← All skills
assess
69 / 100 · Review before installing
Check before installing. Some of what it can do is expected: a coding skill usually runs build and test commands.
By bjcoombs/ai-native-toolkit (GitHub) · coding · 32 stars · scanned at commit f31582e
Assess a codebase's readiness for AI agent contributors using the layered contract model, and generate a complexity hotspot SVG treemap (size = LOC, hue = cyclomatic complexity, saturation = recent git churn). TRIGGER when the user types /assess, asks for an AI-readiness review, wants a complexity heatmap or hotspot map, asks 'how complex is this code?', wants migration risk triage, or asks for a codebase snapshot/report. Produces an MD report + SVG that can be opened as a PR in the target repo.
Works with any agent that supports SKILL.md skills.
Partially scanned — some files couldn't be read; we'll retry on the next scan
What this skill can do
Runs commands on your computer
This is disclosed by the author in the skill's SKILL.md or README. Expected for a coding skill.
Found in 126 places.
Show 17 more
- skills/assess/SKILL.md, line 127
[ "$(uname)" = "Darwin" ] && command -v brew >/dev/null && brew install scc - skills/assess/SKILL.md, line 155
PY_FILES=$(fd -t f -e py . "$REPO_ROOT" 2>/dev/null | wc -l | tr -d ' ') - skills/assess/SKILL.md, line 201
jq '.capability_offers' "$REPO_ROOT/.assess/run-context.json" - skills/assess/SKILL.md, line 236
uv run "${CLAUDE_SKILL_DIR}/scripts/complexity-treemap.py" "$REPO_ROOT" --exclude regulatory-raw --exclude vetted-context --exclude '*.csv' - skills/assess/SKILL.md, line 279
if [ -f "$REPO_ROOT/.assess/complexity-stats.json" ]; then - skills/assess/SKILL.md, line 317
jq '.test_focus' "$REPO_ROOT/.assess/run-context.json" - skills/assess/SKILL.md, line 330
FOCUS_FILES=$(jq -r '.test_focus.entries[] | select(.test_signal == "covered_but_hollow" or .test_signal == "sibling_test_only") | .path | select(split("/") as - skills/assess/SKILL.md, line 355
uv run "${CLAUDE_SKILL_DIR}/scripts/assess_core.py" "$REPO_ROOT" --opt-in-mutation - skills/assess/SKILL.md, line 385
jq '.diff, .diff_detail' "$REPO_ROOT/.assess/run-context.json" - skills/assess/SKILL.md, line 415
mkdir -p "$REPO_ROOT/.assess/.cache" - skills/assess/scripts/assess_emit_workflow.py, line 81
out = subprocess.run(cmd, capture_output=True, text=True, timeout=20, check=False) - skills/assess/scripts/assess_emit_workflow.py, line 82
except (OSError, subprocess.SubprocessError) as exc: - skills/assess/scripts/assess_emit_workflow.py, line 154
out = subprocess.run( - skills/assess/scripts/assess_emit_workflow.py, line 161
except (OSError, subprocess.SubprocessError): - skills/assess/scripts/complexity-treemap.py, line 314
raw = subprocess.run( - skills/assess/scripts/complexity-treemap.py, line 319
except (subprocess.CalledProcessError, FileNotFoundError) as e: - skills/assess/scripts/complexity-treemap.py, line 835
out = subprocess.run(
and 106 more places
Downloads and installs other software
The author does not mention this.
Found in 21 places.
Show 17 more
- skills/assess/SKILL.md, line 132
|| command -v dnf >/dev/null && sudo dnf install -y scc \ - skills/assess/SKILL.md, line 133
|| command -v go >/dev/null && go install github.com/boyter/scc/v3@latest \ - skills/assess/SKILL.md, line 176
&& OFFERS+=("coverage|scc|brew install scc (or apt/dnf/go install - see Step 2a)") - skills/assess/SKILL.md, line 177
needs_offer vulture "$PY_FILES" && OFFERS+=("python|vulture|pip install vulture (or 'uv tool install vulture')") - skills/assess/SKILL.md, line 178
needs_offer ts-prune "$TS_FILES" && [ -f "$REPO_ROOT/tsconfig.json" ] && OFFERS+=("typescript|ts-prune|npm install -g ts-prune") - skills/assess/SKILL.md, line 179
needs_offer staticcheck "$GO_FILES" && OFFERS+=("go|staticcheck|go install honnef.co/go/tools/cmd/staticcheck@latest (or 'brew install staticcheck')") - skills/assess/SKILL.md, line 192
> "This repo has 47 Go files. `staticcheck -checks U1000` would let `/assess` flag unreachable Go funcs as Layer 1 candidates. Install? (`go install honnef.co/g - skills/assess/scripts/lib/agent_environment.py, line 463
if head in ("uv", "poetry", "uvx"): - skills/assess/scripts/lib/agent_environment.py, line 465
if head != "uvx": - skills/assess/scripts/lib/ci_workflow.py, line 42
+ " run: go install github.com/boyter/scc/v3@v3.7.0\n" - skills/assess/scripts/lib/ci_workflow.py, line 47
+ " run: go install honnef.co/go/tools/cmd/staticcheck@2026.1\n" - skills/assess/scripts/lib/ci_workflow.py, line 52
+ " run: npm install -g ts-prune@0.10.3\n" - skills/assess/scripts/lib/ci_workflow.py, line 57
+ " run: npm install -g knip@6.16.1\n" - skills/assess/scripts/lib/command_resolver.py, line 31
script or ``[tool.*]`` table, a file), uvx, tox (``-e`` environments), nox - skills/assess/scripts/lib/command_resolver.py, line 536
if words[0] == "uvx": - skills/assess/scripts/lib/command_resolver.py, line 726
"uv": _uv, "uvx": _uv, "poetry": _poetry, "tox": _tox, "nox": _nox, - skills/assess/scripts/lib/liveness_scan.py, line 225
"(npm install -g knip)"),
and 1 more places
Reads your saved credentials, such as SSH keys or .env files
This is disclosed by the author in the skill's SKILL.md or README.
Found in 2 places.
Connects to the internet
This is disclosed by the author in the skill's SKILL.md or README.
Found in 1 place.
Safer alternatives
Low-risk skills in the same category (coding) that look related. Check that one does what you need.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'assess' ] || [ -L ~/.agents/skills/'assess' ]; then echo 'A skill folder named assess already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/bjcoombs/ai-native-toolkit' "$d" && git -C "$d" checkout --quiet 'f31582e1c9fe75950a9e522649565b93e3072fe0' -- 'skills/assess' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/assess' ~/.agents/skills/'assess' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'assess' ~/.claude/skills/'assess' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
The badge for bjcoombs/ai-native-toolkit shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/bjcoombs/ai-native-toolkit/)
Score history
| Date | Version | Score |
|---|
| 2026-11-13 | f31582e | 69 |
| 2026-11-07 | 82a6017 | 69 |