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

84%

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

88%Weight 40%Scale 1-5

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

A dense, highly actionable dispatcher body with executable probes, explicit validation checkpoints, and a clear step sequence. The main gap is progressive disclosure: the large platform-skill mapping and taxonomy blocks are inlined with no external reference files to offload them.

Suggestions

Move the step-1 platform-signal → skill mapping table and the full mode=wapt hunt-* set list into a referenced file (e.g. references/skill-map.md) and link to it, keeping only the tier precedence and load-budget rules inline.

Tighten the two narrative engagement anecdotes (soft-404 per-host baseline, READ-ONLY subagent lesson) to one-line lessons so the hard-won rule survives without the prose.

Dimension	Reasoning	Score
Conciseness	Lean, lowercase, telegraphic style that assumes Claude's competence throughout; a few narrative engagement anecdotes ("one engagement saw two hosts...", "lesson from an authorized engagement: a subagent was told READ-ONLY...") could be tightened without losing the lesson.	4 / 5
Actionability	Fully executable curl/bash loops for the 404 baseline, fingerprint scan, and auth preflight, plus concrete platform-skill mapping tables — copy-paste ready and covering the common dispatch cases.	5 / 5
Workflow Clarity	Clear step 0→4 sequence with explicit validation checkpoints (404 baseline control triple, auth preflight checking live/role/MFA) and a feedback loop (preflight failure surfaces rather than silently continuing as blackbox).	5 / 5
Progressive Disclosure	Well-organized into clearly labeled sections with a Related Skills & Chains map, and the inline routing tables are justified as core dispatch logic; however no bundle files exist and large mapping/taxonomy tables remain inlined rather than split into referenced files.	4 / 5
	Total	18 / 20 Passed

Description

80%Weight 40%Scale 1-5

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

A strong, specific description that clearly states both purpose and trigger condition with a useful negative-boundary clause. Its only weakness is trigger-term naturalness: the activation language is internal orchestrator jargon rather than user-spoken phrases.

Suggestions

Soften the trigger phrasing toward language an operator would actually say (e.g. "after /hunt confirms redteam vs WAPT mode") rather than the internal "mode answer (redteam or wapt + blackbox|greybox)" token.

Name the dispatch outcome concretely in the action list (e.g. "selects platform skills by tier, caps loads at 8, prints a colon-delimited taxonomy") so the decision logic is enumerated rather than implied.

Dimension	Reasoning	Score
Specificity	"Fingerprints the target, picks the right platform attack skills, and loads the Red Team or WAPT skill set" plus "print the taxonomy" lists several concrete actions, though coverage of the dispatch decision logic is implied rather than enumerated.	4 / 5
Completeness	Explicitly answers both what ("Skill-set loader... Fingerprints... picks... loads") and when ("Use when /hunt has just received a mode answer... needs to load the appropriate skills and print the taxonomy") with concrete trigger phrasing.	5 / 5
Trigger Term Quality	Triggers are internal-orchestrator jargon ("mode answer (redteam or wapt + blackbox\|greybox)", "/hunt orchestrator") — relevant keywords but not natural phrases a user would say, and the skill is explicitly not user-invoked.	3 / 5
Distinctiveness Conflict Risk	Clear niche as the /hunt dispatcher with distinct mode-based triggers and an explicit negative boundary ("Not for direct user invocation"), giving minimal conflict risk with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: elementalsouls/Claude-BugHunter
Path: skills/hunt-dispatch/SKILL.md
Commit: 58017df

Reviewed: 3 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.