Skip to content

Bundled Skills Reference

29 atomic skills ship with agents-fleet. Skills are composable knowledge packs the coordinator attaches to roles when spawning workers — they are NOT agent personas (for those, see Roles). Skills live in src/skills/bundled/skills/ and are always loaded (bundled tier); override any skill with a same-named .skill.md in .fleet/skills/ or ~/.fleet/skills/. List them at runtime with /skills or list_features --kind skill.

Generated for agents-fleet v0.52.0 · 29 bundled skills.


Fleet & Architecture

SkillTagsDescription
agents-fleet-conventionsshared, conventions, typescript, esmShared conventions for agents-fleet codebase (TypeScript/ESM/branded types/named exports)
ci-pipeline-authoringci, testing, infrastructureAuthoring robust CI/CD pipelines — test, coverage, regression matrix, and build gates (GitHub Actions)
coordinator-worker-architecturearchitecture, coordinator-worker, fleetagents-fleet coordinator-worker primitives, boundaries, and concurrency
hub-tool-disciplinehub, topology, discipline, communication, coordinatorHub topology — workers MUST route ALL coordinator-bound communication through report_to_coordinator
prepared-statements-patternsqlite, database, prepared-statementsIntelDatabase prepared-statement conventions for better-sqlite3 (WAL, sync, idempotent migrations)
react-ink-patternsreact, ink, terminal-ui, hooksReact 18 + Ink 5 terminal-UI patterns — function components, hooks, Static, Box layout, polling
workflow-authoringworkflows, authoring, orchestrationWorkflow authoring guide — file anatomy, runner types, edges, forEach, postChecks, dispatch ceremony, author→validate→fix loop

Code Quality

SkillTagsDescription
ponytail-minimalismminimalism, yagni, code-qualityYAGNI ladder and minimalism rules — forces the laziest solution that actually works
ponytail-reviewreview, minimalism, over-engineering, code-qualityOver-engineering code review — finds what to delete, replace with stdlib/native, or shrink
vitest-patternstesting, vitest, asyncVitest 4.x test patterns — fixtures, mocking, async, tmpDir cleanup

Reporting & Documentation

SkillTagsDescription
html-report-authoringreporting, html, documentation, pdf, diagramsAuthor polished, self-contained, interactive HTML reports in the agents-fleet light brand theme (SVG/PNG/interactive diagrams, never ASCII) with on-demand PDF export

Security — Application

SkillTagsDescription
sec-authz-auditsecurity, authz, authn, idor, jwt, access-control, appsecAudit authentication and authorization flaws — broken access control, IDOR, missing function-level authz, JWT weaknesses, session/cookie flaws, privilege escalation
sec-cicd-auditsecurity, cicd, github-actions, supply-chain, appsecAudit CI/CD and GitHub Actions security — over-privileged tokens, untrusted pull_request_target, script injection via github.event, unpinned actions, secret exposure, artifact tampering
sec-crypto-auditsecurity, cryptography, tls, randomness, appsecAudit cryptographic misuse — weak algorithms, hardcoded keys/IVs, insecure randomness, unauthenticated encryption, improper TLS/cert validation
sec-deserialization-auditsecurity, deserialization, prototype-pollution, reflection, appsecAudit insecure deserialization, JS prototype pollution, and unsafe reflection across Node/TS and C#/.NET
sec-injection-auditsecurity, injection, sqli, ssti, ssrf, xxe, path-traversal, appsecFind and safely confirm injection classes — SQL/NoSQL, OS command, SSTI, path traversal, SSRF, XXE, open redirect, header injection
sec-llm-agent-auditsecurity, llm, agent, prompt-injection, mcp, atlas, appsecAudit LLM and agent security (MITRE ATLAS) — prompt injection (direct/indirect), tool/command injection via model output, system-prompt leakage, RAG poisoning, unsafe MCP/tool allowlists, over-broad agent permissions
sec-recon-attack-surfacesecurity, recon, attack-surface, threat-model, appsecMethodology to map a codebase's attack surface — entry points, trust boundaries, dangerous sinks, dependencies, CI/CD, and secrets locations
sec-secrets-auditsecurity, secrets, credentials, gitleaks, git-history, appsecDetect secrets and credential exposure in source, config, and git history — API keys, tokens, private keys, connection strings — with gitleaks-style patterns and remediation
sec-supplychain-auditsecurity, supply-chain, sca, dependency-confusion, sbom, npm, nuget, appsecAudit dependency and supply-chain risk — known-vulnerable packages, lockfile integrity, dependency confusion, typosquatting, SBOM review for npm and NuGet
security-audit-checklistsecurity, audit, threat-modelThreat-model audit checklist — path traversal, SQL injection, prototype pollution, credentials, command injection, MCP allowlists

