Chalk Labs
Need help deploying wishket-pipeline?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/epicsagas-wishket-pipeline
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: data
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/wishket-pipeline
What's inside
- Skill name
wishket-pipeline- Description
- Track Wishket application pipeline. Manages project stages across the 10 Wishket phases in the pipeline store (state.db), calculating conversion and win rates. 위시켓 지원 파이프라인 추적. 관심 공고 관리 및 10단계 상태 갱신, 수주율/전환율 계산. "위시켓 지원했어", "지원 현황", "파이프라인 보여줘", "미팅 잡혔어", "계약했어", "떨어졌어", "탈락" 등에 사용.
- License
- Apache-2.0
- Instructions
- 81 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# wishket-pipeline — Wishket Application Pipeline Tracker
## Data Schema
`~/.wishket-radar/state.db`의 `applications` 테이블 (v0.4부터 SQLite가 정규 소스. 구 `applications.yaml`이 있으면 첫 기동에 자동 이관되고 `applications.yaml.migrated`로 보존된다. 필드 스키마는 아래와 동일):
```yaml
applications:
- id: "12345" # Wishket project ID
title: Project Title
url: https://wishket.com/project/12345
grade: A # Scout evaluation grade at application time
quote_manwon: 3000 # Proposed amount in 10k KRW (null if negotiable)
applied_at: 2026-09-02
deadline: 2026-09-10 # Project deadline (if present)
status: 지원 # One of the 10 official stages below
status_at: 2026-09-02 # Last status change date
next_action: Review follow-up message # Next action item (or null)
note: |
Freeform notes (meeting logs, feedback, etc.)
```
## Overall Workflow
```mermaid
flowchart LR
A[Scan] --> B[Inbox: Untriaged]
B -->|Interested| C[관심 (Interested)]
B -->|Skip| Z[Excluded]
C -->|Draft proposal & Apply| D[지원 (Applied)]
D --> E{Screening}
E -->|Rejected| X[탈락 (Rejected)]
E -->|Passed| F[상담 (Consulting)] --> G[미팅 (Meeting)] --> H{Contract}
H -->|Uncontracted| Y[미체결 (Uncontracted)]
H -->|Contracted| I[체결 (Contracted)] --> J[진행 중 (In Progress)] --> K[완료 (Completed)]
```
Scan results accumulate in `seen` inside `state.db` (SQLite, WAL). Items without a `triage` field remain in the Inbox. When the user marks an item as Interested in the dashboard Inbox, `triage: interested` is set, and **only Interested items** appear in the pipeline. Changing the stage to Applied or later promotes the item into the pipeline store (`state.db` applications).
## The 10 Official Wishket Stages
| Status | Official Wishket Stage | Meaning |
|---|---|---|
| 관심 | (Pre-application) | Marked interested in Inbox, not yet applied |
| 지원 | 1. 지원 (Applied) | Application submitted with proposed price/duration |
| 상담 | 2. 위시켓 상담 (Consulting) | Wishket manager is screening applicants with client |
| 미팅 | 3. 미팅 (Meeting) | 3-way meeting between client, partner, and manager |
| 체결 | 4. 체결 (Contracted) | Final contract signed |
| 진행 중 | 5. 진행 중 (In Progress) | Client escrow deposited; project started |
| 완료 | 6. 완료 (Completed) | Approved and payment settled; project closed |
| 미체결 | 4. 미체결 (Uncontracted) | Terms did not match; cancelled |
| 탈락 | Rejected at step 2-3 | Not selected during screening |
| 철회 | Withdrawn | Applicant withdrew their proposal |
Win rate = (체결 + 진행 중 + 완료) / (체결 + 진행 중 + 완료 + 미체결 + 탈락). Withdrawn (`철회`) is excluded from the denominator.
Examine stage conversion rates (Applied -> Consulting -> Meeting -> Contracted -> Completed) to identify funnel drop-offs.
### Rules:
- Triage in the dashboard (`wishket-dashboard`) is fastest. If triaging via chat ("관심 있어"), call the dashboard API instead of editing files: `POST /api/inbox/{id}/triage` with `{"action":"interested"}` (token: `~/.wishket-radar/dashboard-token`). Direct `state.db` edits are discouraged.
- Promote items to the pipeline store when applying (via `wishket-apply` or direct user statement "지원했어").
