trailmark-summary
- Repo stars 5,723
- Forks 499
- Author updated Jun 15, 2026, 04:05 PM
- Author repo skills
- Domain
- AI
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @trailofbits · no license declared
- Token usage
- Lean
- Setup complexity
- Guided setup
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- Python
- Permissions
-
- Read-only
- Shell exec
- Write / modify
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: trailmark-summary
description: Runs a Trailmark summary analysis on a codebase. Returns auto-detected languages, entry point co…
category: ai
runtime: Python
---
# trailmark-summary output preview
## PART A: Task fit
- Use case: Runs a Trailmark summary analysis on a codebase. Returns auto-detected languages, entry point count, and dependency list. Use when vivisect or galvanize needs a quick structural overview. Triggers: trailmark summary, code summary, structural overview..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “When to Use / When NOT to Use / Rationalizations to Reject” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Runs a Trailmark summary analysis on a codebase. Returns auto-detected languages, entry point count, and dependency list. Use when vivisect or galvanize needs a quick structural overview. Triggers: trailmark summary, code summary, structural overview.”.
- **02** When the source has headings, the agent prioritizes “When to Use / When NOT to Use / Rationalizations to Reject” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, run shell commands, write/modify files; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, run shell commands, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options.The source does not require a stable slash command. After installation, invoke the skill by name and describe the task.
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, run shell commands, write/modify files.
Start with a small task and check whether the result follows “When to Use / When NOT to Use / Rationalizations to Reject”. Inspect diffs, logs, previews, or tests before expanding scope.
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: trailmark-summary
description: Runs a Trailmark summary analysis on a codebase. Returns auto-detected languages, entry point co…
category: ai
source: trailofbits/skills
---
# trailmark-summary
## When to use
- Runs a Trailmark summary analysis on a codebase. Returns auto-detected languages, entry point count, and dependency li…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “When to Use / When NOT to Use / Rationalizations to Reject” and keep inference separate from source facts.
- read files, run shell commands, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies.The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "trailmark-summary" {
input -> user goal + target files + boundaries + acceptance criteria
context -> When to Use / When NOT to Use / Rationalizations to Reject
rules -> SKILL.md triggers / order / output contract
runtime -> Python | read files, run shell commands, write/modify files | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}Trailmark Summary
Runs trailmark analyze --language auto --summary on a target directory.
When to Use
- Vivisect Phase 0 needs a quick structural overview before decomposition
- Galvanize Phase 1 needs detected languages and entry point count
- Quick orientation on an unfamiliar codebase before deeper analysis
When NOT to Use
- Full structural analysis with all passes needed (use
trailmark-structural) - Detailed code graph queries (use the main
trailmarkskill directly) - You need hotspot scores or taint data (use
trailmark-structural)
Rationalizations to Reject
| Rationalization | Why It's Wrong | Required Action |
|---|---|---|
| "I can read the code manually instead" | Manual reading misses parser-based language detection, dependency data, and entry point enumeration | Install and run trailmark |
| "Language detection doesn't matter" | Wrong language selection produces empty or partial analysis | Use Trailmark's parser-based detection or --language auto |
| "Partial output is good enough" | Missing any of the three required outputs (detected languages, entry points, dependencies) means incomplete analysis | Verify all three are present |
| "Tool isn't installed, I'll skip it" | This skill exists specifically to run trailmark | Report the installation gap instead of skipping |
Usage
The target directory is passed via the args parameter.
Execution
Step 1: Check that trailmark is available.
trailmark analyze --help 2>/dev/null || \
uv run trailmark analyze --help 2>/dev/nullIf neither command works, report "trailmark is not installed"
and return. Do NOT run pip install, uv pip install,
git clone, or any install command. The user must install
trailmark themselves.
Step 2: Detect languages with Trailmark's parse API.
python3 - "{args}" <<'PY'
import json
import sys
from trailmark.parse import detect_languages
print(json.dumps(detect_languages(sys.argv[1])))
PYIf the import fails, rerun the same snippet with uv run python - "{args}".
If the result is [], report "Trailmark found no supported languages under
target" and return.
Step 3: Run the summary with auto-detection.
trailmark analyze --language auto --summary {args} 2>&1 || \
uv run trailmark analyze --language auto --summary {args} 2>&1Step 4: Verify the output.
The output must include ALL THREE of:
- Detected languages from Step 2
Entrypoints:line from the summary outputDependencies:line from the summary output
If any are missing, report the gap. Do not fabricate output.
Return the detected language list plus the full Trailmark summary output.
Decide Fit First
Design Intent
How To Use It
Boundaries And Review