API Forge
EliasOulkadi/shokunin
Design REST/GraphQL APIs with OpenAPI 3.1, error handling, pagination, rate limiting, webhooks, and idempotency.
Design and interpret advanced content discovery with ffuf and complementary web fuzzers.
Install Operate Content Discovery
$ npx skills add cyberful/cyberful --skill operate-content-discovery -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install cyberful/cyberful operate-content-discovery --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/cyberful/cyberful.git skills-src && mkdir -p .claude/skills && cp -r skills-src/cyberful/builtin/skills/operate-content-discovery .claude/skills/operate-content-discovery && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "operate-content-discovery" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/operate-content-discovery into .claude/skills/operate-content-discovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "operate-content-discovery", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/operate-content-discoveryType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add cyberful/cyberful --skill operate-content-discovery -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install cyberful/cyberful operate-content-discovery --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cyberful/cyberful.git skills-src && mkdir -p .agents/skills && cp -r skills-src/cyberful/builtin/skills/operate-content-discovery .agents/skills/operate-content-discovery && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "operate-content-discovery" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/operate-content-discovery into .agents/skills/operate-content-discovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "operate-content-discovery", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add cyberful/cyberful --skill operate-content-discovery -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install cyberful/cyberful operate-content-discovery --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cyberful/cyberful.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/cyberful/builtin/skills/operate-content-discovery .cursor/skills/operate-content-discovery && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "operate-content-discovery" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/operate-content-discovery into .cursor/skills/operate-content-discovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "operate-content-discovery", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/cyberful/cyberful.git --path cyberful/builtin/skills/operate-content-discovery--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add cyberful/cyberful --skill operate-content-discovery -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install cyberful/cyberful operate-content-discovery --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cyberful/cyberful.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/cyberful/builtin/skills/operate-content-discovery .gemini/skills/operate-content-discovery && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "operate-content-discovery" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/operate-content-discovery into .gemini/skills/operate-content-discovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "operate-content-discovery", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install cyberful/cyberful operate-content-discoveryInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add cyberful/cyberful --skill operate-content-discovery -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/cyberful/cyberful.git skills-src && mkdir -p .github/skills && cp -r skills-src/cyberful/builtin/skills/operate-content-discovery .github/skills/operate-content-discovery && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "operate-content-discovery" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/operate-content-discovery into .github/skills/operate-content-discovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "operate-content-discovery", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add cyberful/cyberful --skill operate-content-discovery -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install cyberful/cyberful operate-content-discovery --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cyberful/cyberful.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/cyberful/builtin/skills/operate-content-discovery .opencode/skills/operate-content-discovery && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "operate-content-discovery" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/operate-content-discovery into .opencode/skills/operate-content-discovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "operate-content-discovery", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
operate-content-discovery- GitHub stars
- 135
- Token cost
- ~1.5k tokens
- SKILL.md length
- 606 words
- Files
- 9 (incl. scripts, references, assets)
- Skills in repo
- 85
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
Design and interpret advanced content discovery with ffuf and complementary web fuzzers.
- Works in 5 steps: Capture several random nonexistent… → Compare status, body length/words/lines,… → Repeat with and without authentication,… → …
- Recursive discovery when response normalization
- SKILL.md covers Calibrate before fuzzing, Choose the mutation axis, Run ffuf as an experiment and Validate each cluster, plus 2 more sections
- Runs Python scripts from its folder
What it does
Operate Content Discovery is an agent skill from cyberful/cyberful. Design and interpret advanced content discovery with ffuf and complementary web fuzzers. Use for path, file, extension, parameter, value, header, method, API object, virtual-host, subdomain, backup, and recursive discovery when response normalization, wildcard routing, authentication, rate limits, or edge behavior make naive status-code filtering unreliable.
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including scripts, reference files and assets (for example `agents/openai.yaml`, `assets/content-discovery-campaign.example.json` and `assets/content-discovery-campaign.schema.json`).
