Skip to content
Agentmart
Submit a tool

wishket-apply

Draft Wishket project proposals.

Skill by epicsagas

IndexedApache-2.0
Write a review

Chalk Labs

Need help deploying wishket-apply?

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.

Book a call

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-apply

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.

We use your email only for this newsletter. Privacy

About

Draft Wishket project proposals. Writes a markdown `draft.md` for local review and a plain-text `form.txt` for the Wishket paste form. Recommends and ranks portfolio attachments. 위시켓 공고 지원서·제안서 작성. "위시켓 지원서 써줘", "이 공고 지원할 건데 제안서", "제안서 작성" 등에 사용. 포트폴리오 추천·선별 포함.

Use cases: documents

No 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-apply

What's inside

Skill name
wishket-apply
Description
Draft Wishket project proposals. Writes a markdown `draft.md` for local review and a plain-text `form.txt` for the Wishket paste form. Recommends and ranks portfolio attachments. 위시켓 공고 지원서·제안서 작성. "위시켓 지원서 써줘", "이 공고 지원할 건데 제안서", "제안서 작성" 등에 사용. 포트폴리오 추천·선별 포함.
License
Apache-2.0
Instructions
79 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# wishket-apply — Wishket Application & Proposal Drafting

## Flow

```mermaid
flowchart LR
    A[Project ID/URL/scout report] --> B[Fetch get_project details]
    B --> C[Read profile.yaml + portfolios/]
    C --> D[Draft proposal]
    D --> E[Recommend portfolios to attach]
    E --> F[Save to proposals/ + Summary]
    F --> G{Confirmed apply?}
    G -- Yes --> H[Register to wishket-pipeline]
```

## Step 1: Obtain Project Details

- If the user provides a project ID or URL, retrieve details via `get_project`.
- If given a scout report file, extract the project ID and call `get_project`.
- If missing, search using `search_projects` and confirm with the user.
- If `description` is already cached in the `state.db` cache under `seen[<id>]`, reuse it first to avoid the 5-second `Crawl-delay`.
- Writing a proposal means the project is already at 관심. If `triage` is missing, suggest marking it Interested in `wishket-pipeline` first.

## Step 2: Gather Materials

- `~/.wishket-radar/profile.yaml` (respect `WISHKET_PROFILE` override): tech stack, roles, notes.
- Existing drafts in `~/.wishket-radar/portfolios/`: scan file headers (title, tech stack, core features) to determine relevance.
- If the user provides extra requirement documents, use the extraction pattern from `wishket-portfolio` (PDF=Read, PPTX/DOCX/XLSX=unzip).

## Step 3: Draft Proposal

Always produce **exactly two files**. Do not write a third `submit` copy.

| File | Role | Format |
|---|---|---|
| `draft.md` | Local review in the dashboard | Markdown allowed (`#`, `**`, tables) |
| `form.txt` | Paste into the Wishket application form | **Plain text only** |

Write `draft.md` first. Derive `form.txt` from it by flattening headings, bold, and tables into sentences and `-` / `1)` lists. Wishket's form does not render markdown, so `form.txt` must not contain `#`, `**`, backticks, or markdown tables.

If the user provides an exact application form schema, `form.txt` follows that field layout. `draft.md` may keep a richer review structure.

Standard sections (both files):

1. **Project Understanding** (Restate core requirements in 2-3 sentences. Never copy-paste raw text).
2. **Approach & Strategy** (Phase-by-phase execution plan, technology choices, and rationale).
3. **Relevant Experience** (Directly relevant items from profile/portfolios with quantitative metrics where possible).
4. **Schedule & Staffing** (Estimated duration and team composition; provide ranges if uncertain).
5. **Proposed Budget** (State rationale. Reference `wishket-quote` results if available; otherwise state "금액 협의" and suggest `wishket-quote`).

### Drafting Rules:
- Naturally integrate matched skill keywords (intersection of `profile.yaml` keywords and project description). Avoid keyword stuffing.
- Do not fabricate or exaggerate experience. Only include verifiable skills/projects.
- Prohibit external contact info (email, phone, websites). Same rule as the portfolio form.
- Use client information only as provided in `get_project`.

## Step 4: Recommend Portfolio Attachments

- Propose top 3 relevant portfolios by tech overlap, with a one-line rationale for each.
- If `portfolios/` is empty, recommend running `wishket-portfolio`.
- Recommend the display order (Wishket displays the first portfolio as primary).

## Step 5: Save & Register

- File location: **`~/.wishket-radar/proposals/<PROJECT_ID>/YYYY-MM-DD-<usage>.<ext>`** (create directory if missing).
  - **Directory name MUST be the project ID.** The dashboard associates proposals by directory name. Placing files at root classifies them as "Other" and breaks project linkage.
  - Usages: `draft` and `form` only. Never write `submit.md`.
  - Extensions: `draft.md` (dashboard markdown), `form.txt` (Wishket paste).
  - Examples: `proposals/158080/2026-09-02-draft.md`, `proposals/158080/2026-09-02-form.txt`.
  - Do not duplicate the project ID in the filename.
- Chat summary: 1-line strategy, key matching strengths, budget status, recommended portfolio attachments.
- When application is confirmed: Promote stage to "지원" in `wishket-pipeline` (pipeline store in `state.db`), recording budget, duration, and deadline.
- If drafting is complete but submission is deferred: Keep in "관심" and set `next_action` to "제안서 초안 완료 — 제출 여부 결정".

## Caution
- Do not finalize budget numbers without user confirmation; use placeholder or call `wishket-quote`.
- If the project deadline is within 3 days, place an urgent deadline warning at the top of the chat response.

From epicsagas/wishket-radar, Apache-2.0.

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
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from epicsagas

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-apply 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.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying wishket-apply?

CallGet help
Cite this page

wishket-apply skill. Agent Mart. https://agentmart.dev/skills/epicsagas-wishket-apply (last updated 2026-10-24)