CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

oss-forensics

GitHub supply-chain forensics: recovery, IOCs, reporting.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/security/oss-forensics/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

This is a strong, operationally dense skill: a clearly sequenced 7-phase workflow with genuine mechanical validation gates, feedback loops, and copy-paste executable commands for most investigators. The main defects are the missing templates/forensic-report.md file that Phase 0 depends on, and a few prose-level steps (Investigator 5 enrichment, Phase 3 hash verification) that lack executable guidance.

DimensionReasoningScore

Conciseness

The body is dense and operational — commands, role boundaries, and rules — with essentially no explanation of concepts Claude already knows. Minor over-explanation exists (the three Example Scenarios, the long guardrail-8 prose, and parts of the ethical-use section could be trimmed or moved), matching the level-4 anchor rather than level 5's every-token-earns-its-place.

4 / 5

Actionability

Most investigators give copy-paste ready commands with concrete detection patterns (e.g., "git fsck --lost-found --unreachable", the BigQuery "payload.distinct_size = 0 AND payload.size > 0" force-push indicator), matching level 4-5. Investigator 5's actions ("check passive DNS, WHOIS records") and Phase 3's hash verification remain prose-level without executable steps, which are minor gaps keeping it below 5.

4 / 5

Workflow Clarity

The 8 phases (0-7) are clearly sequenced, with an explicit mechanical validation gate in Phase 5 (hard failure on missing evidence IDs; VALIDATED/INCONCLUSIVE/REJECTED outcomes) and feedback loops (rejected hypotheses re-enter Phase 4, max 3 iterations) plus error-recovery paths for rate limits and missing BigQuery credentials. This matches the level-5 anchor: explicit validation, feedback loops, and checklists.

5 / 5

Progressive Disclosure

The bundle structure is good: four real reference files and one real script, each referenced one level deep at point of use with a summary Reference Materials section, matching the level-4 anchor. It is not level 5 because templates/forensic-report.md is referenced three times (Phase 0, Phase 6, Reference Materials) but no templates/ directory exists in the bundle, breaking Phase 0's first concrete step — a notable organization gap.

4 / 5

Total

17

/

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 concise and names a distinct, well-scoped domain, but it reads as a terse label rather than an operational description. It lacks any "Use when..." trigger guidance and its capability list uses compressed jargon nouns instead of concrete actions, which limits discovery and completeness.

Suggestions

Add a "Use when..." clause with natural user phrasings, e.g., "Use when the user asks to investigate a repository for supply-chain compromise, recover deleted or force-pushed commits, or extract IOCs from a suspicious repo."

Expand the one-word capability nouns into concrete actions: "recovers deleted commits and force-pushed history, extracts indicators of compromise, and generates evidence-cited forensic reports" instead of "recovery, IOCs, reporting".

Include common natural terms users would actually say ("compromised", "suspicious commit", "force push", "malicious package") and avoid unexplained jargon like "IOCs".

DimensionReasoningScore

Specificity

"GitHub supply-chain forensics: recovery, IOCs, reporting" names a clear domain and three capability areas, but each is a compressed one-word label rather than the concrete, explicit actions of the level-4 anchor (e.g., "recovers deleted commits, extracts IOCs, generates forensic reports"). It is above the level-2 anchor's single generic action, so it fits the level-3 anchor: domain plus a few concrete actions, not comprehensive.

3 / 5

Completeness

The "what" is clearly stated (supply-chain forensics covering recovery, IOCs, reporting), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not level 2 because the "what" is specific, not vague.

3 / 5

Trigger Term Quality

The terms "supply-chain", "forensics", and "recovery" are relevant keywords, but "IOCs" is technical jargon and the natural phrases a user would say ("was this repo compromised", "suspicious commit", "force push", "investigate this repo") are missing from the description. This matches the level-3 anchor (some relevant keywords, missing common variations) rather than level 4's good coverage.

3 / 5

Distinctiveness Conflict Risk

"GitHub supply-chain forensics" carves a clear niche with minimal overlap risk against most skills, matching the level-4 anchor. It falls short of level 5 because the generic tail words ("recovery", "reporting") could pull in general git or reporting skills, and the description carries no distinct trigger phrases to disambiguate.

4 / 5

Total

13

/

20

Passed

Validation

75%

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

Validation — 12 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 2 missing

Warning

Total

12

/

16

Passed

Repository

NousResearch/hermes-agent

Path

optional-skills/security/oss-forensics/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.