hunt-dispatch

Skill-set loader for /hunt orchestrator. Fingerprints the target, picks the right platform attack skills, and loads the Red Team or WAPT skill set. Use when /hunt has just received a mode answer (redteam or wapt + blackbox|greybox) and needs to load the appropriate skills and print the taxonomy. Not for direct user invocation.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is lean, highly actionable, and sequences a multi-step load flow with strong validation checkpoints. Its single weakness is progressive disclosure: a skill this long keeps all lookup tables and skill-set rosters inline rather than splitting them into one-level-deep reference files.

Suggestions

Move the large signal→skill mapping table and the tier precedence list into a references file (e.g. fingerprint-mapping.md), keeping SKILL.md as a concise overview that links to it.

Move the full per-mode hunt-* skill rosters (the wapt block alone lists ~45 skills) into a references file such as skill-sets.md, with SKILL.md naming only the always-on and platform skills inline.

Add a short 'References' section near the top signaling these files one level deep, so the overview stays scannable while the rosters remain discoverable.

Dimension	Reasoning	Score
Conciseness	Dense and tactical throughout — signal→skill mappings, tier precedence, load-budget caps, dedup rules, and auth preflight — with no padding and no explanation of concepts Claude already knows; every block earns its place.	3 / 3
Actionability	Provides copy-paste-ready executable bash (curl fingerprint scan with -L/-D/-o, auth preflight with -w http_code), explicit 200-vs-401/403 decision rules, and exact taxonomy print format — fully executable, not pseudocode.	3 / 3
Workflow Clarity	Steps 1–4 are clearly sequenced with explicit validation checkpoints: the greybox auth preflight gates the authenticated hunt-* fan-out with 'STOP, re-auth' on failure and three confirmations (live, role/privilege, not MFA-gated), plus a feedback loop surfacing invalid creds instead of silently continuing.	3 / 3
Progressive Disclosure	Well-organized into clearly headed steps, but at ~280 lines everything is inline with no external reference files — the 20+ signal mapping table, tier list, and full hunt-* skill sets could be offloaded to reference files to slim the overview.	2 / 3
	Total	11 / 12 Passed

Description

85%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, complete, and well-scoped with explicit what/when guidance and a clear niche. Its only weakness is trigger-term quality: the activation condition is orchestration state rather than natural user phrasing.

Suggestions

Add user-facing trigger phrasing alongside the state condition, e.g. 'Use when the user wants to kick off a /hunt engagement in redteam or WAPT (blackbox/greybox) mode', so the trigger reads like something an operator would actually say.

Surface a couple of natural synonyms ('red team assessment', 'web app pentest', 'WAPT', 'engagement mode') to broaden keyword coverage beyond the bare mode tokens.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Fingerprints the target, picks the right platform attack skills, and loads the Red Team or WAPT skill set' — plus 'print the taxonomy', matching the multiple-specific-actions anchor.	3 / 3
Completeness	Clearly answers both what (fingerprint, pick, load, print taxonomy) and when ('Use when /hunt has just received a mode answer ... and needs to load the appropriate skills and print the taxonomy').	3 / 3
Trigger Term Quality	It carries the relevant mode vocabulary (redteam, wapt, blackbox, greybox), but the trigger is framed as orchestrator state ('/hunt has just received a mode answer') rather than language a user would naturally say, and it explicitly notes 'Not for direct user invocation'.	2 / 3
Distinctiveness Conflict Risk	Narrow loader niche gated by /hunt mode state with an explicit 'Not for direct user invocation' guard, making it unlikely to fire for the wrong skill.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: elementalsouls/Claude-BugHunter
Path: skills/hunt-dispatch/SKILL.md
Commit: 6b9c96e

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.