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.
npx skills add PramodDutta/qaskills --skill application-form-fillergit clone --depth 1 https://github.com/PramodDutta/qaskillsWrote 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.
[](https://agentmods.dev/skills/pramoddutta/qaskills/application-form-filler)<a href="https://agentmods.dev/skills/pramoddutta/qaskills/application-form-filler"><img src="https://agentmods.dev/badge/skills/pramoddutta/qaskills/application-form-filler/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.
<a href="https://agentmods.dev/skills/pramoddutta/qaskills/application-form-filler"><img src="https://agentmods.dev/badge/skills/pramoddutta/qaskills/application-form-filler.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00027 | $0.02340 |
| Opus 5 | $0.00014 | $0.01170 |
| Sonnet 5 | $0.00005 | $0.00468 |
| Haiku 4.5 | $0.00003 | $0.00234 |
Grade A, and why
Application Form Filler scanned grade A with 0 findings 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.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
92% identical to application-form-filler — 98 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Application Form Filler
When to Use This Skill
Use this skill when the user wants to:
- Answer specific questions on a job application form
- Fill out text fields on Greenhouse, Lever, Ashby, Workday, or any ATS
- Write responses to "tell us about yourself" or "why do you want to work here" prompts
- Get clean, copy-pasteable answers to application questions
- Mentions: "fill this out", "what do I write here", "answer this question", "application form", "form field"
Core Principle
Application form answers should be direct and specific -> not a cover letter crammed into a text box. Each field has a purpose. Answer that purpose clearly, then stop.
The answer should feel like: A real person typed it, not a template was filled in.
Before Answering
Always read:
- The job description -> mirror its language and priorities
- The candidate's CV/profile -> pull real projects, roles, and metrics
- The specific question -> answer exactly what was asked, not what you wish was asked
If the user hasn't provided a CV or JD, ask for them before writing.
Question Types and How to Handle Each
Type 1: Experience/Background Questions
Examples:
- "How many years of experience do you have with [technology]?"
- "Describe your experience with [domain]"
- "What backend frameworks have you used?"
Format:
[Technology/skill] -> [X years]. [One sentence on what you used it for, with a
specific project or context]. [Optional: secondary tools in the same category].
Rules:
- Lead with the most used/relevant technology
- Give years honestly -> don't inflate
- Anchor every claim to a real project or role
- For "describe experience" questions: 2-4 sentences max, one project per sentence
- If experience is indirect (adjacent domain), say so and pivot to what is relevant
Type 2: Why This Company / What Interests You
Examples:
- "Why do you want to work at [Company]?"
- "What interests you about this role?"
- "Why are you a good fit?"
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.
- 10d ago First seen · 294 lines · 27 tokens per session scan A ee585f22ddef
Application Form Filler is a skill published in the GitHub repository PramodDutta/qaskills (220 stars, last pushed 10d ago), licensed MIT. It adds 27 tokens to every session and 2,340 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to application-form-filler, differing in 98 lines, and is treated as a copy.
Other skills, from other repositories
ai-dev-jobs-mcp
Search 8,400+ AI and ML jobs across 489 companies, inspect listings and employers, match roles, and view salary and market stats via AI Dev Jobs MCP.
job-application-agent
Finds, evaluates, fills, submits, and tracks a candidate's own job applications using a verified resume, evidence-based targeting, secure local profile storage, and browser automation. Use for onboarding or migrating a job-search profile, searching active roles, assessing a posting, applying to an authorized URL or…
apply
Apply to a single job (URL or pasted page) with fit review, or score and apply the job links pasted into an apply campaign when no argument is given.
scan-inbox
Classify unscanned mailbox messages, fuzzy-match each to an existing application, and write the proposal back. The user approves in /inbox.
resume-campaign
Resume a paused JobPilot campaign by id. Re-flips the campaign to inprogress and replays the apply loop on any remaining approved jobs without re-asking for fit confirmation.
mentor-patterns
The six patterns the Mentor hunts in the records to decide WHEN to speak. Silence is the default; only a real, recurring pattern earns a word. This skill gives the canonical detection method for each pattern (DB query + threshold) so the Mentor never speaks from a single data point. Read-only — never writes to the DB.…