CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

johnwick

Use when the user says "run johnwick" / "/johnwick", hands you a bug-bounty target or scope and wants the full manual+recon+automated hunt run end-to-end, or asks to hunt a target with total coverage (every in-scope domain/subdomain, all JS, signup+login, then exploit and validate). Self-contained long-running orchestrator — recon, JS mining, auto-signup, and hunting for IDOR, SSRF, RCE, SSTI, XXE, SQLi, request smuggling, cache poisoning, race conditions, OAuth/JWT/SAML ATO, GraphQL, 403-bypass, and mobile are all built in via internal reference files (each grounded in disclosed paid HackerOne reports), with a zero-skip coverage ledger and a superpowers verification gate between every phase.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

66%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 body is an exceptionally well-sequenced orchestrator: explicit phase gates, a machine-checkable completion invariant, and comprehensive per-class reference coverage make the workflow unambiguous and highly actionable. Its main defect is token efficiency — a large duplicated JS-recon block and six-fold repetition of the no-skip doctrine inflate the body well beyond what the reference files already carry.

Suggestions

Delete the ~120-line "MANDATORY JS RECON GATE" block and replace it with a two-line pointer to references/js-mining.md plus the enforcement rule ("if any web target is in scope, complete the js-mining.md pipeline before recon ends") — the detailed commands already exist in that file.

Consolidate the no-skip doctrine, currently restated in Rule 0, Rule 1, the rationalizations table, the red-flag self-check, the ledger section, and the completion criteria, into a single section (e.g. keep the rules and the ledger invariant; drop the restated motivational variants).

Trim rhetorical padding such as "Hunters who skip JS lose the P1s", "is running a different, worse skill", and "budget the time; this step is supposed to be slow" — the rules already command the behavior.

DimensionReasoningScore

Conciseness

The ~120-line injected "MANDATORY JS RECON GATE" block duplicates content that already lives in references/js-mining.md (same crawlers, download/beautify/sourcemap commands, and secret patterns), and the no-skip doctrine is restated six times (Rule 0, Rule 1, the rationalizations table, the red flags, the ledger section, and the completion criteria), plus motivational padding ("Hunters who skip JS lose the P1s", "this step is supposed to be slow") — several unnecessary padded sections, matching anchor 2 rather than 3 where trimming would be incidental.

2 / 5

Actionability

The body provides copy-paste-ready bash for recon and JS mining (subfinder/httpx/waybackurls/gau/katana pipelines, beautify loop, sourcemap recovery), a machine-checkable ledger invariant (jq query), and a per-class checklist mapping each trigger condition (e.g. "every URL-fetch/webhook/import/preview/media feature → ssrf.md") to a real reference file. It falls short of anchor 5 only because several phases remain high-level directives ("Build the threat model", "walk the entire application") whose execution detail is delegated to references.

4 / 5

Workflow Clarity

Seven numbered phases in strict order, a start protocol, a verification gate between every phase, explicit validation gates (7-Question Gate, 4 pre-submission gates), and concrete feedback loops ("If any is false, the run is not complete — return to the ledger and finish it") with a red-flag self-check — clear sequence with explicit validation, error-recovery loops, and checklists, matching anchor 5.

5 / 5

Progressive Disclosure

All 28 referenced files exist, are exactly one level deep, and are well signaled through both a reference-map table and contextual inline links; however, the inline JS-recon gate block is technique content that clearly belongs in js-mining.md (its own comment marks it as injected boilerplate), so content placement has a notable organization gap — anchor 4 rather than 5.

4 / 5

Total

15

/

20

Passed

Description

87%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 description: it explicitly covers both what the skill does (a comprehensive, named list of hunt capabilities) and when to use it (concrete invocation triggers), with excellent distinctiveness. Its weaknesses are verbosity in a single run-on sentence and a second-person phrase ("hands you"), plus missing common trigger synonyms like "pentest" or "security assessment".

Suggestions

Rewrite in third person and split the single run-on sentence: replace "hands you a bug-bounty target" with "when the user provides a bug-bounty target" and trim meta-phrases like "Self-contained long-running orchestrator" and "superpowers verification gate between every phase".

Add natural trigger synonyms users might say, e.g. "pentest", "penetration test", or "security assessment of a target", to broaden trigger coverage.

DimensionReasoningScore

Specificity

The description lists a comprehensive set of concrete actions ("recon, JS mining, auto-signup, and hunting for IDOR, SSRF, RCE, SSTI, XXE, SQLi, request smuggling, cache poisoning, race conditions, OAuth/JWT/SAML ATO, GraphQL, 403-bypass, and mobile are all built in"), matching the anchor-5 action coverage, but it is padded with meta-language ("Self-contained long-running orchestrator", "superpowers verification gate between every phase") and uses second person ("hands you a bug-bounty target"), which the guidelines penalize by one point — placing it at anchor 4 rather than 5.

4 / 5

Completeness

It explicitly answers both questions: the "what" is concrete (full end-to-end hunt: recon, JS mining, auto-signup, exploit, validate, with named vulnerability classes) and the "when" opens with an explicit "Use when the user says 'run johnwick' / '/johnwick', hands you a bug-bounty target or scope… or asks to hunt a target with total coverage" — concrete trigger phrases on both dimensions, matching anchor 5.

5 / 5

Trigger Term Quality

Natural invocation triggers are explicit ("run johnwick", "/johnwick", "bug-bounty target or scope", "hunt a target with total coverage") — phrases a user would genuinely say — but common synonyms such as "pentest", "penetration test", or "security assessment" are absent, so coverage is good rather than comprehensive (anchor 4, not 5).

4 / 5

Distinctiveness Conflict Risk

Named-skill invocation triggers ("run johnwick", "/johnwick") plus a distinct end-to-end bug-bounty orchestration niche (full coverage ledger, exploit-and-validate pipeline) give it a clear niche with minimal conflict risk against single-technique skills — anchor 5.

5 / 5

Total

18

/

20

Passed

Validation

100%

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

Awarexone/Agentic-Bug-Hunter

Path

skills/johnwick/SKILL.md

Reviewed

Table of Contents

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.