It sits in Security, covering Fuzzing, Database schema design and Rate limiting. The repository describes itself as: Cyberful is an open-source AI Red Team for discovering, exploiting, verifying, and remediating vulnerabilities. The licence is AGPL-3.0.
When your agent uses it
- Recursive discovery when response normalization
- Wildcard routing
- Edge behavior make naive status-code filtering unreliable
Example prompts
- “/operate-content-discovery”
Requirements
- Python 3
- Docker
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Capture several random nonexistent requests with equal path depth and extension shape.
- Compare status, body length/words/lines, title, redirect target, content type, cache headers, timing, and stable body fingerprints.
- Repeat with and without authentication, cookies, expected headers, trailing slash, alternate method, and cache buster.
- Identify wildcard DNS, catch-all virtual hosts, framework soft-404s, CDN/WAF challenges, and login redirects.
- Select filters from a distribution, never from one response.
What it can do on your machine
Read from SKILL.md and the folder at commit ec598a6. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 2 files in scripts/ (Python), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Operate Content Discovery loads about 1.5k tokens when it runs, and up to ~2.9k if it reads all its reference files. Until then it costs about 97 tokens; SKILL.md has 606 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from cyberful/cyberful at commit ec598a6, republished under its AGPL-3.0 licence (© cyberful). 606 words, ~1,467 tokens.
Download SKILL.mdSave it as
.claude/skills/operate-content-discovery/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.- name
- operate-content-discovery
- description
- Design and interpret advanced content discovery with ffuf and complementary web fuzzers. Use for path, file, extension, parameter, value, header, method, API object, virtual-host, subdomain, backup, and recursive discovery when response normalization, wildcard routing, authentication, rate limits, or edge behavior make naive status-code filtering unreliable.
- metadata.domain
- application-security
- metadata.subdomain
- attack-surface-discovery
- metadata.triggers
- content discovery, ffuf campaign, hidden route discovery, virtual host fuzzing, soft 404 calibration, recursive web discovery
- metadata.tags
- ffuf, web-fuzzing, attack-surface, wildcard-routing, OWASP-WSTG-CONF-04
Operate Content Discovery
Treat discovery as response classification under controlled mutations. The goal is a compact set of meaningful differentials, not a large set of URLs.
Calibrate before fuzzing
- Capture several random nonexistent requests with equal path depth and extension shape.
- Compare status, body length/words/lines, title, redirect target, content type, cache headers, timing, and stable body fingerprints.
- Repeat with and without authentication, cookies, expected headers, trailing slash, alternate method, and cache buster.
- Identify wildcard DNS, catch-all virtual hosts, framework soft-404s, CDN/WAF challenges, and login redirects.
- Select filters from a distribution, never from one response.
Read references/differential-discovery.md before choosing -fs, -fw, -fl, -fc, or auto-calibration.
Choose the mutation axis
- Paths/directories: target/FUZZ
- Files/extensions: FUZZ plus a justified extension set
- Parameters: known route with parameter-name wordlist
- Values/identifiers: one parameter at a time with semantic value classes
- Virtual hosts: Host: FUZZ.example while connecting to the resolved service
- Headers: only headers the stack is likely to route or trust
- Methods: explicit small method set against a known route
- API objects/actions: nouns, pluralizations, versions, verbs, and framework conventions
Do not mix axes until each axis has a stable baseline; otherwise response clusters become uninterpretable.
Run ffuf as an experiment
Use the dedicated ffuf tool with an argv array. Set:
- one wordlist and one FUZZ position per pass;
- explicit concurrency and delay/rate appropriate to the target;
- request timeout that exceeds observed high-percentile latency;
- replay proxy only when every match needs capture;
- JSON/eJSON output under the workarea;
- matchers broad enough to preserve anomalies, then filters for known baselines.
Prefer the bundled frequency-ordered cyberful-os lists for capped campaigns. Promote discovered directories, technologies, schema names, and route fragments into a smaller second-stage wordlist.
