CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

patch-diff-research

Authorized patch-diff workflow for deriving and validating vulnerability variants from a known vulnerable-to-fixed source change.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./packages/decepticon/decepticon/skills/standard/analyst/patch-diff/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 a tight, well-structured workflow with explicit validation checkpoints, independent verification of candidates, and a concrete promotion gate; it is an efficient, actionable instruction-only skill with no padding.

DimensionReasoningScore

Conciseness

The body is lean and efficient with no padding or explanation of concepts Claude already knows; every line (the loop steps, artifact tree, promotion gate) earns its place, matching the 5 anchor.

5 / 5

Actionability

Concrete, specific guidance throughout (record commits/hashes/build commands, identify source/guard/sink/trust boundary, run validate_workspace_finding per candidate, produce named artifacts) with only minor gaps since no literal executable commands are given, fitting the 4 anchor for an instruction-only skill.

4 / 5

Workflow Clarity

A clear six-step sequence with explicit validation checkpoints (positive must reproduce, fixed-side negative control, independent per-candidate validation) and a promotion feedback loop, matching the 5 anchor.

5 / 5

Progressive Disclosure

Under 50 lines with no external references needed, organized into clear sections (Inputs, Loop, Required artifacts) and an artifact tree, which per the scoring notes earns a 5 for well-structured simple skills.

5 / 5

Total

19

/

20

Passed

Description

53%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 distinct, clearly stating what the skill does in third person, but it lacks an explicit "when to use" trigger clause and broader natural synonyms, which cap completeness and trigger quality at 3.

Suggestions

Add an explicit "Use when..." clause naming natural triggers (e.g., "Use when analyzing patch diffs, n-day variants, or known vulnerable-to-fixed source changes").

Include common synonyms a user would actually say, such as n-day, advisory, CVE, or regression, to broaden trigger coverage.

Optionally list one or two more concrete actions (e.g., "builds differential tests") to lift specificity toward comprehensive coverage.

DimensionReasoningScore

Specificity

Names the patch-diff domain and two concrete actions ("deriving and validating vulnerability variants") but stops at two actions without comprehensive coverage of the workflow's steps, matching the 3 anchor.

3 / 5

Completeness

The "what" is clearly stated (deriving/validating variants from a source change) but there is no "Use when..." clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Includes relevant terms ("patch-diff", "vulnerability variants", "vulnerable-to-fixed source change") but omits common synonyms a user might say (n-day, advisory, CVE, regression), fitting the 3 anchor.

3 / 5

Distinctiveness Conflict Risk

The patch-diff variant niche is clearly distinct from general skills with minimal conflict risk, though the technical phrasing leaves minor overlap with broader vulnerability-research skills, fitting the 4 anchor.

4 / 5

Total

13

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

PurpleAILAB/Decepticon

Path

packages/decepticon/decepticon/skills/standard/analyst/patch-diff/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.