agentleFS
palashjain95palashjain95/jobhunter/.claude/skills/pipeline-status/SKILL.md

pipeline-status

Skill2 starsChanged 8 months agoMITView on GitHub

This skill should be used when the user asks about "pipeline", "what's my status", "what should I be doing", "track [company]", or "what's next". Shows the application pipeline dashboard, adds roles, updates status, and surfaces prioritized next actions. Supercharged with ~~calendar for upcoming interviews.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Add new application to pipeline-data.md with date applied, source, contact.

    line 70
  2. Distinctive:

    If ~~calendar is connected:

    line 107
  3. Distinctive:

    Check next 7 days for interview-like events

    line 108
  4. Distinctive:

    Add Upcoming Interviews section to dashboard

    line 109
  5. Distinctive:

    No pipeline-data.md exists: Create it. "Starting your pipeline tracker now."

    line 113
  6. Distinctive:

    Application status is unclear: Ask the user to clarify.

    line 115
  7. Very specific:

    No response 5+ days → "Follow up?

    line 119
  8. Distinctive:

    Always suggest the exact next action

    line 129

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/pipeline-status

If you see unfamiliar ~~ placeholders, see CONNECTORS.md.

Usage

/pipeline-status
/pipeline-status add Stripe Senior PM
/pipeline-status update Google technical
/pipeline-status followup Stripe

How It Works

┌─────────────────────────────────────────────────────────┐
│                   PIPELINE STATUS                        │
├─────────────────────────────────────────────────────────┤
│  /pipeline-status           → Full dashboard             │
│  /pipeline-status add       → Add new application        │
│  /pipeline-status update    → Update status              │
│  /pipeline-status followup  → Draft follow-up message    │
│                                                          │
│  + ~~calendar: show upcoming interviews, flag unprepped  │
├─────────────────────────────────────────────────────────┤
│  🔴 Needs Action Today                                   │
│  🟡 Watch List                                           │
│  🟢 Active — Waiting                                     │
│  ⚫ Closed                                               │
└─────────────────────────────────────────────────────────┘

Inputs

  • pipeline-data.md at project root — source of truth
  • knowledge/profile.md — for follow-up tone
  • Arguments: none (full status), or "add/update/followup [company] [details]"

Commands

/pipeline-status (no args) — Full Dashboard

CompanyRoleStatusLast ActionNext ActionDue

Grouped by priority:

  • Needs Action Today — overdue for follow-up or pending tasks
  • Watch List — something happening or due soon
  • Active — Waiting — in progress, no action needed
  • Closed — rejected, withdrawn, declined

Plus:

  • This Week's Priority — single most important action
  • Risk Flags — going cold or needs urgent attention
  • Pattern Observations — if consistently failing at a stage, flag it

/pipeline-status add [company] [role]

Add new application to pipeline-data.md with date applied, source, contact.

/pipeline-status update [company] [status]

Status options: applied | recruiter-screen | technical | hiring-manager | final | offer | negotiating | accepted | rejected | withdrawn | cold

/pipeline-status followup [company]

Draft follow-up using timing rules (5-7 days, then 5 more, then stop).

Output Format

## Pipeline Dashboard
*Last updated: [date]*

### 🔴 Needs Action Today
| Company | Role | Status | Next Action | Due |
|---------|------|--------|-------------|-----|
| Stripe | Senior PM | Applied | Follow up | Today |

### 🟡 Watch List
| ... |

### 🟢 Active — Waiting
| ... |

### ⚫ Closed (last 30 days)
| ... |

---

**This week's priority:** Follow up with Stripe — it's been 7 days.
**Risk flag:** Google application going cold — no response in 12 days.
**Pattern:** 3 rejections at screen stage — consider refining your pitch.

If Connectors Available

If ~~calendar is connected:

  • Check next 7 days for interview-like events
  • Add Upcoming Interviews section to dashboard
  • Flag any interview without a corresponding interview-prep.md

If Something Goes Wrong

  • No pipeline-data.md exists: Create it. "Starting your pipeline tracker now."
  • Pipeline is empty: Suggest /discover to find roles.
  • Application status is unclear: Ask the user to clarify.

After Output

Contextual next steps based on pipeline state:

  • No response 5+ days → "Follow up? /follow-up [company]"
  • Interview scheduled, no prep → "Prep for [company]? /interview-prep"
  • Post-interview, no thank-you → "Send a thank-you? /interview-debrief [company]"
  • Offer received → "Evaluate this? /offer-analysis [company]"
  • Pipeline empty → "Find new roles? /discover"
  • Application looks dead → Be honest and suggest moving on
  • Pattern detected (e.g., 3+ rejections at same stage) → "Looks like a pattern — want to talk through what's happening and adjust your approach?"

Rules

  • pipeline-data.md is the source of truth — update it after every change
  • Always suggest the exact next action
  • Be honest if an application looks dead
  • Flag patterns across the pipeline

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.