For a bounded active run, stage scripts/run_content_discovery_campaign.py, assets/content-discovery-campaign.example.json, and assets/content-discovery-campaign.schema.json. Replace the example values in the workarea, keep one mutation axis per invocation, and set an external authorization reference, exact allowed origins, request limit, rate, concurrency, and timeout explicitly. These campaign fields are defense-in-depth constraints, not authority: the mission-bound Cyberful gateway or ZAP route remains the transport authority. The orchestrator refuses non-loopback targets without the matching runtime HTTP_PROXY or HTTPS_PROXY, accepts Docker hostnames for that host-owned proxy, and inherits only SSL_CERT_FILE or CURL_CA_BUNDLE for trust after validating the JSON. Loopback IP literals explicitly bypass every proxy. The orchestrator resolves only the fixed ffuf command from the trusted runtime, uses argv without a shell, bounds streams and native output while the process runs, and preserves command/version/exit evidence. Read references/differential-discovery.md to interpret the raw result; a match still requires controlled replay.
Show full SKILL.md (189 more words)Show less
Validate each cluster
For every candidate cluster:
- replay one hit and two nearby controls;
- vary only the discovered token;
- compare unauthenticated and relevant authenticated roles;
- test slash, case, encoding, extension, and method only when routing evidence supports them;
- inspect full headers/body and follow redirects manually;
- classify as real resource, routed alias, authorization boundary, input reflection, wildcard artifact, transient edge state, or unknown.
An authorization response is discovery: a stable 401/403 differential can reveal a real handler even without content. A 200 can still be a soft-404.
Pivot intelligently
- Directory listing or index leak -> extract names and recurse only those branches.
- JavaScript/source map/OpenAPI/GraphQL schema -> build application-specific route and parameter lists.
- Framework/admin signature -> add framework conventions, versioned assets, health/metrics/debug routes.
- Backup/temp artifact -> pivot to sibling naming, deployment timestamps, editor suffixes, archive formats.
- Distinct vhost -> recalibrate from scratch for that host; do not reuse filters.
- Stable timing outlier -> replay serially and separate backend work from queue/CDN jitter.
Report
Preserve baseline samples, wordlist identity/hash, command arguments, filters/matchers, rate/concurrency, authentication context, raw output, validated candidates, rejected clusters, and coverage gaps. Report discovered attack surface separately from confirmed vulnerabilities.
© cyberful, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 8 other files (scripts, references, assets) in cyberful/builtin/skills/operate-content-discovery of cyberful/cyberful.
- SKILL.md
- agents/openai.yaml
- assets/content-discovery-campaign.example.json
- assets/content-discovery-campaign.schema.json
- assets/content-discovery-record.schema.json
- references/differential-discovery.md
- scripts/manifest.json
- scripts/run_content_discovery_campaign.py
- tests/test_run_content_discovery_campaign.py
Open the folder on GitHubat commit ec598a6
Compare with similar skills
Operate Content Discovery next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Operate Content Discovery this skillcyberful/cyberful | 135 | — | ~1.5k | Automated safety check: Pass | AGPL-3.0 | |
| API ForgeEliasOulkadi/shokunin | 114 | — | ~2.9k | Automated safety check: Pass | MIT | |
| API Architectcuriositech/some_claude_skills | 244 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Convex Security Auditwaynesutton/builder-skills | 406 | — | ~2.6k | Automated safety check: Pass | Apache-2.0 | |
| Stateful Invariant Testingaviggiano/security | 144 | — | ~2.8k | Automated safety check: Pass | MIT | |
| API Security Checklistrevfactory/harness-100 | 1.3k | — | ~1.7k | Automated safety check: Pass | Apache-2.0 |
Similar skills
API Architect
curiositech/some_claude_skills
Expert API designer for REST, GraphQL, gRPC architectures. An agent skill from curiositech/some_claude_skills.
Convex Security Audit
waynesutton/builder-skills
Deep security review of a Convex app: authorization model, data access paths per table, HTTP action exposure, rate limiting, file storage access, scheduled function trust, and a written findings…
Stateful Invariant Testing
aviggiano/security
Build metric-driven Chimera/create-chimera-app stateful invariant testing campaigns for Solidity projects.
