CtrlK
BlogDocsLog inGet started
Tessl Logo

capability-primitive-search

能力原语+状态空间搜索:read/write/exec/ssrf等原语凑RCE等式A-F,低危映射,正反向搜索,跨域兑现。Use when no single RCE, chaining low-severity vulns, or deriving novel attack chains.

76

Quality

96%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%

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

A lean, highly actionable methodology body with a clear sequenced search workflow and explicit validation gate. Its main weakness is organization: everything sits in one undifferentiated code block with no section headers, which slightly hurts navigability despite the short length.

Suggestions

Break the single code block into headed markdown sections (e.g. ## Primitives, ## RCE equations A-F, ## Low-severity→primitive map, ## State-space search, ## Breakthrough heuristics) so the body is scannable rather than a monolithic block.

Pull the closing validation note (tentative vs confirmed, verify each step) out of the code block into a short ## Verification section so the validation gate is visually prominent.

Consider extracting the low-severity→primitive mapping table into a references/ file if the body grows, keeping SKILL.md as a concise overview.

DimensionReasoningScore

Conciseness

Dense, terse methodology prose that assumes Claude's competence and adds domain-specific heuristics Claude would not already have; no padding or explanation of generic concepts.

3 / 3

Actionability

Concrete, specific guidance throughout — named primitives, equations A-F, exact mappings (e.g. 'SSRF→内网Redis/Consul/K8s/云元数据→C', 'SQLi→OUTFILE→A') and equivalent RCE sinks (crontab/.bashrc/LD_PRELOAD/authorized_keys/systemd unit).

3 / 3

Workflow Clarity

Provides a sequenced search procedure (forward capability-combination and reverse goal→subgoal decomposition with arrow-chained steps) plus an explicit validation gate: chains stay tentative until executed with evidence, and '整条链每步都验证过才成立'.

3 / 3

Progressive Disclosure

The skill is short (~36 lines) with no external bundle files, so no file-level disclosure is needed, but the entire body is a single monolithic code block with no internal section headers or navigation, unlike the well-organized sections the rubric rewards for sub-50-line skills.

2 / 3

Total

11

/

12

Passed

Description

100%

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 states concrete capabilities and an explicit trigger, covering both what and when in a distinctive niche. The only minor caveat is that the bulk is dense Chinese jargon, but the English trigger clause is clear and natural for the target audience.

DimensionReasoningScore

Specificity

Names concrete primitives (read/write/exec/ssrf), RCE equations A-F, low-severity mappings, and forward/reverse search directions — multiple specific concrete actions rather than vague language.

3 / 3

Completeness

Explicitly answers both what (assembling primitives into RCE equations A-F, low-severity mapping, bidirectional search, cross-domain realization) and when (explicit 'Use when...' clause).

3 / 3

Trigger Term Quality

The trigger 'Use when no single RCE, chaining low-severity vulns, or deriving novel attack chains' uses natural terms a pentester would say when needing this skill.

3 / 3

Distinctiveness Conflict Risk

A clearly delineated primitive-chain/state-space-search niche with a distinct trigger unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
Ed1s0nZ/CyberStrikeAI
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.