bb-methodology

Use at the START of any bug bounty hunting session, when switching targets, or when feeling lost about what to do next. Master orchestrator that combines the 5-phase non-linear hunting workflow with the critical thinking framework (developer psychology, anomaly detection, What-If experiments). Routes to all other skills based on current hunting phase. Also use when asking "what should I do next" or "where am I in the process."

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/bb-methodology/SKILL.md

Quality

Content

60%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.

The content is highly actionable and well-sequenced with real validation gates, making it a strong operational skill. Its main weaknesses are conciseness (concept re-explanation and engagement anecdotes inflate length) and progressive disclosure (everything is inlined into one large file with no external references despite clearly separable reference material).

Suggestions

Move the large reference tables (Tool Routing by Phase, escalation decision trees, Amateur-vs-Pro comparison) into separate files under references/ and link to them from SKILL.md, keeping the body as an overview.

Cut concept re-explanations Claude already knows (CIA triad, what IDOR/race conditions/OOB are) down to one-line definitions or remove them, retaining only the workflow-specific framing.

Trim the recurring 'Lesson from an authorized engagement' anecdotes to a single compact example per discipline rule, or relocate them to a reference file.

Dimension	Reasoning	Score
Conciseness	The ~485-line body is mostly efficient tactical content, but it repeatedly re-states framework concepts Claude already knows (explaining race conditions, IDOR, what OOB means, CIA triad definitions) and includes several verbose 'Lesson from an authorized engagement' anecdotes and an 'Operator Notes' section that pad the token budget beyond what is strictly instructional.	3 / 5
Actionability	Provides mostly executable guidance — concrete tool chains ('subfinder -> amass -> puredns -> httpx'), specific probes (' {{7*7}}', 'SLEEP(10)'), and decision trees — with only minor gaps where steps are framed as checklists rather than runnable commands.	4 / 5
Workflow Clarity	The 5-phase flow is clearly sequenced with explicit validation checkpoints (Phase 5 '7-Question Gate', Multi-Tool Reproduction Bar, hard rules that kill findings), and PART 4 adds strong feedback loops (validate -> fix -> retest); minor gaps keep it just below fully explicit checklisting.	4 / 5
Progressive Disclosure	No bundle files (references/scripts/assets) exist and the entire methodology is inlined as a monolithic ~485-line SKILL.md with only markdown section headers; the large reference-style tables (tool routing, escalation trees, operator notes) that clearly belong in separate files are all inlined with no one-level-deep references.	2 / 5
	Total	13 / 20 Passed

Description

83%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.

The description is strong, explicit, and third-person: it names concrete capabilities, gives multiple natural trigger phrases, and answers both 'what' and 'when'. It is held back only slightly by being a meta/orchestrator skill whose own action list is relatively abstract, and by mild overlap risk with the skills it routes to.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities ('combines the 5-phase non-linear hunting workflow with the critical thinking framework (developer psychology, anomaly detection, What-If experiments)', 'Routes to all other skills based on current hunting phase') but stays at the orchestrator/meta level without enumerating the specific hunting actions it performs, leaving minor coverage gaps.	4 / 5
Completeness	Clearly answers both 'what' (master orchestrator combining the 5-phase workflow with the critical thinking framework, routing to other skills) and 'when' (start of session, switching targets, feeling lost, asking what to do next) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural trigger phrases ('at the START of any bug bounty hunting session', 'when switching targets', 'what should I do next', 'where am I in the process') that users would actually say, though it leans on a couple of repeated phrasings rather than offering broader synonyms.	4 / 5
Distinctiveness Conflict Risk	The orchestrator framing and explicit routing behavior carve a fairly distinct niche, but because it positions itself as a router to 'all other skills' there is some overlap risk with the sibling hunt-* skills it dispatches to.	4 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (514 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: elementalsouls/Claude-BugHunter
Path: skills/bb-methodology/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.