API Security Checklist
revfactory/harness-100
Walks a backend-dev agent through OWASP API Top 10 checks, authentication and authorization patterns, and defense code during API design.
Secure Code Guardian
Jeffallan/claude-skills
Guides secure implementation of authentication, authorization, input validation and security headers, with password hashing, parameterized queries and OWASP Top 10 checks.
More from cyberful/cyberful
All 85 skills in this repoAudit Infrastructure As Code
cyberful/cyberful
Audit infrastructure-as-code artifacts for unsafe defaults, policy gaps, privilege exposure, control drift, and deployment-impact evidence.
Audit Kubernetes Policy Enforcement
cyberful/cyberful
Audit Kubernetes admission and policy-as-code enforcement against local workload manifests, exception paths, namespace scope, and deployment evidence.
Audit Pci Dss Penetration Test Evidence
cyberful/cyberful
Audit PCI DSS penetration-test methodology, scope, internal and external reports, segmentation results, tester independence, remediation, retesting, retention, and multi-tenant support evidence.
Operate Network Recon
cyberful/cyberful
Build a high-fidelity network and service inventory using Nmap, Masscan, packet capture, DNS, and protocol-specific follow-up.
Operate Sast Toolchain
cyberful/cyberful
Operate Semgrep and source-oriented static analysis as a hypothesis, coverage, and regression system during advanced code audits.
Operate Supply Chain Toolchain
cyberful/cyberful
Operate Syft, Grype, Trivy, Gitleaks, Retire.js, package-manager metadata, and build evidence for advanced software-supply-chain assessment.
Related
Categories
Questions about Operate Content Discovery
What does Operate Content Discovery do?
Design and interpret advanced content discovery with ffuf and complementary web fuzzers. Operate Content Discovery is an agent skill from cyberful/cyberful. Design and interpret advanced content discovery with ffuf and complementary web fuzzers.
When should I use Operate Content Discovery?
Operate Content Discovery fits situations like: recursive discovery when response normalization; wildcard routing; edge behavior make naive status-code filtering unreliable.
How do I install Operate Content Discovery in Claude Code?
Run `npx skills add cyberful/cyberful --skill operate-content-discovery -a claude-code`. Or copy the skill folder (cyberful/builtin/skills/operate-content-discovery in cyberful/cyberful) into .claude/skills/operate-content-discovery in your project. Claude Code loads it when a task matches its description.
How do I install Operate Content Discovery in Codex?
Run `npx skills add cyberful/cyberful --skill operate-content-discovery -a codex`. Or copy the skill folder (cyberful/builtin/skills/operate-content-discovery in cyberful/cyberful) into .agents/skills/operate-content-discovery in your project. Codex loads it when a task matches its description.
Can I use Operate Content Discovery in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cyberful/cyberful --skill operate-content-discovery -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/operate-content-discovery, .gemini/skills/operate-content-discovery, .github/skills/operate-content-discovery and .opencode/skills/operate-content-discovery in your project.
What does Operate Content Discovery need to run?
Going by SKILL.md and its folder, Operate Content Discovery needs Python for the scripts in its folder. Our summary lists: Python 3; Docker.
Does Operate Content Discovery access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Operate Content Discovery safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Operate Content Discovery use?
Operate Content Discovery is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Operate Content Discovery use?
About 1.5k tokens (SKILL.md is roughly 5.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.4k tokens, read only when the agent opens those files.
What are the alternatives to Operate Content Discovery?
Skills that share tags, products or a category with Operate Content Discovery: API Forge (EliasOulkadi/shokunin, 114 stars), API Architect (curiositech/some_claude_skills, 244 stars), Convex Security Audit (waynesutton/builder-skills, 406 stars) and Stateful Invariant Testing (aviggiano/security, 144 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Operate Content Discovery?
cyberful (a GitHub organization) maintains it in cyberful/cyberful, which has 135 GitHub stars. The repository holds 85 skills in this directory. The repository was last updated on August 24, 2026.
Source: cyberful/cyberful on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.