CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

c2-sliver

Sliver C2 operations through hosted E2B MCP tools or an explicitly available standalone console.

Quality

74%

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/post-exploit/c2-sliver/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%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 actionable, well-sequenced operational guide: executable commands with exact flags and tool-call parameters, explicit connection and validation checkpoints, and an end-of-skill validation checklist. Its main structural weakness is duplication — the inlined standalone CLI reference overlaps heavily with the bundled quickstart file, so the split between SKILL.md and the reference is not clean.

DimensionReasoningScore

Conciseness

The body is dominated by lean, commented command blocks that earn their tokens, with only minor over-explanation: the one-sentence framework intro, the "OPSEC: Implant Hardening" section re-demonstrating --skip-symbols already mandated above, and the output-format table duplicated in the reference file. It is not 5 because these few sections could be trimmed; not 3 because padding is incidental, not pervasive.

4 / 5

Actionability

Commands are fully executable and copy-paste ready: exact listener/implant/beacon/stager/shellcode invocations with flags and save paths, concrete bash(...) calls including session="c2", is_input=True, and timeout=300, plus a complete JSON HTTP C2 profile. The common cases (HTTPS/mTLS listeners, Windows/Linux implants, session and beacon management, pivoting) are all covered with runnable examples.

5 / 5

Workflow Clarity

Both paths are explicitly sequenced: the standalone connection procedure is a numbered 4-step list with a reachability checkpoint (nc -z ... C2_OK/C2_DOWN), a conditional skip ("skip if already imported"), and an error-recovery branch ("If multiple configs found..."), while the hosted path orders c2_ensure → listenerUrl → generate → stage/import, and Section 9 provides an end-to-end validation checklist. Checkpoints and error branches are explicit, matching the top anchor rather than the "most checkpoints" wording of anchor 4.

5 / 5

Progressive Disclosure

The single bundle reference (references/sliver-quickstart.md) is real and clearly signaled in a dedicated "Bundled Resources" section, but the body inlines roughly 300 lines of standalone CLI command reference that substantially duplicates that file's content (listeners, implant generation, post-implant ops, pivoting, OPSEC). Content that clearly belongs in the reference file is inlined in SKILL.md, which matches anchor 3 rather than 4's "most content is appropriately placed".

3 / 5

Total

17

/

20

Passed

Description

52%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 identifies a distinct, low-conflict niche (Sliver C2) and distinguishes its two access modes, but it reads more like a scope declaration than a capability description: it lists no concrete operations and omits any "Use when" trigger guidance from the description field itself. Trigger keywords like implant, beacon, listener, armory, and BOF exist only in the metadata when_to_use field, not in the description.

Suggestions

Replace the generic word "operations" with 2-3 concrete capabilities, e.g. "Run Sliver C2 listeners, generate implants and beacons, execute BOFs, and pivot through compromised hosts".

Add an explicit trigger clause to the description, e.g. "Use when the user mentions Sliver, sliver-client, implants, beacons, armory, or BOFs" — currently that guidance lives only in metadata.when_to_use and is invisible to description-only consumers.

Surface the natural trigger terms (implant, beacon, listener, armory, BOF) inside the description text itself so keyword matching works without relying on the separate when_to_use field.

DimensionReasoningScore

Specificity

The description names the domain ("Sliver C2") and two access paths ("hosted E2B MCP tools", "an explicitly available standalone console"), but "operations" is generic — no concrete capabilities such as listeners, implants, beacons, or pivoting are stated. It sits between anchor 2 (domain named, actions minimal or generic) and anchor 3, closer to 2 because no concrete action is listed.

2 / 5

Completeness

The "what" is reasonably clear (Sliver C2 operations through two access paths), but the description contains no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is not 2 because the "what" is specific, not vague; not 4 because the "when" is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

"Sliver" and "C2" are relevant natural keywords, but common variations a user would say (implant, beacon, listener, armory, BOF) are absent from the description — they only appear in a separate metadata when_to_use field. This matches anchor 3 (some relevant keywords, missing common variations) rather than 4, since coverage is thin within the description itself.

3 / 5

Distinctiveness Conflict Risk

"Sliver" names a specific open-source C2 framework, giving the description a clear niche with distinct triggers and minimal conflict risk against unrelated skills. Only other Sliver-specific skills would overlap, which is expected.

5 / 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/post-exploit/c2-sliver/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.