- Detect state transitions from user conversation: "지원했어" -> 지원, "위시켓에서 연락 왔어" -> 상담, "미팅 잡혔어" -> 미팅, "계약했어" -> 체결, "착수했어" -> 진행 중, "끝났어/정산됐어" -> 완료, "떨어졌어" -> 탈락, "조건 안 맞아서 엎어졌어" -> 미체결. Clarify if ambiguous.
- Legacy status names (검토중/면담/수주/거절) are automatically mapped by the server. Always write using the new 10 stages.
- Keep only the latest `status_at` date per item.
- Use Edit tools to modify only specific items; do not overwrite the entire file.
## Presentation
When responding to "show pipeline" requests:
- Funnel: 지원 N -> 상담 a -> 미팅 b -> 체결 c -> 완료 d with conversion % per step.
- Win rate = Won / (Won + Uncontracted + Rejected). Note "Insufficient data" if sample size < 5.
- Active items table: Title, Status, Deadline, Next Action.
- Highlight imminent deadlines (within 3 days) and suggest `wishket-deadline`.
## Skill Integrations
- Suggest `wishket-deadline` (calendar export) when registering an application with a deadline.
- Suggest `wishket-feedback` once 5+ closed items (Won / Uncontracted / Rejected) accumulate.
- Items triaged as Interested in Inbox appear automatically in the pipeline without manual registration. Changing the stage to 지원 or later promotes the item into the pipeline store (`state.db` applications).From epicsagas/wishket-radar, Apache-2.0.
More from epicsagas/wishket-radar
- 0.549score
wishket-scout
epicsagas
In-depth analysis and report generation for new Wishket projects.
SkillAFreshness: AClaude Code +9 - 0.549score
wishket-feedback
epicsagas
Calibrate matching profile using historical application outcomes.
SkillAFreshness: AClaude Code +9 - 0.549score
wishket-onboard
epicsagas
Onboarding for Wishket plugin.
SkillAFreshness: AClaude Code +9 - 0.549score
wishket-portfolio
epicsagas
Draft Wishket portfolio entries.
SkillAFreshness: AClaude Code +9 - 0.549score
wishket-dashboard
epicsagas
Launch the Wishket local dashboard web UI.
SkillAFreshness: AClaude Code +9 - 0.549score
wishket-apply
epicsagas
Draft Wishket project proposals.
SkillAFreshness: AClaude Code +9 - 0.549score
wishket-deadline
epicsagas
Register Wishket project deadlines into macOS / Google Calendar.
SkillAFreshness: AClaude Code +9 - 0.549score
wishket-quote
epicsagas
Estimate project cost and man-days for Wishket postings.
SkillAFreshness: AClaude Code +9 - 0.547score
wishket-profile
epicsagas
View or edit technical matching profile.
SkillAFreshness: AClaude Code +9 - 0.545score
wishket-search
epicsagas
Ad-hoc search for Wishket projects without recording to seen cache.
SkillAFreshness: AClaude Code +9 - 0.545score
wishket-scan
epicsagas
Diff scan for new Wishket projects registered since the last scan.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 4, 2026 (2 months ago)
- Last release
- Oct 23, 2026 (13 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/epicsagas/wishket-radar
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from epicsagas
- 0.641score
book-visuals
epicsagas
Book visual system: art bible and look lock, figure plan per chapter, code-rendered diagrams/charts/technical drawings, diffusion-generated illustrations and…
SkillAFreshness: A★ 38Claude Code +9 - 0.638score
book-game
epicsagas
Game narrative craft reference: branching architecture, quest design, dialogue systems, lore bible, player agency, and game-writing AI tells.
SkillAFreshness: A★ 38Claude Code +9 - 0.638score
book-academic
epicsagas
Academic writing craft reference: IMRAD and discipline structures, literature review, argument chains, citation integrity, academic register in en/ko/ja, and…
SkillAFreshness: A★ 38Claude Code +9 - 0.638score
book-draft
epicsagas
Phase 3: Drafting.
SkillAFreshness: A★ 38Claude Code +9 - 0.638score
book-fiction
epicsagas
Fiction craft reference for all subgenres: structure options, scene design, character depth, dialogue, POV and distance, the fiction-specific AI tells, and…
SkillAFreshness: A★ 38Claude Code +9 - 0.638score
book-edit
epicsagas
Phase 4: Editing.
SkillAFreshness: A★ 38Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get wishket-pipeline running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
wishket-pipeline skill. Agent Mart. https://agentmart.dev/skills/epicsagas-wishket-pipeline (last updated 2026-10-24)