Systems Lab

Agent skill

follow-up-management

Schedule resume touches, nurture cadences, and no-show rescue flows for not-now, out-of-office, and warm-but-not-now recipients.

slowingNeeds a keyActs undeclared478 words

Filed under Outbound email.

From devangk003/gtm-agent-skills · 32 skills · 0 · pushed 2026-06-18

What it does when it runs

Schedule resume touches, nurture cadences, and no-show rescue flows for not-now, out-of-office, and warm-but-not-now recipients. Use when the user says "schedule follow-up", "parse resume date", "no-show rescue", or "nurture this lead.

Read from the skill and the 4 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.

Keys and connectors you must supply
  • AGENTIC_APP_TOKEN
Hosts it reaches
No third-party host appears in the skill or its bundled files.
Tool permissions it declares
No allowed-tools in the frontmatter. It does act, so it runs under whatever permissions your session already grants.
Actions present in the files
shell

Ask about follow-up-management

Opens your assistant with this page's verified links already in the prompt.

Is this safe to install?ClaudeChatGPT
Adapt it to my stackClaudeChatGPT
What else do I need for it to workClaudeChatGPT
Rather ask a human? Talk to Cheetah

Install it

View source on GitHub ↗
git clone --depth 1 --filter=blob:none --sparse https://github.com/devangk003/gtm-agent-skills.git /tmp/gtm-agent-skills
git -C /tmp/gtm-agent-skills sparse-checkout set "follow-up-management"
mkdir -p ~/.claude/skills/follow-up-management
cp -R "/tmp/gtm-agent-skills/follow-up-management/." ~/.claude/skills/follow-up-management/

Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗

The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.

Before you install: this skill will not complete its job on a bare agent. It needs AGENTIC_APP_TOKEN, which you have to obtain separately.

The skill

Source on GitHub ↗

Reproduced in full from devangk003/gtm-agent-skills/blob/6b9a1b0094ffd83d6c02bc03b7ce1610661a1644/follow-up-management/SKILL.md, which is licensed MIT (skill frontmatter). 478 words, 6 headings.

Follow-Up Management

Schedule the right follow-up at the right time for not-now recipients, OOO auto-replies, nurture-parked leads, and meeting no-shows. Owns date parsing from reply text, the 30/60/90-day nurture library, and the no-show rescue flow.

When to Use

  • Not-now reply with stated resume date — schedule the resume
  • OOO auto-reply with return date — pause + resume
  • Meeting no-show — rescue flow within 24h
  • Tier-1/2 recipient parked in nurture — schedule next touch
  • Bulk schedule resume touches for not-now replies
  • User says "schedule follow-up" or "parse resume date"

Quick Reference

ConceptValue
Resume-date sourcesExplicit date → parse; implied window → resolve; no date → default 60d
Nurture cadences30-60-90-light (3 touches) / 90-180-365-deep (3 touches) / no-show-rescue (24h + 7d)
Date parsingNatural language → ISO. "Q1 2027" → 2027-01-15. "After holidays" → Jan 5. Provenance: explicit = [verified]; inferred = [unverified]
Resume channelSame as original reply unless redirect detected
No-show rescue windowWithin 24h of missed meeting; tone: low-stakes, single CTA
Capacity-cap respectResume + nurture touches count against per-channel caps

Procedure

  1. Validate inputs. Read trigger event + lead record + cadence/reply history. Confirm trigger type (not-now / OOO / nurture / no-show).
  2. Parse resume date. Extract date/window from reply text. Pattern-match phrases. Default per matrix when ambiguous. Tag provenance. See ${HERMES_SKILL_DIR}/references/date-parsing.md.
  3. Pick follow-up flow. not-now with date → single resume. not-now without → 60d. OOO → resume after return+1. nurture → 30-60-90-light. no-show → rescue. See ${HERMES_SKILL_DIR}/references/nurture-cadences.md.
  4. Generate touches. Hand off to channel skill (cold-email-sequence / linkedin-outreach) with cadence position context. Channel skill produces copy.
  5. Schedule + capacity check. Compute new touches against per-channel weekly caps. Over capacity → surface for user. Schedule via channel skill API.
  6. Update lead record. PATCH person: next_followup_at, nurture_state, cadence_state.
  7. Push to CRM + emit run summary. Per-recipient interaction:research with schedule + provenance. Run summary: triggers processed, flow distribution. See ${HERMES_SKILL_DIR}/scripts/push_to_crm.py.

Pitfalls

  • Forgetting the parsed date — ALWAYS PATCH person record with next_followup_at
  • Default 60d when reply named a specific date — honor stated date
  • No-show rescue at 7 days instead of 24 hours — window matters
  • Nurture touches that pitch — nurture is value-first; pitches trigger unsubscribes
  • Re-engaging on not-interested — hard no = exit-permanent; follow-up does NOT re-engage
  • Holiday-window resume — "Q1 2027" arriving Dec 24 → schedule Jan 5, not Dec 25

Verification

  1. Every trigger has a scheduled resume OR documented archive decision
  2. Resume dates trace to reply text or documented default
  3. Channel-skill handoffs succeeded with cadence position context
  4. Person records patched with next_followup_at + nurture_state + cadence_state
  5. Capacity checks passed at schedule time

Files bundled with it

These load only when the skill asks for them, so they cost nothing until it runs.

Other skills for the same job

Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.

Need help setting it up?

This page tells you what follow-up-management does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.

Book a call →

The directory stays free. There is nothing gated behind this.