CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

secure-workflow-guide

Guides through Trail of Bits' 5-step secure development workflow. Runs Slither scans, checks special features (upgradeability/ERC conformance/token integration), generates visual security diagrams, helps document security properties for fuzzing/verification, and reviews manual security areas. Use when securing a smart contract end to end rather than hunting one bug, checking a project on every check-in or before deployment, triaging a Slither report, or asking where to start on smart contract security.

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 ./plugins/building-secure-contracts/skills/secure-workflow-guide/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

56%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 presents a clear, well-sequenced 5-step workflow with a notably strong rationalization table that pre-empts skipped steps, but it is padded with three overlapping summary sections, provides no executable commands itself, and its two referenced detail files are missing from the bundle, undermining its progressive-disclosure structure.

Suggestions

Create resources/WORKFLOW_STEPS.md and resources/EXAMPLE_REPORT.md (or fix the link paths) so the referenced detail files actually exist in the bundle — the current links are dead.

Consolidate the redundant "Example Output", "What You'll Get", and "Workflow Checklist" sections into a single compact output description to cut duplicated content.

Add at least the key executable commands inline (e.g., the slither --print commands for the three diagrams, slither-check-erc usage) so the body is actionable without the missing reference file.

DimensionReasoningScore

Conciseness

Mostly efficient with bullet lists and a useful rationalization table, but the "Example Output", "What You'll Get", and "Workflow Checklist" sections substantially repeat the step descriptions and each other (e.g., Slither findings/severity/fixes appear in Steps 1, Example Output, and What You'll Get), and the "Ready to Start" section is pure filler. This matches the anchor for content that is mostly efficient but could be tightened, rather than the leaner level-4 anchor.

3 / 5

Actionability

Tool names are concrete (slither-check-upgradeability, slither-check-erc, slither-prop, Echidna, Manticore, "slither --print commands") but the body contains no actual commands, flags, or copy-paste examples — execution details are deferred to a referenced file. This sits at 'some concrete guidance but incomplete; missing key details', below the level-4 anchor of mostly executable guidance with concrete commands.

3 / 5

Workflow Clarity

The 5-step sequence is explicit, each step has a stated goal (e.g., "Goal: Clean Slither report or documented triages"), and the "How I Work" section and rationalization table provide ordering and skip-guards. Validation checkpoints are only implicit (goals stated but no verify-then-proceed loops), which keeps it just below the level-5 anchor; the operations are read-only analysis, so the destructive-operation cap does not apply.

4 / 5

Progressive Disclosure

The body is well structured as an overview and clearly signals two one-level-deep references ([WORKFLOW_STEPS.md](resources/WORKFLOW_STEPS.md) and [EXAMPLE_REPORT.md](resources/EXAMPLE_REPORT.md)), but neither referenced file exists in the bundle — only assets/trail-of-bits-mark.svg is present. The structure earns level 4, but the broken disclosure promise (detail content entirely absent) drags it to 'some structure but could be better organized' with references that cannot actually be navigated.

3 / 5

Total

13

/

20

Passed

Description

88%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.

A strong description in third-person voice that clearly states what the skill does with concrete enumerated capabilities and gives an explicit, well-phrased 'Use when...' clause covering end-to-end reviews, check-in/pre-deployment checks, Slither triage, and getting-started scenarios. Its only weakness is trigger-term breadth — synonyms like 'audit' or 'security review' are not covered.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "Runs Slither scans", "checks special features (upgradeability/ERC conformance/token integration)", "generates visual security diagrams", "helps document security properties for fuzzing/verification", "reviews manual security areas" — comprehensively covering the workflow's scope. This matches the anchor for multiple specific concrete actions with comprehensive coverage, not the level 4 anchor which implies minor gaps.

5 / 5

Completeness

It explicitly answers both what ("Guides through Trail of Bits' 5-step secure development workflow" plus enumerated actions) and when ("Use when securing a smart contract end to end rather than hunting one bug, checking a project on every check-in or before deployment, triaging a Slither report, or asking where to start"). This mirrors the level-5 example's structure of clear what + concrete trigger phrases, and clearly exceeds level 4 where the 'when' could be more explicit.

5 / 5

Trigger Term Quality

Includes natural trigger phrases like "triaging a Slither report", "on every check-in or before deployment", "hunting one bug", and "where to start on smart contract security". Good coverage, but common variations such as "audit", "security review", or "fuzzing setup" are absent, so it falls just short of the comprehensive-with-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

The niche is distinct — Trail of Bits' 5-step workflow, Slither tooling, smart-contract security — with specific triggers unlikely to fire for unrelated skills. However, it would overlap with a dedicated Slither/audit skill since it bundles scanning as Step 1, so it is 'mostly distinct with minor overlap risk' rather than fully minimal conflict.

4 / 5

Total

18

/

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

relative_links

Relative link issues: 2 missing

Warning

Total

15

/

16

Passed

Repository

trailofbits/skills

Path

plugins/building-secure-contracts/skills/secure-workflow-guide/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.