candidate context
- knowledge/frameworks/writing-framework.md — communication style
- For rejection: what they said, how far you got
- If available: output/[company]/fit-analysis.md, interview-prep.md
Mode 1: Follow-Up (stalled application)
Timing Rules
- After applying, no response: follow up after 5-7 business days
- After no response to first follow-up: one more nudge after ~5 days
- After two follow-ups with no response: stop. Application is cold.
Produce
Follow-Up Message (concise, ~75-100 words)
- Lead with something real — new context, relevant news, additional insight
- Restate interest briefly
- Make it easy to respond (yes/no question or clear next step)
Two versions: Email (with subject line) + LinkedIn message (shorter).
Context Note — why this follow-up is appropriate now, what risk exists, when to give up.
Mode 2: Handle Rejection
Ask the user (if details not provided)
One at a time:
- "Which company and role?"
- "What stage were you at? (applied / screened / interviewed / final)"
- "What did they say?"
Produce
1. What This Rejection Tells You
- Stage signal (what rejection at this stage typically means)
- Pattern check (is this repeated? what's emerging?)
- What was in your control vs not
2. Gracious Response (send within 24-48 hours, concise ~50-75 words)
- Thank them genuinely, express continued interest, leave the door open
- DO NOT ask why you were rejected or push back
Two versions: Email + LinkedIn message.
3. Lessons Extracted Stage-specific analysis: what to improve for next time.
4. Pipeline Update Move to Closed with date, stage, key lesson.
5. What's Next Redirect energy to active applications. Flag patterns if emerging.
Output Format
## Follow-Up: [Company]
**Context:** [Why following up now — days since last contact, what stage]
**Risk:** [What happens if you don't follow up]
### Email
**Subject:** [subject line]
[Full email text — ready to send]
### LinkedIn
[Shorter message text]
---
**Next move if no response:** [when to nudge again, or when to stop]If Connectors Available
If ~~email is connected:
- Create as email draft (don't send — user reviews first)
- Tell user: "Draft created — review and send when ready."
If Something Goes Wrong
- Application is clearly dead: Say so honestly. Don't waste the user's time crafting messages for a cold lead.
- User wants to follow up a third time: Advise against it. Explain why.
- Rejection with no details: Work with what you have; note that patterns are hard to read without specifics.
After Output
For follow-up mode:
- "Check all your pending applications?
/pipeline-status" - "If no response after this, one more nudge then move on"
- "Want to find new roles?
/discover"
For rejection mode:
- "See your active applications?
/pipeline-status" - "Want to find new roles?
/discover" - "Need to recalibrate? Paste a JD and I'll score your fit"
For withdraw/decline mode:
- "Pipeline updated.
/pipeline-statusto see your active applications" - "Want to stay connected? I'll draft a LinkedIn note to keep the relationship warm"
Mode 3: Withdraw / Decline (after accepting another offer)
When the user has accepted an offer and needs to exit other processes gracefully.
Ask: "Which companies do you need to withdraw from?"
Produce
Withdrawal Message (concise, ~50-75 words per company)
- Thank them for their time and the opportunity
- Note you've accepted another position (don't name the company)
- Express genuine interest in staying connected
- Leave the door open for the future
Two versions: Email + LinkedIn message.
Pipeline Update — move each company to Closed with status: withdrawn.
Rules
- Never: "I just wanted to check in" or "I hope this finds you well"
- Always lead with value or new information in follow-ups
- If application is likely dead, say so honestly
- For rejections: be honest but not brutal — respect that rejection hurts
- Never say "it wasn't meant to be" or "everything happens for a reason"
- Focus on what's actionable, not what's done
- Always end with forward momentum
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.