Security — Reporting & PoC

SkillTagsDescription
sec-crash-triage-exploitabilitysecurity, binary, crash-triage, exploitability, poc, appsecTriage fuzzing crashes and assess realistic exploitability — reproduce, classify (WinDbg !exploitable / !analyze, ASan reports), determine the memory-safety primitive (OOB read/write, UAF, type confusion), assess mitigations (DEP/ASLR/CFG/stack cookies), and write the minimal PoC that PROVES impact (controlled crash/AV) — never a weaponized exploit
sec-finding-reportsecurity, reporting, cwe, owasp, mitre, appsecDocument a security finding — title, qualitative severity, affected file:line, description, PoC/repro, impact, remediation, and framework mapping (CWE, OWASP Top 10 2021, MITRE ATT&CK)
sec-msrc-reportsecurity, reporting, msrc, coordinated-disclosure, cvss, cwe, appsecProduce an MSRC-format coordinated-disclosure report — affected product/build, vulnerability type + CWE, CVSS 3.1 and 4.0 vectors + base scores, attack vector/prerequisites/privileges/user-interaction, numbered repro steps, PoC reference, impact classification, affected configurations, suggested mitigation, and coordinated-disclosure timeline
sec-poc-authoringsecurity, poc, testing, responsible-disclosure, appsecProve a security finding SAFELY — write a local failing test or minimal sandboxed proof-of-concept against the operator's own code only, that goes green once fixed

Security — Binary Analysis & Fuzzing

SkillTagsDescription
sec-binary-static-analysissecurity, binary, reverse-engineering, static-analysis, patch-diff, appsecStatic reverse engineering of a target binary (PE/ELF/Mach-O) — triage the file, extract imports/exports/strings/sections, disassemble + decompile (Ghidra headless / IDA / radare2 / objdump), identify dangerous APIs, parsing routines, and trust boundaries, and patch-diff a patched-vs-unpatched build to locate the fixed/target code
sec-fuzzingsecurity, binary, fuzzing, coverage-guided, sanitizers, appsecCoverage-guided fuzzing of a target (parser/decoder/IPC/file-format) — build a harness (libFuzzer/AFL++/WinAFL/honggfuzz), assemble a seed corpus + dictionaries, run with sanitizers (ASan/UBSan), measure coverage, and minimize crashers — all inside an isolated, disposable VM

Security — Infrastructure

SkillTagsDescription
sec-azure-vm-provisioningsecurity, azure, vm, isolation, disposable, coordinated-disclosure, appsecSafely provision an ISOLATED, DISPOSABLE Azure VM for PoC validation with the az CLI — dedicated resource group, isolated vnet/subnet, deny-all NSG, no public IP, snapshot before detonation, TTL tag, and guaranteed teardown; NEVER a production subscription
sec-vm-detonationsecurity, azure, vm, detonation, evidence, integrity, coordinated-disclosure, appsecDetonate a PoC inside an isolated, disposable Azure VM and capture evidence — transfer via az vm run-command / Custom Script Extension, execute, collect logs/screenshots/crash-dumps/process+event evidence, hash + timestamp each artifact, assert the security impact vs a benign baseline, then snapshot-revert or delete the RG