agentleFS
rafaym1rafaym1/scholarship-desk/.claude/skills/recon/SKILL.md

recon

Skill18 starsChanged 4 days agoMITView on GitHub

Walk an application portal without submitting to collect every question, word limit, upload slot, file rule and extra field, and save reusable notes (a playbook) for that platform. Use "/recon <opportunity id>" before tailoring or applying.

32 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use reporting, osint and 3 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • GitHubSkill

    reporting

    Report formatting guidelines for gh-aw workflows (header levels, collapsible details, run-ID links)

    Also in 3 projects that use this

  • JosBen74Skill

    osint

    OSINT-sökning och informationsinhämtning från öppna källor för Länsstyrelsen VG

    Also in 4 projects that use this

  • samklee1Skill

    web-pentest

    Orchestrates authorized web app pentesting on Kali Linux using Opus sub-agents with difficulty-aware planning (TDA/EGATS), browser-first exploration, iterative verification, two-layer review (per-sub-agent + phase-level), optional cross-model gap audit (GPT/codex via codex-plugin-cc), and enforced KB updates. Trigger on: pentesting, penetration testing, web app security assessment, vulnerability assessment, OWASP testing, PTES, attack surface mapping, API security testing, pentest reporting, or 'help me test this app'. NOT for network-only pentesting, malware analysis, reverse engineering, or CTFs.

    Also in 3 projects that use this

  • SentrySkill

    create-pr

    Create pull requests following Sentry conventions. Use when opening PRs, writing PR descriptions, or preparing changes for review. Follows Sentry's code review guidelines.

    Also in 3 projects that use this

  • NVIDIASkill

    research

    Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 27 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read CLAUDE.md first. Use Sonnet.

    line 8
  2. Very specific:

    Read the platform playbook if one exists: playbooks/<platform>.md (platform from the record, or the portal's domain, e.g.

    line 11
  3. Very specific:

    Read the anthropic-skills:chrome-browser skill, load the Chrome tools in one ToolSearch call, open apply_url in a new tab.

    line 13
  4. Distinctive:

    every question: prompt verbatim, limit, unit (words/characters), required or optional

    line 21
  5. Distinctive:

    every upload slot: label, required, accepted formats, max MB, max pages, which document type it maps to

    line 22
  6. Very specific:

    Create or update playbooks/<platform>.md with portal mechanics only — no personal data: navigation, autosave and session timeout, odd …

    line 37

“Common” is measured: kept by at least 6 in 10 of the 27 edited versions of this file we could read. “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

Portal recon

Read CLAUDE.md first. Use Sonnet. Nothing is submitted during recon.

  1. python -m scholar opp show <id> and python -m scholar app prepare <id>.
  2. Read the platform playbook if one exists: playbooks/<platform>.md (platform from the record, or the portal's domain, e.g. varbi, jobbnorge, universityadmissions).
  3. Read the anthropic-skills:chrome-browser skill, load the Chrome tools in one ToolSearch call, open apply_url in a new tab.
  4. Login or account creation needed → tell the applicant: "Please sign in (or create the account) at <host> in the Chrome tab and tell me when you're done." Never type passwords or codes.
  5. Move through the form with the portal's own Next/Save buttons. Saving a draft is fine; never press the final Submit. Don't fill fields, except a choice that reveals later pages (e.g. picking the programme) — ask the applicant first.
  6. Collect:
    • every question: prompt verbatim, limit, unit (words/characters), required or optional
    • every upload slot: label, required, accepted formats, max MB, max pages, which document type it maps to
    • other fields that need information not in the profile
    • declarations/consent text, any payment step, how referees are handled (does entering a referee email them immediately?), the deadline and time zone shown in the portal
  7. Save to the record — write data/tmp/patch.json:
    {"application": {"questions": [{"prompt": "...", "limit": 300, "unit": "words", "required": true, "category": "motivation"}],
                     "upload_rules": [{"slot": "CV", "type": "cv", "formats": ["pdf"], "max_mb": 2, "max_pages": 2, "required": true}],
                     "requires_account": true, "platform": "varbi",
                     "referee_process": "Referees are emailed when you press Save on page 4",
                     "extra_fields": ["How did you hear about the programme?"]}}
    python -m scholar opp patch <id> data/tmp/patch.json Question category: motivation, career_goals, research, leadership, challenge, impact, why_country, academic, diversity, other.
  8. Create or update playbooks/<platform>.md with portal mechanics only — no personal data: navigation, autosave and session timeout, odd widgets (date pickers, searchable dropdowns), upload behaviour, when referee emails go out, where the final Submit is.
  9. Report to the applicant: the questions, information you still need from them, the documents required, and that /tailor <id> is next.

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.