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.

Quality

69%

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/capability-primitive-search/SKILL.md

Quality

Content

67%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 a token-efficient, highly actionable mental model with a real validation checkpoint, but it is presented as one unstructured wall of text with no progressive disclosure or section navigation.

Suggestions

Break the single code block into markdown sections (Mental model, RCE equations, Low-severity mapping, Search procedure, Breakthroughs, Validation) so the structure is navigable.

Pull the equation table and low-severity→primitive mapping into a separate reference file and link to it one level deep from SKILL.md.

Add an explicit validation checklist (e.g. per-segment verify → evidence → confirm Fact / record_vulnerability) rather than embedding it as a trailing prose line.

Dimension	Reasoning	Score
Conciseness	The body is a dense, mnemonic-style block with no padding and no over-explanation of concepts Claude already knows; it is efficient, though the extreme compression occasionally trades away readability.	4 / 5
Actionability	As an instruction-only methodology skill it gives concrete, specific guidance — RCE equations A-F, low-severity→primitive mappings, and named RCE-equivalent sinks (crontab/.bashrc/LD_PRELOAD/authorized_keys/systemd unit) — with only minor gaps.	4 / 5
Workflow Clarity	A clear sequenced search procedure is laid out (state/action/goal, forward then backward, meet-in-the-middle, '逐段验证') with an explicit validation gate that chains stay tentative until executed with evidence, though it lacks a clean checklist format.	4 / 5
Progressive Disclosure	No bundle files exist and the entire body is a single monolithic code block with one heading and only inline pseudo-section labels, giving minimal navigable structure.	2 / 5
	Total	14 / 20 Passed

Description

71%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 a distinctive, trigger-rich summary that names concrete primitives and an explicit 'Use when' condition. Its main weakness is jargon density and missing natural-language synonyms, which slightly hurt trigger-term quality and completeness.

Suggestions

Add plain-language synonyms to the 'Use when' clause (e.g. 'privilege escalation', 'exploit chaining', 'lateral movement') so users phrase the need naturally.

Soften the compressed jargon in the 'what' portion with one readable clause stating the skill's purpose in common terms.

Consider adding file-extension or tool-agnostic trigger phrasing if this skill should also fire on broader red-team engagement requests.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions/primitives (read/write/exec/ssrf, RCE equations A-F, low-severity mapping, forward/backward search, cross-domain realization) rather than vague language, though the compressed jargon leaves minor coverage gaps.	4 / 5
Completeness	Both 'what' (assemble RCE via capability primitives + state-space search) and 'when' (explicit 'Use when...' trigger phrases) are present and concrete, but the 'what' is dense enough that it could be clearer.	4 / 5
Trigger Term Quality	The 'Use when no single RCE, chaining low-severity vulns, or deriving novel attack chains' clause supplies relevant keywords, but it is jargon-dense and mixed-language with missing common synonyms (e.g. privilege escalation, lateral movement, exploit chain).	3 / 5
Distinctiveness Conflict Risk	It carves a clear niche (low-severity vuln chaining into RCE via primitive equations) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	16 / 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
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: Ed1s0nZ/CyberStrikeAI
Path: skills/capability-primitive-search/SKILL.md
Commit: 893f134

Reviewed: 2 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.