agentmods.dev

run-candidacy

run-candidacy is a skill for Claude Code from niharya/skills-drawer. It costs 89 tokens per session (4,004 once invoked), scanned A, original, MIT.

A workflow for tailoring a resume, job-application answers, and outreach messages to one job at a time. It is designed for applications to design, product, and frontend roles and uses the candidate's own facts and writing style.

In plain words
What is it for?
Use it after providing a job description to adapt application materials and prepare role-specific outreach contacts.
Why use it?
It helps prevent generic applications and provides a setup path when the candidate's background and voice have not yet been supplied.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the run-candidacy plugin — 1 skill shipped together

not rated 2repo 2mo ago A scan 89 tokens original MIT

Good fit Use it after providing a job description to adapt application materials and prepare role-specific outreach contacts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/niharya/skills-drawer/run-candidacy
View source ↗ niharya/skills-drawer
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add niharya/skills-drawer --skill run-candidacy
Clone the repo
git clone --depth 1 https://github.com/niharya/skills-drawer

Made for: Claude Code.

Or install run-candidacy, the plugin that ships this one along with the rest of its 1 skill.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for run-candidacy

README.md
[![agentmods](https://agentmods.dev/badge/skills/niharya/skills-drawer/run-candidacy/github.svg)](https://agentmods.dev/skills/niharya/skills-drawer/run-candidacy)
Your own site
<a href="https://agentmods.dev/skills/niharya/skills-drawer/run-candidacy"><img src="https://agentmods.dev/badge/skills/niharya/skills-drawer/run-candidacy/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for run-candidacy

Your own site · 80×15
<a href="https://agentmods.dev/skills/niharya/skills-drawer/run-candidacy"><img src="https://agentmods.dev/badge/skills/niharya/skills-drawer/run-candidacy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,004 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00089 $0.04004
Opus 5 $0.00044 $0.02002
Sonnet 5 $0.00018 $0.00801
Haiku 4.5 $0.00009 $0.00400

Measured 10d ago against content hash 3982b8c95796, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

run-candidacy scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/app_log.py, scripts/build.py, scripts/scan_voice.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**Fallback of last resort.** If neither web_fetch nor Chrome can reach the content, ask the user to paste the JD body. Do not silently invent context from JD-shaped guessing. Do not use `curl` / `wget` / Python `requests
run-candidacy/skills/run-candidacy/SKILL.md · 267 lines

How it starts

The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.

run-candidacy

A candidacy skill whose single purpose is to fill the application in the best way possible, in the candidate's voice, talking directly to the reader, no flattery. Everything below serves that.

When to invoke

When the user pastes a job description (text or URL) and asks to tailor a resume, draft application answers, or run candidacy. Slash trigger: /run-candidacy. Natural-language triggers: "run candidacy", "tailor my resume for X", "draft my application for X".

First-run setup

Check before anything else. If facts/identity.md still contains the string <TODO: filled by setup>, the skill has not been set up for this user yet. Do not attempt to generate a resume. Instead, run the setup flow below.

Setup flow

  1. Surface the two paste-prompts. Tell the user there are two prompts to run in the AI they talk to most (the one that knows their writing and history). Show the paths: prompts/01-facts-extraction.md and prompts/02-voice-extraction.md. Suggest the user open prompt 1, paste it into their AI, and paste the AI's response back here.

  2. Parse prompt-1 response. The AI's reply contains five fenced markdown blocks: identity.md, roles.md, receipts.md, logistics.md, phrasings.md. Extract each block and write it to facts/<filename>, overwriting the placeholder file.

  3. Surface prompt 2. Once prompt 1 is in, ask the user to run prompt 2 the same way. Parse the AI's reply for three fenced blocks: voice.md, style.md, voice-samples.md. Write each to facts/<filename>.

  4. Surface remaining TODOs. After both prompts land, grep facts/ for TODO: ask the user markers and ask the user inline. One question at a time, conversational, not a bulk dump.

  5. Workflow questions (4 questions, in the skill itself):

    • Where should application folders be written? Default: <skill>/examples/<slug>/. Allow override.
    • Render PDF by default, or just HTML? Default: HTML only. PDF on request via --pdf.
    • Enable applications.xlsx logging? Default: yes. If yes, ask for path (default <skill>/applications.xlsx, can override via APP_LOG_PATH env var).
    • Spelling system: American or British? Default: American.

Read the full file on GitHub · 267 lines

Files

What ships with it

22 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 267 lines · 89 tokens per session scan A 3982b8c95796

Subscribe to this mod's changes

run-candidacy is a skill published in the GitHub repository niharya/skills-drawer (2 stars, last pushed 2mo ago), licensed MIT. It adds 89 tokens to every session and 4,004 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

ProductivityWriting and docsanthropicclaude-skillcssdesign-toolsfigmautilities
Related

Other skills, from other repositories

bewerbungsexperte

Spezialist fuer den gesamten Bewerbungsprozess. Analysiert Stellenanzeigen, optimiert Profile (LinkedIn/CV) und generiert massgeschneiderte Anschreiben. Generiert ASCII-Lebenslaeufe aus einer SQLite-Datenbank und Ordnerstruktur. cvgenerator.py ist standalone portiert -- keine BACH-Runtime noetig.

ellmos-ai/skills · 78 tokens

folder-flattening

Verschachtelte Ordnerhierarchien in flache, maschinenlesbare Strukturen umbauen. Bash-basiert mit intelligenter Merge-Logik.

ellmos-ai/skills · 39 tokens

batch-file-ops

Batch-Dateioperationen (Löschen, Verschieben, Kopieren, Auflisten) mit Glob-Mustern. CLI-Werkzeug für effiziente Dateisystem-Operationen. Ohne Abhängigkeiten.

ellmos-ai/skills · 49 tokens

patterns

Instinct Engine — scans recent sessions, journals, and decisions for recurring patterns and turns them into concrete captures (CLAUDE.md rules, concept notes, writing seeds, skill improvements). Run after a weekly review or whenever you sense a pattern hardening. Also runs semi-autonomously via session-end…

adelaidasofia/claude-patterns · 86 tokens

file-collect-sort-action

Erkennt Nutzeraufträge der Form "hole aus einem Ordner immer bestimmte Dateien und sammle sie an einem Ziel" und richtet dafür das Modul file-collect-sort-action (CLI fcsa) ein — ein konfigurationsgetriebener Agent, der Ordner scannt, Dateien per Schablone kategorisiert und gestufte Aktionen anwendet…

ellmos-ai/skills · 206 tokens

layout-discipline

A set of rules for keeping AI-generated web pages visually consistent, including their text sizes, spacing, alignment, cards, and colors.

crazyzlnofficial/layout-discipline · 105 tokens