agentleFS
noamgariani11noamgariani11/claude-skills/skills/h1-report/SKILL.md

h1-report

Skill0 starsChanged 4 months agoNo licenceView on GitHub

Write, review, and improve HackerOne or BugCrowd vulnerability reports — and get measurably better at it after every single report. Drafts a new report from a confirmed finding, OR takes an existing draft/report and makes it stronger: tighter title, copy-pasteable repro, a defensible CVSS vector (H1) or P1-P5 priority + VRT category (BugCrowd), a concrete program-tailored impact scenario, correct redaction, and prose that reads like a careful human researcher wrote it (not a chatbot). Runs two mechanical gates every time — research/tools/report_validator.py (structure + anti-slop evidence) and this skill's tools/report_lint.py (grammar/style + a hard em-dash purge: it removes ALL em/en dashes). Grounded in research/05-report-writing.md, the disclosed-report corpus, and HackerOne's own Quality-Reports guidance. Closes every run by writing back lessons + memories (memory/LESSONS.md, memory/report-log.jsonl) so each report is sharper than the last; also ingests triage OUTCOMES (resolved/dup/N-A/severity-change/bounty) to learn what this and other programs actually reward. Use when: "write a HackerOne report", "write a BugCrowd report", "review my report", "review my bugcrowd report", "improve / polish this report", "draft a report for this finding", "draft a bugcrowd finding", "remove the em dashes", "the triager said X — what did I learn", "/h1-report". NOT for finding bugs (use /bug-hunt or /vuln-research) — this is the writing + learning loop that runs after a finding is confirmed.

The file

Show its rules and text

We split this skill into the rules it gives an agent

28 rules. About 0 are common, 16 are distinctive, and 12 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈16

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 12

    Very specific

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

No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

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.