CtrlK
BlogDocsLog inGet started
Tessl Logo

verifier-overview

Stage 3 triage and verification playbook. Crafts minimal PoCs, runs them with ZFP controls, promotes validated bugs to FINDING nodes with CVSS. Load at verifier-agent startup.

66

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./packages/decepticon/decepticon/skills/plugins/verifier/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

92%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 lean, highly actionable, and structured around explicit validation checkpoints with a strong failure-recovery feedback loop; the only gap is the prose-only insecure-deserialization example lacking an executable command.

Suggestions

Add a concrete executable command for the insecure-deserialization case (e.g., a curl call that triggers the gadget plus the `ls /tmp/decepticon-sentinel` success check) to match the other bug-class entries.

Optionally factor the CVSS cheat-sheet table into a references file if the bug-class catalog grows, keeping SKILL.md as the overview.

DimensionReasoningScore

Conciseness

Lean and efficient throughout: it never explains what SQLi, SSRF, or CVSS are, and every section (contract, PoC patterns, cheat-sheet, failure handling) earns its place, matching 'lean and efficient; assumes Claude's competence'.

5 / 5

Actionability

Four of five bug classes give copy-paste curl commands with explicit success/negative patterns, but the insecure-deserialization entry is prose-only with no executable command, a minor gap fitting 'mostly executable guidance with minor gaps'.

4 / 5

Workflow Clarity

Provides explicit validation checkpoints (negative control demotion on noise) and a clear failure-recovery feedback loop (check service up, check encoding, retry ONCE, record attempts, do not keep retrying), matching 'clear sequence with explicit validation steps; feedback loops for error recovery'.

5 / 5

Progressive Disclosure

No bundle files exist and none are needed; the body is well-organized into clearly headed sections (Verification contract, PoC patterns, CVSS cheat-sheet, failure handling) that are self-contained and easy to navigate, satisfying the simple-skill exception for well-organized content.

5 / 5

Total

19

/

20

Passed

Description

67%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 specific and clearly niche-targeted with concrete actions, but relies heavily on internal pipeline jargon and lacks an explicit 'Use when...' user-trigger clause, capping trigger quality and completeness.

Suggestions

Add an explicit 'Use when...' trigger clause naming natural user-facing situations (e.g., 'Use when triaging and verifying candidate vulnerabilities during stage 3 of the vulnresearch pipeline').

Soften internal jargon ('FINDING nodes', 'ZFP controls') or pair each with a natural synonym so the description reads as terms a user would actually say.

Include common synonyms/extensions (e.g., 'proof-of-concept', 'PoC', 'false-positive control') to broaden natural keyword coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Crafts minimal PoCs', 'runs them with ZFP controls', 'promotes validated bugs to FINDING nodes with CVSS' — covering the verification workflow comprehensively, matching the 'multiple specific concrete actions' anchor.

5 / 5

Completeness

Has a clear 'what' (craft/run/promote PoCs with CVSS) but the only 'when' is 'Load at verifier-agent startup', a lifecycle load instruction rather than an explicit 'Use when...' trigger clause, which per the guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Contains relevant keywords (triage, verification, PoC, CVSS) but is dominated by internal-pipeline jargon ('FINDING nodes', 'ZFP controls', 'stage 3') that a user would not naturally say, missing common synonyms and variations; fits 'some relevant keywords but missing common variations'.

3 / 5

Distinctiveness Conflict Risk

Targets a highly specific niche ('Stage 3 triage and verification playbook' for a verifier-agent) with distinct triggers and minimal overlap risk with other skills, matching the 'clear niche with distinct triggers' anchor.

5 / 5

Total

16

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
PurpleAILAB/Decepticon
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.