agentleFS
zyphr-labszyphr-labs/bounty-harness/.claude/skills/auto-research/SKILL.md

auto-research

Skill1 starsChanged 3 months agoMITView on GitHub

This is a thin human-facing router. Use skill.yaml as the source of truth for exact commands, inputs, outputs, and workflow chaining.

10 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use marketing-pages, close-spec and 10 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.
  • dzhngSkill

    marketing-pages

    Best-practice rulebook for a marketing site's pages, organized by page class — campaign landers, product pages, programmatic SEO trees, editorial. Use when writing or updating a landing/marketing page, wiring a campaign lander to an attribution identifier, changing site-wide nav/footer links, touching sitemap/robots/agent-readable surfaces, or auditing a public site's indexing, reachability, and conversion setup.

    Also in 4 projects that use this

  • dzhngSkill

    close-spec

    When a spec under specs/<feature>/ is done shipping (a write-spec build, or any planned task that produced a spec), archive it to specs/done/ and rewrite it from a build-plan into a durable rationale — the why, the principles, the invariants — pointing back to the real code for the how. Use when implementation has landed and the plan no longer matches what shipped, or the user says a feature/spec is finished. Pairs with [write-spec](../write-spec/SKILL.md) (the plan this closes) and [review](../review/SKILL.md) (run before closing).

    Also in 4 projects that use this

  • transitive-bullshitSkill

    compare-screenshots

    Compare screenshots against the intended design, distinguishing approved references from historical baselines. Use for iterative implementation matching, before/after visual review, objective image telemetry, or checking a lone capture for flat, empty, or badly framed content.

    Also in 5 projects that use this

  • LucasMatuszewskiSkill

    audit-agents

    Audit and maintain agent configuration files (.claude/agents, AGENTS.md, CLAUDE.md, agent-memory). Checks for duplicates, outdated info, naming conflicts, wrong technical facts, and files over 200 lines. Fixes all issues and commits.

    Also in 4 projects that use this

  • +8 more from dzhng

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 10 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. Very specific:

    Start with scan to check all sources for changes since last scan.

    line 17
  2. Very specific:

    Run batch for the full pipeline: scan -> extract -> deduplicate -> review.

    line 18
  3. Very specific:

    Run review to score and filter extraction candidates.

    line 19
  4. Distinctive:

    If a workflow has no script reference, treat it as a manual or tool-native workflow.

    line 21
  5. Distinctive:

    Not applicable — this skill produces candidate data, not vulnerability findings.

    line 31
  6. Distinctive:

    All candidates are traceable to their origin source for provenance.

    line 33

“Common” is measured: kept by at least 6 in 10 of the 10 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

Auto Research

Overview

Imports and normalizes public security knowledge into the technique knowledge base. Watches public sources (OWASP WSTG, ASVS, nuclei-templates, CISA KEV, PayloadsAllTheThings, HackTricks, SecLists, PortSwigger Research, Bugcrowd VRT, and more), extracts candidate improvements, normalizes them into Technique KB schema, and proposes skill updates. Nothing goes live without validation. Everything is attributed.

This is a thin human-facing router. Use skill.yaml as the source of truth for exact commands, inputs, outputs, and workflow chaining.

Quick Reference

  • Skill: auto-research
  • Severity range: info
  • Required tools: python3, jq
  • Expected input files: none
  • Scope check: not applicable — imports public data into local KB.
  • Redaction: imported research and the source cache are local-only and must never be committed; keep the cache/ directory in .gitignore and sanitize any captured tokens or credentials before sharing.

Workflow Selection

  • Start with scan to check all sources for changes since last scan.
  • Run batch for the full pipeline: scan -> extract -> deduplicate -> review.
  • Run review to score and filter extraction candidates.
  • Runbooks: use runbooks/.
  • If a workflow has no script reference, treat it as a manual or tool-native workflow.

Available Workflows

WorkflowPurposeScript pathsPrimary outputsEvidence
scanScan all sources for new content since last check..claude/skills/auto-research/scripts/source_scanner.py.claude/skills/auto-research/cache/scan_result.json$OUTDIR/auto-research/evidence/
batchRun full import pipeline scan extract deduplicate review..claude/skills/auto-research/scripts/batch_importer.py.claude/skills/auto-research/cache/pipeline_log.json$OUTDIR/auto-research/evidence/
reviewReview pipeline output candidates..claude/skills/auto-research/scripts/candidate_reviewer.py.claude/skills/auto-research/cache/batch_review.json$OUTDIR/auto-research/evidence/

Evidence Required

  • Not applicable — this skill produces candidate data, not vulnerability findings.
  • Attribution is embedded in each candidate record (source_id, source_type, extracted_at, content_hash).
  • All candidates are traceable to their origin source for provenance.

References

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.